Evidence Networks: simple losses for fast, amortized, neural Bayesian model comparison [CL]

http://arxiv.org/abs/2305.11241


Evidence Networks can enable Bayesian model comparison when state-of-the-art methods (e.g. nested sampling) fail and even when likelihoods or priors are intractable or unknown. Bayesian model comparison, i.e. the computation of Bayes factors or evidence ratios, can be cast as an optimization problem. Though the Bayesian interpretation of optimal classification is well-known, here we change perspective and present classes of loss functions that result in fast, amortized neural estimators that directly estimate convenient functions of the Bayes factor. This mitigates numerical inaccuracies associated with estimating individual model probabilities. We introduce the leaky parity-odd power (l-POP) transform, leading to the novel “l-POP-Exponential” loss function. We explore neural density estimation for data probability in different models, showing it to be less accurate and scalable than Evidence Networks. Multiple real-world and synthetic examples illustrate that Evidence Networks are explicitly independent of dimensionality of the parameter space and scale mildly with the complexity of the posterior probability density function. This simple yet powerful approach has broad implications for model inference tasks. As an application of Evidence Networks to real-world data we compute the Bayes factor for two models with gravitational lensing data of the Dark Energy Survey. We briefly discuss applications of our methods to other, related problems of model comparison and evaluation in implicit inference settings.

Read this paper on arXiv…

N. Jeffrey and B. Wandelt
Mon, 22 May 23
12/60

Comments: 21 pages, 8 figures

Photo-zSNthesis: Converting Type Ia Supernova Lightcurves to Redshift Estimates via Deep Learning [CEA]

http://arxiv.org/abs/2305.11869


Upcoming photometric surveys will discover tens of thousands of Type Ia supernovae (SNe Ia), vastly outpacing the capacity of our spectroscopic resources. In order to maximize the science return of these observations in the absence of spectroscopic information, we must accurately extract key parameters, such as SN redshifts, with photometric information alone. We present Photo-zSNthesis, a convolutional neural network-based method for predicting full redshift probability distributions from multi-band supernova lightcurves, tested on both simulated Sloan Digital Sky Survey (SDSS) and Vera C. Rubin Legacy Survey of Space and Time (LSST) data as well as observed SDSS SNe. We show major improvements over predictions from existing methods on both simulations and real observations as well as minimal redshift-dependent bias, which is a challenge due to selection effects, e.g. Malmquist bias. The PDFs produced by this method are well-constrained and will maximize the cosmological constraining power of photometric SNe Ia samples.

Read this paper on arXiv…

H. Qu and M. Sako
Mon, 22 May 23
25/60

Comments: submitted to ApJ

Assessing Exoplanet Habitability through Data-driven Approaches: A Comprehensive Literature Review [EPA]

http://arxiv.org/abs/2305.11204


The exploration and study of exoplanets remain at the frontier of astronomical research, challenging scientists to continuously innovate and refine methodologies to navigate the vast, complex data these celestial bodies produce. This literature the review aims to illuminate the emerging trends and advancements within this sphere, specifically focusing on the interplay between exoplanet detection, classification, and visualization, and the the increasingly pivotal role of machine learning and computational models. Our journey through this realm of exploration commences with a comprehensive analysis of fifteen meticulously selected, seminal papers in the field. These papers, each representing a distinct facet of exoplanet research, collectively offer a multi-dimensional perspective on the current state of the field. They provide valuable insights into the innovative application of machine learning techniques to overcome the challenges posed by the analysis and interpretation of astronomical data. From the application of Support Vector Machines (SVM) to Deep Learning models, the review encapsulates the broad spectrum of machine learning approaches employed in exoplanet research. The review also seeks to unravel the story woven by the data within these papers, detailing the triumphs and tribulations of the field. It highlights the increasing reliance on diverse datasets, such as Kepler and TESS, and the push for improved accuracy in exoplanet detection and classification models. The narrative concludes with key takeaways and insights, drawing together the threads of research to present a cohesive picture of the direction in which the field is moving. This literature review, therefore, serves not just as an academic exploration, but also as a narrative of scientific discovery and innovation in the quest to understand our cosmic neighborhood.

Read this paper on arXiv…

M. Jakka
Mon, 22 May 23
33/60

Comments: N/A

MiraBest: A Dataset of Morphologically Classified Radio Galaxies for Machine Learning [IMA]

http://arxiv.org/abs/2305.11108


The volume of data from current and future observatories has motivated the increased development and application of automated machine learning methodologies for astronomy. However, less attention has been given to the production of standardised datasets for assessing the performance of different machine learning algorithms within astronomy and astrophysics. Here we describe in detail the MiraBest dataset, a publicly available batched dataset of 1256 radio-loud AGN from NVSS and FIRST, filtered to $0.03 < z < 0.1$, manually labelled by Miraghaei and Best (2017) according to the Fanaroff-Riley morphological classification, created for machine learning applications and compatible for use with standard deep learning libraries. We outline the principles underlying the construction of the dataset, the sample selection and pre-processing methodology, dataset structure and composition, as well as a comparison of MiraBest to other datasets used in the literature. Existing applications that utilise the MiraBest dataset are reviewed, and an extended dataset of 2100 sources is created by cross-matching MiraBest with other catalogues of radio-loud AGN that have been used more widely in the literature for machine learning applications.

Read this paper on arXiv…

F. Porter and A. Scaife
Fri, 19 May 23
7/46

Comments: 14 pages, 2 figures, accepted by RASTI

PPDONet: Deep Operator Networks for Fast Prediction of Steady-State Solutions in Disk-Planet Systems [EPA]

http://arxiv.org/abs/2305.11111


We develop a tool, which we name Protoplanetary Disk Operator Network (PPDONet), that can predict the solution of disk-planet interactions in protoplanetary disks in real-time. We base our tool on Deep Operator Networks (DeepONets), a class of neural networks capable of learning non-linear operators to represent deterministic and stochastic differential equations. With PPDONet we map three scalar parameters in a disk-planet system — the Shakura \& Sunyaev viscosity $\alpha$, the disk aspect ratio $h_\mathrm{0}$, and the planet-star mass ratio $q$ — to steady-state solutions of the disk surface density, radial velocity, and azimuthal velocity. We demonstrate the accuracy of the PPDONet solutions using a comprehensive set of tests. Our tool is able to predict the outcome of disk-planet interaction for one system in less than a second on a laptop. A public implementation of PPDONet is available at \url{https://github.com/smao-astro/PPDONet}.

Read this paper on arXiv…

S. Mao, R. Dong, L. Lu, et. al.
Fri, 19 May 23
26/46

Comments: 10 pages, 6 figures, 2 tables; ApJL accepted

Physics-driven machine learning for the prediction of coronal mass ejections' travel times [SSA]

http://arxiv.org/abs/2305.10057


Coronal Mass Ejections (CMEs) correspond to dramatic expulsions of plasma and magnetic field from the solar corona into the heliosphere. CMEs are scientifically relevant because they are involved in the physical mechanisms characterizing the active Sun. However, more recently CMEs have attracted attention for their impact on space weather, as they are correlated to geomagnetic storms and may induce the generation of Solar Energetic Particles streams. In this space weather framework, the present paper introduces a physics-driven artificial intelligence (AI) approach to the prediction of CMEs travel time, in which the deterministic drag-based model is exploited to improve the training phase of a cascade of two neural networks fed with both remote sensing and in-situ data. This study shows that the use of physical information in the AI architecture significantly improves both the accuracy and the robustness of the travel time prediction.

Read this paper on arXiv…

S. Guastavino, V. Candiani, A. Bemporad, et. al.
Thu, 18 May 23
40/67

Comments: N/A

A Conditional Denoising Diffusion Probabilistic Model for Radio Interferometric Image Reconstruction [IMA]

http://arxiv.org/abs/2305.09121


In radio astronomy, signals from radio telescopes are transformed into images of observed celestial objects, or sources. However, these images, called dirty images, contain real sources as well as artifacts due to signal sparsity and other factors. Therefore, radio interferometric image reconstruction is performed on dirty images, aiming to produce clean images in which artifacts are reduced and real sources are recovered. So far, existing methods have limited success on recovering faint sources, preserving detailed structures, and eliminating artifacts. In this paper, we present VIC-DDPM, a Visibility and Image Conditioned Denoising Diffusion Probabilistic Model. Our main idea is to use both the original visibility data in the spectral domain and dirty images in the spatial domain to guide the image generation process with DDPM. This way, we can leverage DDPM to generate fine details and eliminate noise, while utilizing visibility data to separate signals from noise and retaining spatial information in dirty images. We have conducted experiments in comparison with both traditional methods and recent deep learning based approaches. Our results show that our method significantly improves the resulting images by reducing artifacts, preserving fine details, and recovering dim sources. This advancement further facilitates radio astronomical data analysis tasks on celestial phenomena.

Read this paper on arXiv…

R. Wang, Z. Chen, Q. Luo, et. al.
Wed, 17 May 23
5/67

Comments: 8 pages

Solar Active Region Magnetogram Image Dataset for Studies of Space Weather [SSA]

http://arxiv.org/abs/2305.09492


In this dataset we provide a comprehensive collection of magnetograms (images quantifying the strength of the magnetic field) from the National Aeronautics and Space Administration’s (NASA’s) Solar Dynamics Observatory (SDO). The dataset incorporates data from three sources and provides SDO Helioseismic and Magnetic Imager (HMI) magnetograms of solar active regions (regions of large magnetic flux, generally the source of eruptive events) as well as labels of corresponding flaring activity. This dataset will be useful for image analysis or solar physics research related to magnetic structure, its evolution over time, and its relation to solar flares. The dataset will be of interest to those researchers investigating automated solar flare prediction methods, including supervised and unsupervised machine learning (classical and deep), binary and multi-class classification, and regression. This dataset is a minimally processed, user configurable dataset of consistently sized images of solar active regions that can serve as a benchmark dataset for solar flare prediction research.

Read this paper on arXiv…

L. Boucheron, T. Vincent, J. Grajeda, et. al.
Wed, 17 May 23
26/67

Comments: N/A

Identification and Classification of Exoplanets Using Machine Learning Techniques [EPA]

http://arxiv.org/abs/2305.09596


NASA’s Kepler Space Telescope has been instrumental in the task of finding the presence of exoplanets in our galaxy. This search has been supported by computational data analysis to identify exoplanets from the signals received by the Kepler telescope. In this paper, we consider building upon some existing work on exoplanet identification using residual networks for the data of the Kepler space telescope and its extended mission K2. This paper aims to explore how deep learning algorithms can help in classifying the presence of exoplanets with less amount of data in one case and a more extensive variety of data in another. In addition to the standard CNN-based method, we propose a Siamese architecture that is particularly useful in addressing classification in a low-data scenario. The CNN and ResNet algorithms achieved an average accuracy of 68% for three classes and 86% for two-class classification. However, for both the three and two classes, the Siamese algorithm achieved 99% accuracy.

Read this paper on arXiv…

P. G and A. Kumari
Wed, 17 May 23
28/67

Comments: 16pages, 3 figures

Intercomparison of Brown Dwarf Model Grids and Atmospheric Retrieval Using Machine Learning [SSA]

http://arxiv.org/abs/2305.07719


Understanding differences between sub-stellar spectral data and models has proven to be a major challenge, especially for self-consistent model grids that are necessary for a thorough investigation of brown dwarf atmospheres. Using the supervised machine learning method of the random forest, we study the information content of 14 previously published model grids of brown dwarfs (from 1997 to 2021). The random forest method allows us to analyze the predictive power of these model grids, as well as interpret data within the framework of Approximate Bayesian Computation (ABC). Our curated dataset includes 3 benchmark brown dwarfs (Gl 570D, {\epsilon} Indi Ba and Bb) as well as a sample of 19 L and T dwarfs; this sample was previously analyzed in Lueber et al. (2022) using traditional Bayesian methods (nested sampling). We find that the effective temperature of a brown dwarf can be robustly predicted independent of the model grid chosen for the interpretation. However, inference of the surface gravity is model-dependent. Specifically, the BT-Settl, Sonora Bobcat and Sonora Cholla model grids tend to predict logg ~3-4 (cgs units) even after data blueward of 1.2 {\mu}m have been disregarded to mitigate for our incomplete knowledge of the shapes of alkali lines. Two major, longstanding challenges associated with understanding the influence of clouds in brown dwarf atmospheres remain: our inability to model them from first principles and also to robustly validate these models.

Read this paper on arXiv…

A. Lueber, D. Kitzmann, C. Fisher, et. al.
Tue, 16 May 23
23/83

Comments: 28 pages, 14 figures, 4 Tables. Under review at AAS Journals. Feedback welcome!

CosmoPower-JAX: high-dimensional Bayesian inference with differentiable cosmological emulators [CEA]

http://arxiv.org/abs/2305.06347


We present CosmoPower-JAX, a JAX-based implementation of the CosmoPower framework, which accelerates cosmological inference by building neural emulators of cosmological power spectra. We show how, using the automatic differentiation, batch evaluation and just-in-time compilation features of JAX, and running the inference pipeline on graphics processing units (GPUs), parameter estimation can be accelerated by orders of magnitude with advanced gradient-based sampling techniques. These can be used to efficiently explore high-dimensional parameter spaces, such as those needed for the analysis of next-generation cosmological surveys. We showcase the accuracy and computational efficiency of CosmoPower-JAX on two simulated Stage IV configurations. We first consider a single survey performing a cosmic shear analysis totalling 37 model parameters. We validate the contours derived with CosmoPower-JAX and a Hamiltonian Monte Carlo sampler against those derived with a nested sampler and without emulators, obtaining a speed-up factor of $\mathcal{O}(10^3)$. We then consider a combination of three Stage IV surveys, each performing a joint cosmic shear and galaxy clustering (3x2pt) analysis, for a total of 157 model parameters. Even with such a high-dimensional parameter space, CosmoPower-JAX provides converged posterior contours in 3 days, as opposed to the estimated 6 years required by standard methods. CosmoPower-JAX is fully written in Python, and we make it publicly available to help the cosmological community meet the accuracy requirements set by next-generation surveys.

Read this paper on arXiv…

D. Piras and A. Mancini
Thu, 11 May 23
43/55

Comments: 11 pages, 5 figures. CosmoPower-JAX is available at this https URL

Weakly-Supervised Anomaly Detection in the Milky Way [GA]

http://arxiv.org/abs/2305.03761


Large-scale astrophysics datasets present an opportunity for new machine learning techniques to identify regions of interest that might otherwise be overlooked by traditional searches. To this end, we use Classification Without Labels (CWoLa), a weakly-supervised anomaly detection method, to identify cold stellar streams within the more than one billion Milky Way stars observed by the Gaia satellite. CWoLa operates without the use of labeled streams or knowledge of astrophysical principles. Instead, we train a classifier to distinguish between mixed samples for which the proportions of signal and background samples are unknown. This computationally lightweight strategy is able to detect both simulated streams and the known stream GD-1 in data. Originally designed for high-energy collider physics, this technique may have broad applicability within astrophysics as well as other domains interested in identifying localized anomalies.

Read this paper on arXiv…

M. Pettee, S. Thanvantri, B. Nachman, et. al.
Tue, 9 May 23
48/88

Comments: N/A

Explaining dark matter halo density profiles with neural networks [CEA]

http://arxiv.org/abs/2305.03077


We use explainable neural networks to connect the evolutionary history of dark matter halos with their density profiles. The network captures independent factors of variation in the density profiles within a low-dimensional representation, which we physically interpret using mutual information. Without any prior knowledge of the halos’ evolution, the network recovers the known relation between the early time assembly and the inner profile, and discovers that the profile beyond the virial radius is described by a single parameter capturing the most recent mass accretion rate. The results illustrate the potential for machine-assisted scientific discovery in complicated astrophysical datasets.

Read this paper on arXiv…

L. Lucie-Smith, H. Peiris and A. Pontzen
Mon, 8 May 23
1/63

Comments: 7 pages, 5 figures

Multiplicity Boost Of Transit Signal Classifiers: Validation of 69 New Exoplanets Using The Multiplicity Boost of ExoMiner [EPA]

http://arxiv.org/abs/2305.02470


Most existing exoplanets are discovered using validation techniques rather than being confirmed by complementary observations. These techniques generate a score that is typically the probability of the transit signal being an exoplanet (y(x)=exoplanet) given some information related to that signal (represented by x). Except for the validation technique in Rowe et al. (2014) that uses multiplicity information to generate these probability scores, the existing validation techniques ignore the multiplicity boost information. In this work, we introduce a framework with the following premise: given an existing transit signal vetter (classifier), improve its performance using multiplicity information. We apply this framework to several existing classifiers, which include vespa (Morton et al. 2016), Robovetter (Coughlin et al. 2017), AstroNet (Shallue & Vanderburg 2018), ExoNet (Ansdel et al. 2018), GPC and RFC (Armstrong et al. 2020), and ExoMiner (Valizadegan et al. 2022), to support our claim that this framework is able to improve the performance of a given classifier. We then use the proposed multiplicity boost framework for ExoMiner V1.2, which addresses some of the shortcomings of the original ExoMiner classifier (Valizadegan et al. 2022), and validate 69 new exoplanets for systems with multiple KOIs from the Kepler catalog.

Read this paper on arXiv…

H. Valizadegan, M. Martinho, J. Jenkins, et. al.
Fri, 5 May 23
24/67

Comments: N/A

Interpretable Machine Learning for Science with PySR and SymbolicRegression.jl [IMA]

http://arxiv.org/abs/2305.01582


PySR is an open-source library for practical symbolic regression, a type of machine learning which aims to discover human-interpretable symbolic models. PySR was developed to democratize and popularize symbolic regression for the sciences, and is built on a high-performance distributed back-end, a flexible search algorithm, and interfaces with several deep learning packages. PySR’s internal search algorithm is a multi-population evolutionary algorithm, which consists of a unique evolve-simplify-optimize loop, designed for optimization of unknown scalar constants in newly-discovered empirical expressions. PySR’s backend is the extremely optimized Julia library SymbolicRegression.jl, which can be used directly from Julia. It is capable of fusing user-defined operators into SIMD kernels at runtime, performing automatic differentiation, and distributing populations of expressions to thousands of cores across a cluster. In describing this software, we also introduce a new benchmark, “EmpiricalBench,” to quantify the applicability of symbolic regression algorithms in science. This benchmark measures recovery of historical empirical equations from original and synthetic datasets.

Read this paper on arXiv…

M. Cranmer
Wed, 3 May 23
23/67

Comments: 24 pages, 5 figures, 3 tables. Feedback welcome. Paper source found at this https URL ; PySR at this https URL ; SymbolicRegression.jl at this https URL

Ensemble Learning for CME Arrival Time Prediction [SSA]

http://arxiv.org/abs/2305.00258


The Sun constantly releases radiation and plasma into the heliosphere. Sporadically, the Sun launches solar eruptions such as flares and coronal mass ejections (CMEs). CMEs carry away a huge amount of mass and magnetic flux with them. An Earth-directed CME can cause serious consequences to the human system. It can destroy power grids/pipelines, satellites, and communications. Therefore, accurately monitoring and predicting CMEs is important to minimize damages to the human system. In this study we propose an ensemble learning approach, named CMETNet, for predicting the arrival time of CMEs from the Sun to the Earth. We collect and integrate eruptive events from two solar cycles, #23 and #24, from 1996 to 2021 with a total of 363 geoeffective CMEs. The data used for making predictions include CME features, solar wind parameters and CME images obtained from the SOHO/LASCO C2 coronagraph. Our ensemble learning framework comprises regression algorithms for numerical data analysis and a convolutional neural network for image processing. Experimental results show that CMETNet performs better than existing machine learning methods reported in the literature, with a Pearson product-moment correlation coefficient of 0.83 and a mean absolute error of 9.75 hours.

Read this paper on arXiv…

K. Alobaid and J. Wang
Tue, 2 May 23
8/57

Comments: 13 pages, 8 figures

Galaxy Classification Using Transfer Learning and Ensemble of CNNs With Multiple Colour Spaces [IMA]

http://arxiv.org/abs/2305.00002


Big data has become the norm in astronomy, making it an ideal domain for computer science research. Astronomers typically classify galaxies based on their morphologies, a practice that dates back to Hubble (1936). With small datasets, classification could be performed by individuals or small teams, but the exponential growth of data from modern telescopes necessitates automated classification methods.
In December 2013, Winton Capital, Galaxy Zoo, and the Kaggle team created the Galaxy Challenge, which tasked participants with developing models to classify galaxies. The Kaggle Galaxy Zoo dataset has since been widely used by researchers. This study investigates the impact of colour space transformation on classification accuracy and explores the effect of CNN architecture on this relationship. Multiple colour spaces (RGB, XYZ, LAB, etc.) and CNN architectures (VGG, ResNet, DenseNet, Xception, etc.) are considered, utilizing pre-trained models and weights. However, as most pre-trained models are designed for natural RGB images, we examine their performance with transformed, non-natural astronomical images.
We test our hypothesis by evaluating individual networks with RGB and transformed colour spaces and examining various ensemble configurations. A minimal hyperparameter search ensures optimal results. Our findings indicate that using transformed colour spaces in individual networks yields higher validation accuracy, and ensembles of networks and colour spaces further improve accuracy.
This research aims to validate the utility of colour space transformation for astronomical image classification and serve as a benchmark for future studies.

Read this paper on arXiv…

Y. Andrew
Tue, 2 May 23
12/57

Comments: Master’s Thesis

Distinguishing a planetary transit from false positives: a Transformer-based classification for planetary transit signals [EPA]

http://arxiv.org/abs/2304.14283


Current space-based missions, such as the Transiting Exoplanet Survey Satellite (TESS), provide a large database of light curves that must be analysed efficiently and systematically. In recent years, deep learning (DL) methods, particularly convolutional neural networks (CNN), have been used to classify transit signals of candidate exoplanets automatically. However, CNNs have some drawbacks; for example, they require many layers to capture dependencies on sequential data, such as light curves, making the network so large that it eventually becomes impractical. The self-attention mechanism is a DL technique that attempts to mimic the action of selectively focusing on some relevant things while ignoring others. Models, such as the Transformer architecture, were recently proposed for sequential data with successful results. Based on these successful models, we present a new architecture for the automatic classification of transit signals. Our proposed architecture is designed to capture the most significant features of a transit signal and stellar parameters through the self-attention mechanism. In addition to model prediction, we take advantage of attention map inspection, obtaining a more interpretable DL approach. Thus, we can identify the relevance of each element to differentiate a transit signal from false positives, simplifying the manual examination of candidates. We show that our architecture achieves competitive results concerning the CNNs applied for recognizing exoplanetary transit signals in data from the TESS telescope. Based on these results, we demonstrate that applying this state-of-the-art DL model to light curves can be a powerful technique for transit signal detection while offering a level of interpretability.

Read this paper on arXiv…

H. Salinas, K. Pichara, R. Brahm, et. al.
Fri, 28 Apr 23
34/68

Comments: N/A

A Measurement of the Kuiper Belt's Mean Plane From Objects Classified By Machine Learning [EPA]

http://arxiv.org/abs/2304.14312


Mean plane measurements of the Kuiper Belt from observational data are of interest for their potential to test dynamical models of the solar system. Recent measurements have yielded inconsistent results. Here we report a measurement of the Kuiper Belt’s mean plane with a sample size more than twice as large as in previous measurements. The sample of interest is the non-resonant Kuiper belt objects, which we identify by using machine learning on the observed Kuiper Belt population whose orbits are well-determined. We estimate the measurement error with a Monte Carlo procedure. We find that the overall mean plane of the non-resonant Kuiper Belt (semimajor axis range 35-150 au) and also that of the classical Kuiper Belt (semimajor axis range 42-48 au) are both close to (within about 0.7 degrees) but distinguishable from the invariable plane of the solar system to greater than 99.7% confidence. When binning the sample into smaller semimajor axis bins, we find the measured mean plane mostly consistent with both the invariable plane and the theoretically expected Laplace surface forced by the known planets. Statistically significant discrepancies are found only in the semimajor axis ranges 40.3-42 au and 45-50 au; these ranges are in proximity to a secular resonance and Neptune’s 2:1 mean motion resonance where the theory for the Laplace surface is likely to be inaccurate. These results do not support a previously reported anomalous warp at semimajor axes above 50 au.

Read this paper on arXiv…

I. Matheson and R. Malhotra
Fri, 28 Apr 23
38/68

Comments: 15 pages, 4 figures. Accepted for The Astronomical Journal

Morphological Classification of Extragalactic Radio Sources Using Gradient Boosting Methods [IMA]

http://arxiv.org/abs/2304.12729


The field of radio astronomy is witnessing a boom in the amount of data produced per day due to newly commissioned radio telescopes. One of the most crucial problems in this field is the automatic classification of extragalactic radio sources based on their morphologies. Most recent contributions in the field of morphological classification of extragalactic radio sources have proposed classifiers based on convolutional neural networks. Alternatively, this work proposes gradient boosting machine learning methods accompanied by principal component analysis as data-efficient alternatives to convolutional neural networks. Recent findings have shown the efficacy of gradient boosting methods in outperforming deep learning methods for classification problems with tabular data. The gradient boosting methods considered in this work are based on the XGBoost, LightGBM, and CatBoost implementations. This work also studies the effect of dataset size on classifier performance. A three-class classification problem is considered in this work based on the three main Fanaroff-Riley classes: class 0, class I, and class II, using radio sources from the Best-Heckman sample. All three proposed gradient boosting methods outperformed a state-of-the-art convolutional neural networks-based classifier using less than a quarter of the number of images, with CatBoost having the highest accuracy. This was mainly due to the superior accuracy of gradient boosting methods in classifying Fanaroff-Riley class II sources, with 3–4\% higher recall.

Read this paper on arXiv…

A. Darya, I. Fernini, M. Vellasco, et. al.
Wed, 26 Apr 23
56/62

Comments: Accepted by The 2023 International Joint Conference on Neural Networks (IJCNN). The code and dataset used in this work are available from this https URL

Identifying Stochasticity in Time-Series with Autoencoder-Based Content-aware 2D Representation: Application to Black Hole Data [CL]

http://arxiv.org/abs/2304.11560


In this work, we report an autoencoder-based 2D representation to classify a time-series as stochastic or non-stochastic, to understand the underlying physical process. Content-aware conversion of 1D time-series to 2D representation, that simultaneously utilizes time- and frequency-domain characteristics, is proposed. An autoencoder is trained with a loss function to learn latent space (using both time- and frequency domains) representation, that is designed to be, time-invariant. Every element of the time-series is represented as a tuple with two components, one each, from latent space representation in time- and frequency-domains, forming a binary image. In this binary image, those tuples that represent the points in the time-series, together form the “Latent Space Signature” (LSS) of the input time-series. The obtained binary LSS images are fed to a classification network. The EfficientNetv2-S classifier is trained using 421 synthetic time-series, with fair representation from both categories. The proposed methodology is evaluated on publicly available astronomical data which are 12 distinct temporal classes of time-series pertaining to the black hole GRS 1915 + 105, obtained from RXTE satellite. Results obtained using the proposed methodology are compared with existing techniques. Concurrence in labels obtained across the classes, illustrates the efficacy of the proposed 2D representation using the latent space co-ordinates. The proposed methodology also outputs the confidence in the classification label.

Read this paper on arXiv…

C. Pradeep and N. Sinha
Tue, 25 Apr 23
69/72

Comments: N/A

Lossy Compression of Large-Scale Radio Interferometric Data [IMA]

http://arxiv.org/abs/2304.07050


This work proposes to reduce visibility data volume using a baseline-dependent lossy compression technique that preserves smearing at the edges of the field-of-view. We exploit the relation of the rank of a matrix and the fact that a low-rank approximation can describe the raw visibility data as a sum of basic components where each basic component corresponds to a specific Fourier component of the sky distribution. As such, the entire visibility data is represented as a collection of data matrices from baselines, instead of a single tensor. The proposed methods are formulated as follows: provided a large dataset of the entire visibility data; the first algorithm, named $simple~SVD$ projects the data into a regular sampling space of rank$-r$ data matrices. In this space, the data for all the baselines has the same rank, which makes the compression factor equal across all baselines. The second algorithm, named $BDSVD$ projects the data into an irregular sampling space of rank$-r_{pq}$ data matrices. The subscript $pq$ indicates that the rank of the data matrix varies across baselines $pq$, which makes the compression factor baseline-dependent. MeerKAT and the European Very Long Baseline Interferometry Network are used as reference telescopes to evaluate and compare the performance of the proposed methods against traditional methods, such as traditional averaging and baseline-dependent averaging (BDA). For the same spatial resolution threshold, both $simple~SVD$ and $BDSVD$ show effective compression by two-orders of magnitude higher than traditional averaging and BDA. At the same space-saving rate, there is no decrease in spatial resolution and there is a reduction in the noise variance in the data which improves the S/N to over $1.5$ dB at the edges of the field-of-view.

Read this paper on arXiv…

M. Atemkeng, S. Perkins, E. Seck, et. al.
Mon, 17 Apr 23
19/51

Comments: N/A

Fast emulation of cosmological density fields based on dimensionality reduction and supervised machine-learning [CEA]

http://arxiv.org/abs/2304.06099


N-body simulations are the most powerful method to study the non-linear evolution of large-scale structure. However, they require large amounts of computational resources, making unfeasible their direct adoption in scenarios that require broad explorations of parameter spaces. In this work, we show that it is possible to perform fast dark matter density field emulations with competitive accuracy using simple machine-learning approaches. We build an emulator based on dimensionality reduction and machine learning regression combining simple Principal Component Analysis and supervised learning methods. For the estimations with a single free parameter, we train on the dark matter density parameter, $\Omega_m$, while for emulations with two free parameters, we train on a range of $\Omega_m$ and redshift. The method first adopts a projection of a grid of simulations on a given basis; then, a machine learning regression is trained on this projected grid. Finally, new density cubes for different cosmological parameters can be estimated without relying directly on new N-body simulations by predicting and de-projecting the basis coefficients. We show that the proposed emulator can generate density cubes at non-linear cosmological scales with density distributions within a few percent compared to the corresponding N-body simulations. The method enables gains of three orders of magnitude in CPU run times compared to performing a full N-body simulation while reproducing the power spectrum and bispectrum within $\sim 1\%$ and $\sim 3\%$, respectively, for the single free parameter emulation and $\sim 5\%$ and $\sim 15\%$ for two free parameters. This can significantly accelerate the generation of density cubes for a wide variety of cosmological models, opening the doors to previously unfeasible applications, such as parameter and model inferences at full survey scales as the ESA/NASA Euclid mission.

Read this paper on arXiv…

M. Conceição, A. Krone-Martins, A. Silva, et. al.
Fri, 14 Apr 23
12/64

Comments: 10 pages, 6 figures. To be submitted to A&A. Comments are welcome!

Priors for symbolic regression [CL]

http://arxiv.org/abs/2304.06333


When choosing between competing symbolic models for a data set, a human will naturally prefer the “simpler” expression or the one which more closely resembles equations previously seen in a similar context. This suggests a non-uniform prior on functions, which is, however, rarely considered within a symbolic regression (SR) framework. In this paper we develop methods to incorporate detailed prior information on both functions and their parameters into SR. Our prior on the structure of a function is based on a $n$-gram language model, which is sensitive to the arrangement of operators relative to one another in addition to the frequency of occurrence of each operator. We also develop a formalism based on the Fractional Bayes Factor to treat numerical parameter priors in such a way that models may be fairly compared though the Bayesian evidence, and explicitly compare Bayesian, Minimum Description Length and heuristic methods for model selection. We demonstrate the performance of our priors relative to literature standards on benchmarks and a real-world dataset from the field of cosmology.

Read this paper on arXiv…

D. Bartlett, H. Desmond and P. Ferreira
Fri, 14 Apr 23
62/64

Comments: 8+2 pages, 2 figures. Submitted to The Genetic and Evolutionary Computation Conference (GECCO) 2023 Workshop on Symbolic Regression

Deep-learning based measurement of planetary radial velocities in the presence of stellar variability [EPA]

http://arxiv.org/abs/2304.04807


We present a deep-learning based approach for measuring small planetary radial velocities in the presence of stellar variability. We use neural networks to reduce stellar RV jitter in three years of HARPS-N sun-as-a-star spectra. We develop and compare dimensionality-reduction and data splitting methods, as well as various neural network architectures including single line CNNs, an ensemble of single line CNNs, and a multi-line CNN. We inject planet-like RVs into the spectra and use the network to recover them. We find that the multi-line CNN is able to recover planets with 0.2 m/s semi-amplitude, 50 day period, with 8.8% error in the amplitude and 0.7% in the period. This approach shows promise for mitigating stellar RV variability and enabling the detection of small planetary RVs with unprecedented precision.

Read this paper on arXiv…

I. Colwell, V. Timmaraju and A. Wise
Wed, 12 Apr 23
5/45

Comments: Draft, unsubmitted, 10 pages, 8 figures

The CAMELS project: Expanding the galaxy formation model space with new ASTRID and 28-parameter TNG and SIMBA suites [CEA]

http://arxiv.org/abs/2304.02096


We present CAMELS-ASTRID, the third suite of hydrodynamical simulations in the Cosmology and Astrophysics with MachinE Learning (CAMELS) project, along with new simulation sets that extend the model parameter space based on the previous frameworks of CAMELS-TNG and CAMELS-SIMBA, to provide broader training sets and testing grounds for machine-learning algorithms designed for cosmological studies. CAMELS-ASTRID employs the galaxy formation model following the ASTRID simulation and contains 2,124 hydrodynamic simulation runs that vary 3 cosmological parameters ($\Omega_m$, $\sigma_8$, $\Omega_b$) and 4 parameters controlling stellar and AGN feedback. Compared to the existing TNG and SIMBA simulation suites in CAMELS, the fiducial model of ASTRID features the mildest AGN feedback and predicts the least baryonic effect on the matter power spectrum. The training set of ASTRID covers a broader variation in the galaxy populations and the baryonic impact on the matter power spectrum compared to its TNG and SIMBA counterparts, which can make machine-learning models trained on the ASTRID suite exhibit better extrapolation performance when tested on other hydrodynamic simulation sets. We also introduce extension simulation sets in CAMELS that widely explore 28 parameters in the TNG and SIMBA models, demonstrating the enormity of the overall galaxy formation model parameter space and the complex non-linear interplay between cosmology and astrophysical processes. With the new simulation suites, we show that building robust machine-learning models favors training and testing on the largest possible diversity of galaxy formation models. We also demonstrate that it is possible to train accurate neural networks to infer cosmological parameters using the high-dimensional TNG-SB28 simulation set.

Read this paper on arXiv…

Y. Ni, S. Genel, D. Anglés-Alcázar, et. al.
Thu, 6 Apr 23
56/76

Comments: N/A

Prediction of solar wind speed by applying convolutional neural network to potential field source surface (PFSS) magnetograms [SSA]

http://arxiv.org/abs/2304.01234


An accurate solar wind speed model is important for space weather predictions, catastrophic event warnings, and other issues concerning solar wind – magnetosphere interaction. In this work, we construct a model based on convolutional neural network (CNN) and Potential Field Source Surface (PFSS) magnetograms, considering a solar wind source surface of $R_{\rm SS}=2.5R_\odot$, aiming to predict the solar wind speed at the Lagrange 1 (L1) point of the Sun-Earth system. The input of our model consists of four Potential Field Source Surface (PFSS) magnetograms at $R_{\rm SS}$, which are 7, 6, 5, and 4 days before the target epoch. Reduced magnetograms are used to promote the model’s efficiency. We use the Global Oscillation Network Group (GONG) photospheric magnetograms and the potential field extrapolation model to generate PFSS magnetograms at the source surface. The model provides predictions of the continuous test dataset with an averaged correlation coefficient (CC) of 0.52 and a root mean square error (RMSE) of 80.8 km/s in an eight-fold validation training scheme with the time resolution of the data as small as one hour. The model also has the potential to forecast high speed streams of the solar wind, which can be quantified with a general threat score of 0.39.

Read this paper on arXiv…

R. Lin, Z. Luo, J. He, et. al.
Wed, 5 Apr 23
39/62

Comments: N/A

Heating and dynamics of the Solar atmosphere [SSA]

http://arxiv.org/abs/2304.01553


The solar atmosphere shows anomalous variation in temperature, starting from the 5500 K photosphere to the million-degree Kelvin corona. The corona itself expands into the interstellar medium as the free streaming solar wind, which modulates and impacts the near-Earth space weather. The precise source regions of different structures in the solar wind, their formation height, and the heating of the solar atmosphere are inextricably linked and unsolved problems in astrophysics. Observations suggest correlations between Coronal holes (CHs), which are cool, intensity deficit structures in the solar corona, with structures in the solar wind. Observations also suggest the local plasma heating in the corona through power-law distributed impulsive events. In this thesis, we use narrowband photometric, spectroscopic, and disc-integrated emission of the solar atmosphere ranging from Near Ultraviolet to X-rays along with in-situ solar wind measurements to understand (i). the source regions of the solar wind, (ii). the underlying mechanism of solar coronal heating, and (iii). the differentiation in dynamics of CHs with the background Quiet Sun (QS) regions, which do not show any significant signature of the solar wind. We leverage machine learning and numerical modeling tools to develop solar wind forecasting codes using interpretable AI, inversion codes to infer the properties of impulsive events and to understand the differences in the thermodynamics of CHs and QS regions. We finally present a unified scenario of solar wind emergence and heating in the solar atmosphere and discuss the implications of inferences from this thesis.

Read this paper on arXiv…

V. Upendran
Wed, 5 Apr 23
44/62

Comments: PhD thesis presented to IUCAA and JNU. Refer to the thesis for list of papers

Astronomical image time series classification using CONVolutional attENTION (ConvEntion) [IMA]

http://arxiv.org/abs/2304.01236


Aims. The treatment of astronomical image time series has won increasing attention in recent years. Indeed, numerous surveys following up on transient objects are in progress or under construction, such as the Vera Rubin Observatory Legacy Survey for Space and Time (LSST), which is poised to produce huge amounts of these time series. The associated scientific topics are extensive, ranging from the study of objects in our galaxy to the observation of the most distant supernovae for measuring the expansion of the universe. With such a large amount of data available, the need for robust automatic tools to detect and classify celestial objects is growing steadily. Methods. This study is based on the assumption that astronomical images contain more information than light curves. In this paper, we propose a novel approach based on deep learning for classifying different types of space objects directly using images. We named our approach ConvEntion, which stands for CONVolutional attENTION. It is based on convolutions and transformers, which are new approaches for the treatment of astronomical image time series. Our solution integrates spatio-temporal features and can be applied to various types of image datasets with any number of bands. Results. In this work, we solved various problems the datasets tend to suffer from and we present new results for classifications using astronomical image time series with an increase in accuracy of 13%, compared to state-of-the-art approaches that use image time series, and a 12% increase, compared to approaches that use light curves.

Read this paper on arXiv…

A. Bairouk, M. Chaumont, D. Fouchez, et. al.
Wed, 5 Apr 23
49/62

Comments: N/A

Denoising Diffusion Probabilistic Models to Predict the Density of Molecular Clouds [GA]

http://arxiv.org/abs/2304.01670


We introduce the state-of-the-art deep learning Denoising Diffusion Probabilistic Model (DDPM) as a method to infer the volume or number density of giant molecular clouds (GMCs) from projected mass surface density maps. We adopt magnetohydrodynamic simulations with different global magnetic field strengths and large-scale dynamics, i.e., noncolliding and colliding GMCs. We train a diffusion model on both mass surface density maps and their corresponding mass-weighted number density maps from different viewing angles for all the simulations. We compare the diffusion model performance with a more traditional empirical two-component and three-component power-law fitting method and with a more traditional neural network machine learning approach (CASI-2D). We conclude that the diffusion model achieves an order of magnitude improvement on the accuracy of predicting number density compared to that by other methods. We apply the diffusion method to some example astronomical column density maps of Taurus and the Infrared Dark Clouds (IRDCs) G28.37+0.07 and G35.39-0.33 to produce maps of their mean volume densities.

Read this paper on arXiv…

D. Xu, J. Tan, C. Hsu, et. al.
Wed, 5 Apr 23
62/62

Comments: ApJ accepted

Searching for long faint astronomical high energy transients: a data driven approach [HEAP]

http://arxiv.org/abs/2303.15936


HERMES (High Energy Rapid Modular Ensemble of Satellites) pathfinder is an in-orbit demonstration consisting of a constellation of six 3U nano-satellites hosting simple but innovative detectors for the monitoring of cosmic high-energy transients. The main objective of HERMES Pathfinder is to prove that accurate position of high-energy cosmic transients can be obtained using miniaturized hardware. The transient position is obtained by studying the delay time of arrival of the signal to different detectors hosted by nano-satellites on low Earth orbits. To this purpose, the goal is to achive an overall accuracy of a fraction of a micro-second. In this context, we need to develop novel tools to fully exploit the future scientific data output of HERMES Pathfinder. In this paper, we introduce a new framework to assess the background count rate of a space-born, high energy detector; a key step towards the identification of faint astrophysical transients. We employ a Neural Network (NN) to estimate the background lightcurves on different timescales. Subsequently, we employ a fast change-point and anomaly detection technique to isolate observation segments where statistically significant excesses in the observed count rate relative to the background estimate exist. We test the new software on archival data from the NASA Fermi Gamma-ray Burst Monitor (GBM), which has a collecting area and background level of the same order of magnitude to those of HERMES Pathfinder. The NN performances are discussed and analyzed over period of both high and low solar activity. We were able to confirm events in the Fermi/GBM catalog and found events, not present in Fermi/GBM database, that could be attributed to Solar Flares, Terrestrial Gamma-ray Flashes, Gamma-Ray Bursts, Galactic X-ray flash. Seven of these are selected and analyzed further, providing an estimate of localisation and a tentative classification.

Read this paper on arXiv…

R. Crupi, G. Dilillo, E. Bissaldi, et. al.
Wed, 29 Mar 23
59/73

Comments: N/A

Applications of Gaussian Processes at Extreme Lengthscales: From Molecules to Black Holes [CL]

http://arxiv.org/abs/2303.14291


In many areas of the observational and experimental sciences data is scarce. Data observation in high-energy astrophysics is disrupted by celestial occlusions and limited telescope time while data derived from laboratory experiments in synthetic chemistry and materials science is time and cost-intensive to collect. On the other hand, knowledge about the data-generation mechanism is often available in the sciences, such as the measurement error of a piece of laboratory apparatus. Both characteristics, small data and knowledge of the underlying physics, make Gaussian processes (GPs) ideal candidates for fitting such datasets. GPs can make predictions with consideration of uncertainty, for example in the virtual screening of molecules and materials, and can also make inferences about incomplete data such as the latent emission signature from a black hole accretion disc. Furthermore, GPs are currently the workhorse model for Bayesian optimisation, a methodology foreseen to be a guide for laboratory experiments in scientific discovery campaigns. The first contribution of this thesis is to use GP modelling to reason about the latent emission signature from the Seyfert galaxy Markarian 335, and by extension, to reason about the applicability of various theoretical models of black hole accretion discs. The second contribution is to extend the GP framework to molecular and chemical reaction representations and to provide an open-source software library to enable the framework to be used by scientists. The third contribution is to leverage GPs to discover novel and performant photoswitch molecules. The fourth contribution is to introduce a Bayesian optimisation scheme capable of modelling aleatoric uncertainty to facilitate the identification of material compositions that possess intrinsic robustness to large scale fabrication processes.

Read this paper on arXiv…

R. Griffiths
Tue, 28 Mar 23
25/81

Comments: PhD Thesis submitted at the University of Cambridge, August 2022. The thesis is based on a number of previous works also available on arXiv (see Introduction)

Convolutional Neural Networks for the classification of glitches in gravitational-wave data streams [CL]

http://arxiv.org/abs/2303.13917


We investigate the use of Convolutional Neural Networks (including the modern ConvNeXt network family) to classify transient noise signals (i.e.~glitches) and gravitational waves in data from the Advanced LIGO detectors. First, we use models with a supervised learning approach, both trained from scratch using the Gravity Spy dataset and employing transfer learning by fine-tuning pre-trained models in this dataset. Second, we also explore a self-supervised approach, pre-training models with automatically generated pseudo-labels. Our findings are very close to existing results for the same dataset, reaching values for the F1 score of 97.18% (94.15%) for the best supervised (self-supervised) model. We further test the models using actual gravitational-wave signals from LIGO-Virgo’s O3 run. Although trained using data from previous runs (O1 and O2), the models show good performance, in particular when using transfer learning. We find that transfer learning improves the scores without the need for any training on real signals apart from the less than 50 chirp examples from hardware injections present in the Gravity Spy dataset. This motivates the use of transfer learning not only for glitch classification but also for signal classification.

Read this paper on arXiv…

T. Fernandes, S. Vieira, A. Onofre, et. al.
Mon, 27 Mar 23
4/59

Comments: 15 pages, 14 figures

Physics-informed neural networks in the recreation of hydrodynamic simulations from dark matter [CEA]

http://arxiv.org/abs/2303.14090


Physics-informed neural networks have emerged as a coherent framework for building predictive models that combine statistical patterns with domain knowledge. The underlying notion is to enrich the optimization loss function with known relationships to constrain the space of possible solutions. Hydrodynamic simulations are a core constituent of modern cosmology, while the required computations are both expensive and time-consuming. At the same time, the comparatively fast simulation of dark matter requires fewer resources, which has led to the emergence of machine learning algorithms for baryon inpainting as an active area of research; here, recreating the scatter found in hydrodynamic simulations is an ongoing challenge. This paper presents the first application of physics-informed neural networks to baryon inpainting by combining advances in neural network architectures with physical constraints, injecting theory on baryon conversion efficiency into the model loss function. We also introduce a punitive prediction comparison based on the Kullback-Leibler divergence, which enforces scatter reproduction. By simultaneously extracting the complete set of baryonic properties for the Simba suite of cosmological simulations, our results demonstrate improved accuracy of baryonic predictions based on dark matter halo properties, successful recovery of the fundamental metallicity relation, and retrieve scatter that traces the target simulation’s distribution.

Read this paper on arXiv…

Z. Dai, B. Moews, R. Vilalta, et. al.
Mon, 27 Mar 23
31/59

Comments: N/A

Predicting the Initial Conditions of the Universe using Deep Learning [CEA]

http://arxiv.org/abs/2303.13056


Finding the initial conditions that led to the current state of the universe is challenging because it involves searching over a vast input space of initial conditions, along with modeling their evolution via tools such as N-body simulations which are computationally expensive. Deep learning has emerged as an alternate modeling tool that can learn the mapping between the linear input of an N-body simulation and the final nonlinear displacements at redshift zero, which can significantly accelerate the forward modeling. However, this does not help reduce the search space for initial conditions. In this paper, we demonstrate for the first time that a deep learning model can be trained for the reverse mapping. We train a V-Net based convolutional neural network, which outputs the linear displacement of an N-body system, given the current time nonlinear displacement and the cosmological parameters of the system. We demonstrate that this neural network accurately recovers the initial linear displacement field over a wide range of scales ($<1$-$2\%$ error up to nearly $k = 1\ \mathrm{Mpc}^{-1}\,h$), despite the ill-defined nature of the inverse problem at smaller scales. Specifically, smaller scales are dominated by nonlinear effects which makes the backward dynamics much more susceptible to numerical and computational errors leading to highly divergent backward trajectories and a one-to-many backward mapping. The results of our method motivate that neural network based models can act as good approximators of the initial linear states and their predictions can serve as good starting points for sampling-based methods to infer the initial states of the universe.

Read this paper on arXiv…

V. Jindal, D. Jamieson, A. Liang, et. al.
Fri, 24 Mar 23
52/56

Comments: N/A

A machine learning and feature engineering approach for the prediction of the uncontrolled re-entry of space objects [CL]

http://arxiv.org/abs/2303.10183


The continuously growing number of objects orbiting around the Earth is expected to be accompanied by an increasing frequency of objects re-entering the Earth’s atmosphere. Many of these re-entries will be uncontrolled, making their prediction challenging and subject to several uncertainties. Traditionally, re-entry predictions are based on the propagation of the object’s dynamics using state-of-the-art modelling techniques for the forces acting on the object. However, modelling errors, particularly related to the prediction of atmospheric drag may result in poor prediction accuracies. In this context, we explore the possibility to perform a paradigm shift, from a physics-based approach to a data-driven approach. To this aim, we present the development of a deep learning model for the re-entry prediction of uncontrolled objects in Low Earth Orbit (LEO). The model is based on a modified version of the Sequence-to-Sequence architecture and is trained on the average altitude profile as derived from a set of Two-Line Element (TLE) data of over 400 bodies. The novelty of the work consists in introducing in the deep learning model, alongside the average altitude, three new input features: a drag-like coefficient (B*), the average solar index, and the area-to-mass ratio of the object. The developed model is tested on a set of objects studied in the Inter-Agency Space Debris Coordination Committee (IADC) campaigns. The results show that the best performances are obtained on bodies characterised by the same drag-like coefficient and eccentricity distribution as the training set.

Read this paper on arXiv…

F. Salmaso, M. Trisolini and C. Colombo
Tue, 21 Mar 23
43/68

Comments: N/A

ExoplANNET: A deep learning algorithm to detect and identify planetary signals in radial velocity data [EPA]

http://arxiv.org/abs/2303.09335


The detection of exoplanets with the radial velocity method consists in detecting variations of the stellar velocity caused by an unseen sub-stellar companion. Instrumental errors, irregular time sampling, and different noise sources originating in the intrinsic variability of the star can hinder the interpretation of the data, and even lead to spurious detections. In recent times, work began to emerge in the field of extrasolar planets that use Machine Learning algorithms, some with results that exceed those obtained with the traditional techniques in the field. We seek to explore the scope of the neural networks in the radial velocity method, in particular for exoplanet detection in the presence of correlated noise of stellar origin. In this work, a neural network is proposed to replace the computation of the significance of the signal detected with the radial velocity method and to classify it as of planetary origin or not. The algorithm is trained using synthetic data of systems with and without planetary companions. We injected realistic correlated noise in the simulations, based on previous studies of the behaviour of stellar activity. The performance of the network is compared to the traditional method based on null hypothesis significance testing. The network achieves 28 % fewer false positives. The improvement is observed mainly in the detection of small-amplitude signals associated with low-mass planets. In addition, its execution time is five orders of magnitude faster than the traditional method. The superior performance exhibited by the algorithm has only been tested on simulated radial velocity data so far. Although in principle it should be straightforward to adapt it for use in real time series, its performance has to be tested thoroughly. Future work should permit evaluating its potential for adoption as a valuable tool for exoplanet detection.

Read this paper on arXiv…

L. Nieto and R. Díaz
Fri, 17 Mar 23
29/67

Comments: Paper under peer-review, comments are welcome

The Tiny Time-series Transformer: Low-latency High-throughput Classification of Astronomical Transients using Deep Model Compression [IMA]

http://arxiv.org/abs/2303.08951


A new golden age in astronomy is upon us, dominated by data. Large astronomical surveys are broadcasting unprecedented rates of information, demanding machine learning as a critical component in modern scientific pipelines to handle the deluge of data. The upcoming Legacy Survey of Space and Time (LSST) of the Vera C. Rubin Observatory will raise the big-data bar for time-domain astronomy, with an expected 10 million alerts per-night, and generating many petabytes of data over the lifetime of the survey. Fast and efficient classification algorithms that can operate in real-time, yet robustly and accurately, are needed for time-critical events where additional resources can be sought for follow-up analyses. In order to handle such data, state-of-the-art deep learning architectures coupled with tools that leverage modern hardware accelerators are essential. We showcase how the use of modern deep compression methods can achieve a $18\times$ reduction in model size, whilst preserving classification performance. We also show that in addition to the deep compression techniques, careful choice of file formats can improve inference latency, and thereby throughput of alerts, on the order of $8\times$ for local processing, and $5\times$ in a live production setting. To test this in a live setting, we deploy this optimised version of the original time-series transformer, t2, into the community alert broking system of FINK on real Zwicky Transient Facility (ZTF) alert data, and compare throughput performance with other science modules that exist in FINK. The results shown herein emphasise the time-series transformer’s suitability for real-time classification at LSST scale, and beyond, and introduce deep model compression as a fundamental tool for improving deploy-ability and scalable inference of deep learning models for transient classification.

Read this paper on arXiv…

T. Jr., J. Peloton and J. McEwen
Fri, 17 Mar 23
51/67

Comments: 16 pages, 11 figures

Global mapping of fragmented rocks on the Moon with a neural network: Implications for the failure mode of rocks on airless surfaces [EPA]

http://arxiv.org/abs/2301.08151


It has been recently recognized that the surface of sub-km asteroids in contact with the space environment is not fine-grained regolith but consists of centimeter to meter-scale rocks. Here we aim to understand how the rocky morphology of minor bodies react to the well known space erosion agents on the Moon. We deploy a neural network and map a total of ~130,000 fragmented boulders scattered across the lunar surface and visually identify a dozen different desintegration morphologies corresponding to different failure modes. We find that several fragmented boulder morphologies are equivalent to morphologies observed on asteroid Bennu, suggesting that these morphologies on the Moon and on asteroids are likely not diagnostic of their formation mechanism. Our findings suggest that the boulder fragmentation process is characterized by an internal weakening period with limited morphological signs of damage at rock scale until a sudden highly efficient impact shattering event occurs. In addition, we identify new morphologies such as breccia boulders with an advection-like erosion style. We publicly release the produced fractured boulder catalog along with this paper.

Read this paper on arXiv…

O. Ruesch and V. Bickel
Fri, 20 Jan 23
44/72

Comments: N/A

Revisiting mass-radius relationships for exoplanet populations: a machine learning insight [EPA]

http://arxiv.org/abs/2301.07143


The growing number of exoplanet discoveries and advances in machine learning techniques allow us to find, explore, and understand characteristics of these new worlds beyond our Solar System. We analyze the dataset of 762 confirmed exoplanets and eight Solar System planets using efficient machine-learning approaches to characterize their fundamental quantities. By adopting different unsupervised clustering algorithms, the data are divided into two main classes: planets with $\log R_{p}\leq0.91R_{\oplus}$ and $\log M_{p}\leq1.72M_{\oplus}$ as class 1 and those with $\log R_{p}>0.91R_{\oplus}$ and $\log M_{p}>1.72M_{\oplus}$ as class 2. Various regression models are used to reveal correlations between physical parameters and evaluate their performance. We find that planetary mass, orbital period, and stellar mass play preponderant roles in predicting exoplanet radius. The validation metrics (RMSE, MAE, and $R^{2}$) suggest that the Support Vector Regression has, by and large, better performance than other models and is a promising model for obtaining planetary radius. Not only do we improve the prediction accuracy in logarithmic space, but also we derive parametric equations using the M5P and Markov Chain Monte Carlo methods. Planets of class 1 are shown to be consistent with a positive linear mass-radius relation, while for planets of class 2, the planetary radius represents a strong correlation with their host stars’ masses.

Read this paper on arXiv…

M. Mousavi-Sadr, D. Jassur and G. Gozaliasl
Thu, 19 Jan 23
1/100

Comments: Submitted to MNRAS. 15 pages, 17 figures

Coronal Hole Analysis and Prediction using Computer Vision and LSTM Neural Network [SSA]

http://arxiv.org/abs/2301.06732


As humanity has begun to explore space, the significance of space weather has become apparent. It has been established that coronal holes, a type of space weather phenomenon, can impact the operation of aircraft and satellites. The coronal hole is an area on the sun characterized by open magnetic field lines and relatively low temperatures, which result in the emission of the solar wind at higher than average rates. In this study, To prepare for the impact of coronal holes on the Earth, we use computer vision to detect the coronal hole region and calculate its size based on images from the Solar Dynamics Observatory (SDO). We then implement deep learning techniques, specifically the Long Short-Term Memory (LSTM) method, to analyze trends in the coronal hole area data and predict its size for different sun regions over 7 days. By analyzing time series data on the coronal hole area, this study aims to identify patterns and trends in coronal hole behavior and understand how they may impact space weather events. This research represents an important step towards improving our ability to predict and prepare for space weather events that can affect Earth and technological systems.

Read this paper on arXiv…

J. Yun
Wed, 18 Jan 23
18/133

Comments: 15 pages

Pluto's Surface Mapping using Unsupervised Learning from Near-Infrared Observations of LEISA/Ralph [EPA]

http://arxiv.org/abs/2301.06027


We map the surface of Pluto using an unsupervised machine learning technique using the near-infrared observations of the LEISA/Ralph instrument onboard NASA’s New Horizons spacecraft. The principal component reduced Gaussian mixture model was implemented to investigate the geographic distribution of the surface units across the dwarf planet. We also present the likelihood of each surface unit at the image pixel level. Average I/F spectra of each unit were analyzed — in terms of the position and strengths of absorption bands of abundant volatiles such as N${}{2}$, CH${}{4}$, and CO and nonvolatile H${}_{2}$O — to connect the unit to surface composition, geology, and geographic location. The distribution of surface units shows a latitudinal pattern with distinct surface compositions of volatiles — consistent with the existing literature. However, previous mapping efforts were based primarily on compositional analysis using spectral indices (indicators) or implementation of complex radiative transfer models, which need (prior) expert knowledge, label data, or optical constants of representative endmembers. We prove that an application of unsupervised learning in this instance renders a satisfactory result in mapping the spatial distribution of ice compositions without any prior information or label data. Thus, such an application is specifically advantageous for a planetary surface mapping when label data are poorly constrained or completely unknown, because an understanding of surface material distribution is vital for volatile transport modeling at the planetary scale. We emphasize that the unsupervised learning used in this study has wide applicability and can be expanded to other planetary bodies of the Solar System for mapping surface material distribution.

Read this paper on arXiv…

A. Emran, C. Ore, C. Ahrens, et. al.
Wed, 18 Jan 23
81/133

Comments: Accepted for publication in The Planetary Science Journal. 50 pages, 17 figures including appendix

Kinematic Evidence of an Embedded Protoplanet in HD 142666 Identified by Machine Learning [EPA]

http://arxiv.org/abs/2301.05075


Observations of protoplanetary discs have shown that forming exoplanets leave characteristic imprints on the gas and dust of the disc. In the gas, these forming exoplanets cause deviations from Keplerian motion, which can be detected through molecular line observations. Our previous work has shown that machine learning can correctly determine if a planet is present in these discs. Using our machine learning models, we identify strong, localized non-Keplerian motion within the disc HD 142666. Subsequent hydrodynamics simulations of a system with a 5 Jupiter-mass planet at 75 au recreates the kinematic structure. By currently established standards in the field, we conclude that HD 142666 hosts a planet. This work represents a first step towards using machine learning to identify previously overlooked non-Keplerian features in protoplanetary discs.

Read this paper on arXiv…

J. Terry, C. Hall, S. Abreau, et. al.
Fri, 13 Jan 23
46/72

Comments: 7 pages, 3 figures, 1 table. Submitted to ApJ

On the functional form of the radial acceleration relation [GA]

http://arxiv.org/abs/2301.04368


We apply a new method for learning equations from data — Exhaustive Symbolic Regression (ESR) — to late-type galaxy dynamics as encapsulated in the radial acceleration relation (RAR). Relating the centripetal acceleration due to baryons, $g_\text{bar}$, to the total dynamical acceleration, $g_\text{obs}$, the RAR has been claimed to manifest a new law of nature due to its regularity and tightness, in agreement with Modified Newtonian Dynamics (MOND). Fits to this relation have been restricted by prior expectations to particular functional forms, while ESR affords an exhaustive and nearly prior-free search through functional parameter space to identify the equations optimally trading accuracy with simplicity. Working with the SPARC data, we find the best functions typically satisfy $g_\text{obs} \propto g_\text{bar}$ at high $g_\text{bar}$, although the coefficient of proportionality is not clearly unity and the deep-MOND limit $g_\text{obs} \propto \sqrt{g_\text{bar}}$ as $g_\text{bar} \to 0$ is little evident at all. By generating mock data according to MOND with or without the external field effect, we find that symbolic regression would not be expected to identify the generating function or reconstruct successfully the asymptotic slopes. We conclude that the limited dynamical range and significant uncertainties of the SPARC RAR preclude a definitive statement of its functional form, and hence that this data alone can neither demonstrate nor rule out law-like gravitational behaviour.

Read this paper on arXiv…

H. Desmond, D. Bartlett and P. Ferreira
Thu, 12 Jan 23
20/68

Comments: 12+4 pages, 4 figures, 3 tables; MNRAS submitted

A Possible Converter to Denoise the Images of Exoplanet Candidates through Machine Learning Techniques [EPA]

http://arxiv.org/abs/2301.04292


The method of direct imaging has detected many exoplanets and made important contribution to the field of planet formation. The standard method employs angular differential imaging (ADI) technique, and more ADI image frames could lead to the results with larger signal-to-noise-ratio (SNR). However, it would need precious observational time from large telescopes, which are always over-subscribed. We thus explore the possibility to generate a converter which can increase the SNR derived from a smaller number of ADI frames. The machine learning technique with two-dimension convolutional neural network (2D-CNN) is tested here. Several 2D-CNN models are trained and their performances of denoising are presented and compared. It is found that our proposed Modified five-layer Wide Inference Network with the Residual learning technique and Batch normalization (MWIN5-RB) can give the best result. We conclude that this MWIN5-RB can be employed as a converter for future observational data.

Read this paper on arXiv…

P. Chintarungruangchai, I. Jiang, J. Hashimoto, et. al.
Thu, 12 Jan 23
47/68

Comments: 30 pages, 12 figures, 1 table, published by New Astronomy

Hint assisted reinforcement learning: an application in radio astronomy [IMA]

http://arxiv.org/abs/2301.03933


Model based reinforcement learning has proven to be more sample efficient than model free methods. On the other hand, the construction of a dynamics model in model based reinforcement learning has increased complexity. Data processing tasks in radio astronomy are such situations where the original problem which is being solved by reinforcement learning itself is the creation of a model. Fortunately, many methods based on heuristics or signal processing do exist to perform the same tasks and we can leverage them to propose the best action to take, or in other words, to provide a hint'. We propose to usehints’ generated by the environment as an aid to the reinforcement learning process mitigating the complexity of model construction. We modify the soft actor critic algorithm to use hints and use the alternating direction method of multipliers algorithm with inequality constraints to train the agent. Results in several environments show that we get the increased sample efficiency by using hints as compared to model free methods.

Read this paper on arXiv…

S. Yatawatta
Wed, 11 Jan 23
43/80

Comments: N/A

Constraining cosmological parameters from N-body simulations with Variational Bayesian Neural Networks [IMA]

http://arxiv.org/abs/2301.03991


Methods based on Deep Learning have recently been applied on astrophysical parameter recovery thanks to their ability to capture information from complex data. One of these methods is the approximate Bayesian Neural Networks (BNNs) which have demonstrated to yield consistent posterior distribution into the parameter space, helpful for uncertainty quantification. However, as any modern neural networks, they tend to produce overly confident uncertainty estimates and can introduce bias when BNNs are applied to data. In this work, we implement multiplicative normalizing flows (MNFs), a family of approximate posteriors for the parameters of BNNs with the purpose of enhancing the flexibility of the variational posterior distribution, to extract $\Omega_m$, $h$, and $\sigma_8$ from the QUIJOTE simulations. We have compared this method with respect to the standard BNNs, and the flipout estimator. We found that MNFs combined with BNNs outperform the other models obtaining predictive performance with almost one order of magnitude larger that standard BNNs, $\sigma_8$ extracted with high accuracy ($r^2=0.99$), and precise uncertainty estimates. The latter implies that MNFs provide more realistic predictive distribution closer to the true posterior mitigating the bias introduced by the variational approximation and allowing to work with well-calibrated networks.

Read this paper on arXiv…

H. Hortúa, L. García and L. C
Wed, 11 Jan 23
52/80

Comments: 15 pages, 4 figures, 3 tables, submitted. Comments welcome

Identifying Exoplanets with Deep Learning. V. Improved Light Curve Classification for TESS Full Frame Image Observations [EPA]

http://arxiv.org/abs/2301.01371


The TESS mission produces a large amount of time series data, only a small fraction of which contain detectable exoplanetary transit signals. Deep learning techniques such as neural networks have proved effective at differentiating promising astrophysical eclipsing candidates from other phenomena such as stellar variability and systematic instrumental effects in an efficient, unbiased and sustainable manner. This paper presents a high quality dataset containing light curves from the Primary Mission and 1st Extended Mission full frame images and periodic signals detected via Box Least Squares (Kov\’acs et al. 2002; Hartman 2012). The dataset was curated using a thorough manual review process then used to train a neural network called Astronet-Triage-v2. On our test set, for transiting/eclipsing events we achieve a 99.6% recall (true positives over all data with positive labels) at a precision of 75.7% (true positives over all predicted positives). Since 90% of our training data is from the Primary Mission, we also test our ability to generalize on held-out 1st Extended Mission data. Here, we find an area under the precision-recall curve of 0.965, a 4% improvement over Astronet-Triage (Yu et al. 2019). On the TESS Object of Interest (TOI) Catalog through April 2022, a shortlist of planets and planet candidates, Astronet-Triage-v2 is able to recover 3577 out of 4140 TOIs, while Astronet-Triage only recovers 3349 targets at an equal level of precision. In other words, upgrading to Astronet-Triage-v2 helps save at least 200 planet candidates from being lost. The new model is currently used for planet candidate triage in the Quick-Look Pipeline (Huang et al. 2020a,b; Kunimoto et al. 2021).

Read this paper on arXiv…

E. Tey, D. Moldovan, M. Kunimoto, et. al.
Thu, 5 Jan 23
13/51

Comments: accepted for publication in AJ. code can be found at: this https URL and data can be found at: this https URL

Deep Learning for Space Weather Prediction: Bridging the Gap between Heliophysics Data and Theory [IMA]

http://arxiv.org/abs/2212.13328


Traditionally, data analysis and theory have been viewed as separate disciplines, each feeding into fundamentally different types of models. Modern deep learning technology is beginning to unify these two disciplines and will produce a new class of predictively powerful space weather models that combine the physical insights gained by data and theory. We call on NASA to invest in the research and infrastructure necessary for the heliophysics’ community to take advantage of these advances.

Read this paper on arXiv…

J. Dorelli, C. Bard, T. Chen, et. al.
Thu, 29 Dec 22
8/47

Comments: Heliophysics 2050 White Paper

Heliophysics Discovery Tools for the 21st Century: Data Science and Machine Learning Structures and Recommendations for 2020-2050 [IMA]

http://arxiv.org/abs/2212.13325


Three main points: 1. Data Science (DS) will be increasingly important to heliophysics; 2. Methods of heliophysics science discovery will continually evolve, requiring the use of learning technologies [e.g., machine learning (ML)] that are applied rigorously and that are capable of supporting discovery; and 3. To grow with the pace of data, technology, and workforce changes, heliophysics requires a new approach to the representation of knowledge.

Read this paper on arXiv…

R. McGranaghan, B. Thompson, E. Camporeale, et. al.
Thu, 29 Dec 22
35/47

Comments: 4 pages; Heliophysics 2050 White Paper

Artificial Intelligence to Enhance Mission Science Output for In-situ Observations: Dealing with the Sparse Data Challenge [IMA]

http://arxiv.org/abs/2212.13289


In the Earth’s magnetosphere, there are fewer than a dozen dedicated probes beyond low-Earth orbit making in-situ observations at any given time. As a result, we poorly understand its global structure and evolution, the mechanisms of its main activity processes, magnetic storms, and substorms. New Artificial Intelligence (AI) methods, including machine learning, data mining, and data assimilation, as well as new AI-enabled missions will need to be developed to meet this Sparse Data challenge.

Read this paper on arXiv…

M. Sitnov, G. Stephens, V. Merkin, et. al.
Thu, 29 Dec 22
36/47

Comments: 4 pages, 1 figure; Heliophysics 2050 White Paper

Galaxy Image Classification using Hierarchical Data Learning with Weighted Sampling and Label Smoothing [IMA]

http://arxiv.org/abs/2212.10081


With the development of a series of Galaxy sky surveys in recent years, the observations increased rapidly, which makes the research of machine learning methods for galaxy image recognition a hot topic. Available automatic galaxy image recognition researches are plagued by the large differences in similarity between categories, the imbalance of data between different classes, and the discrepancy between the discrete representation of Galaxy classes and the essentially gradual changes from one morphological class to the adjacent class (DDRGC). These limitations have motivated several astronomers and machine learning experts to design projects with improved galaxy image recognition capabilities. Therefore, this paper proposes a novel learning method, “Hierarchical Imbalanced data learning with Weighted sampling and Label smoothing” (HIWL). The HIWL consists of three key techniques respectively dealing with the above-mentioned three problems: (1) Designed a hierarchical galaxy classification model based on an efficient backbone network; (2) Utilized a weighted sampling scheme to deal with the imbalance problem; (3) Adopted a label smoothing technique to alleviate the DDRGC problem. We applied this method to galaxy photometric images from the Galaxy Zoo-The Galaxy Challenge, exploring the recognition of completely round smooth, in between smooth, cigar-shaped, edge-on and spiral. The overall classification accuracy is 96.32\%, and some superiorities of the HIWL are shown based on recall, precision, and F1-Score in comparing with some related works. In addition, we also explored the visualization of the galaxy image features and model attention to understand the foundations of the proposed scheme.

Read this paper on arXiv…

X. Ma, X. Li, A. Luo, et. al.
Wed, 21 Dec 22
17/81

Comments: accepted by MNRAS

Using Machine Learning to Determine Morphologies of $z<1$ AGN Host Galaxies in the Hyper Suprime-Cam Wide Survey [GA]

http://arxiv.org/abs/2212.09984


We present a machine-learning framework to accurately characterize morphologies of Active Galactic Nucleus (AGN) host galaxies within $z<1$. We first use PSFGAN to decouple host galaxy light from the central point source, then we invoke the Galaxy Morphology Network (GaMorNet) to estimate whether the host galaxy is disk-dominated, bulge-dominated, or indeterminate. Using optical images from five bands of the HSC Wide Survey, we build models independently in three redshift bins: low $(0<z<0.25)$, medium $(0.25<z<0.5)$, and high $(0.5<z<1.0)$. By first training on a large number of simulated galaxies, then fine-tuning using far fewer classified real galaxies, our framework predicts the actual morphology for $\sim$ $60\%-70\%$ host galaxies from test sets, with a classification precision of $\sim$ $80\%-95\%$, depending on redshift bin. Specifically, our models achieve disk precision of $96\%/82\%/79\%$ and bulge precision of $90\%/90\%/80\%$ (for the 3 redshift bins), at thresholds corresponding to indeterminate fractions of $30\%/43\%/42\%$. The classification precision of our models has a noticeable dependency on host galaxy radius and magnitude. No strong dependency is observed on contrast ratio. Comparing classifications of real AGNs, our models agree well with traditional 2D fitting with GALFIT. The PSFGAN+GaMorNet framework does not depend on the choice of fitting functions or galaxy-related input parameters, runs orders of magnitude faster than GALFIT, and is easily generalizable via transfer learning, making it an ideal tool for studying AGN host galaxy morphology in forthcoming large imaging survey.

Read this paper on arXiv…

C. Tian, C. Urry, A. Ghosh, et. al.
Wed, 21 Dec 22
40/81

Comments: Accepted for publication in The Astrophysical Journal. 35 Pages. 25 Figures

Identifying AGN host galaxies with convolutional neural networks [GA]

http://arxiv.org/abs/2212.07881


Active galactic nuclei (AGN) are supermassive black holes with luminous accretion disks found in some galaxies, and are thought to play an important role in galaxy evolution. However, traditional optical spectroscopy for identifying AGN requires time-intensive observations. We train a convolutional neural network (CNN) to distinguish AGN host galaxies from non-active galaxies using a sample of 210,000 Sloan Digital Sky Survey galaxies. We evaluate the CNN on 33,000 galaxies that are spectrally classified as composites, and find correlations between galaxy appearances and their CNN classifications, which hint at evolutionary processes that affect both galaxy morphology and AGN activity. With the advent of the Vera C. Rubin Observatory, Nancy Grace Roman Space Telescope, and other wide-field imaging telescopes, deep learning methods will be instrumental for quickly and reliably shortlisting AGN samples for future analyses.

Read this paper on arXiv…

Z. Guo, J. Wu and C. Sharon
Fri, 16 Dec 22
28/72

Comments: 6 pages, 2 figures. Accepted to the 2022 NeurIPS conference ML4PS workshop

A Neural Network Approach for Selecting Track-like Events in Fluorescence Telescope Data [IMA]

http://arxiv.org/abs/2212.03787


In 2016-2017, TUS, the world’s first experiment for testing the possibility of registering ultra-high energy cosmic rays (UHECRs) by their fluorescent radiation in the night atmosphere of Earth was carried out. Since 2019, the Russian-Italian fluorescence telescope (FT) Mini-EUSO (“UV Atmosphere”) has been operating on the ISS. The stratospheric experiment EUSO-SPB2, which will employ an FT for registering UHECRs, is planned for 2023. We show how a simple convolutional neural network can be effectively used to find track-like events in the variety of data obtained with such instruments.

Read this paper on arXiv…

M. Zotov and D. Sokolinskii
Thu, 8 Dec 22
15/63

Comments: 5 pages, to be published in proceedings of the 37th Russian Cosmic Ray Conference (2022)

Incorporating Polar Field Data for Improved Solar Flare Prediction [SSA]

http://arxiv.org/abs/2212.01730


In this paper, we consider incorporating data associated with the sun’s north and south polar field strengths to improve solar flare prediction performance using machine learning models. When used to supplement local data from active regions on the photospheric magnetic field of the sun, the polar field data provides global information to the predictor. While such global features have been previously proposed for predicting the next solar cycle’s intensity, in this paper we propose using them to help classify individual solar flares. We conduct experiments using HMI data employing four different machine learning algorithms that can exploit polar field information. Additionally, we propose a novel probabilistic mixture of experts model that can simply and effectively incorporate polar field data and provide on-par prediction performance with state-of-the-art solar flare prediction algorithms such as the Recurrent Neural Network (RNN). Our experimental results indicate the usefulness of the polar field data for solar flare prediction, which can improve Heidke Skill Score (HSS2) by as much as 10.1%.

Read this paper on arXiv…

M. Aktukmak, Z. Sun, M. Bobra, et. al.
Tue, 6 Dec 22
23/87

Comments: N/A

Applications of AI in Astronomy [IMA]

http://arxiv.org/abs/2212.01493


We provide a brief, and inevitably incomplete overview of the use of Machine Learning (ML) and other AI methods in astronomy, astrophysics, and cosmology. Astronomy entered the big data era with the first digital sky surveys in the early 1990s and the resulting Terascale data sets, which required automating of many data processing and analysis tasks, for example the star-galaxy separation, with billions of feature vectors in hundreds of dimensions. The exponential data growth continued, with the rise of synoptic sky surveys and the Time Domain Astronomy, with the resulting Petascale data streams and the need for a real-time processing, classification, and decision making. A broad variety of classification and clustering methods have been applied for these tasks, and this remains a very active area of research. Over the past decade we have seen an exponential growth of the astronomical literature involving a variety of ML/AI applications of an ever increasing complexity and sophistication. ML and AI are now a standard part of the astronomical toolkit. As the data complexity continues to increase, we anticipate further advances leading towards a collaborative human-AI discovery.

Read this paper on arXiv…

S. Djorgovski, A. Mahabal, M. Graham, et. al.
Tue, 6 Dec 22
79/87

Comments: 12 pages, 1 figure, an invited review chapter, to appear in: Artificial Intelligence for Science, eds. A. Choudhary, G. Fox and T. Hey, Singapore: World Scientific, in press (2023)

Using a Conditional Generative Adversarial Network to Control the Statistical Characteristics of Generated Images for IACT Data Analysis [IMA]

http://arxiv.org/abs/2211.15807


Generative adversarial networks are a promising tool for image generation in the astronomy domain. Of particular interest are conditional generative adversarial networks (cGANs), which allow you to divide images into several classes according to the value of some property of the image, and then specify the required class when generating new images. In the case of images from Imaging Atmospheric Cherenkov Telescopes (IACTs), an important property is the total brightness of all image pixels (image size), which is in direct correlation with the energy of primary particles. We used a cGAN technique to generate images similar to whose obtained in the TAIGA-IACT experiment. As a training set, we used a set of two-dimensional images generated using the TAIGA Monte Carlo simulation software. We artificiallly divided the training set into 10 classes, sorting images by size and defining the boundaries of the classes so that the same number of images fall into each class. These classes were used while training our network. The paper shows that for each class, the size distribution of the generated images is close to normal with the mean value located approximately in the middle of the corresponding class. We also show that for the generated images, the total image size distribution obtained by summing the distributions over all classes is close to the original distribution of the training set. The results obtained will be useful for more accurate generation of realistic synthetic images similar to the ones taken by IACTs.

Read this paper on arXiv…

J. Dubenskaya, A. Kryukov, A. Demichev, et. al.
Wed, 30 Nov 22
37/81

Comments: N/A

Neural networks: solving the chemistry of the interstellar medium [GA]

http://arxiv.org/abs/2211.15688


Non-equilibrium chemistry is a key process in the study of the InterStellar Medium (ISM), in particular the formation of molecular clouds and thus stars. However, computationally it is among the most difficult tasks to include in astrophysical simulations, because of the typically high (>40) number of reactions, the short evolutionary timescales (about $10^4$ times less than the ISM dynamical time) and the characteristic non-linearity and stiffness of the associated Ordinary Differential Equations system (ODEs). In this proof of concept work, we show that Physics Informed Neural Networks (PINN) are a viable alternative to traditional ODE time integrators for stiff thermo-chemical systems, i.e. up to molecular hydrogen formation (9 species and 46 reactions). Testing different chemical networks in a wide range of densities ($-2< \log n/{\rm cm}^{-3}< 3$) and temperatures ($1 < \log T/{\rm K}< 5$), we find that a basic architecture can give a comfortable convergence only for simplified chemical systems: to properly capture the sudden chemical and thermal variations a Deep Galerkin Method is needed. Once trained ($\sim 10^3$ GPUhr), the PINN well reproduces the strong non-linear nature of the solutions (errors $\lesssim 10\%$) and can give speed-ups up to a factor of $\sim 200$ with respect to traditional ODE solvers. Further, the latter have completion times that vary by about $\sim 30\%$ for different initial $n$ and $T$, while the PINN method gives negligible variations. Both the speed-up and the potential improvement in load balancing imply that PINN-powered simulations are a very palatable way to solve complex chemical calculation in astrophysical and cosmological problems.

Read this paper on arXiv…

L. Branca and A. Pallottini
Wed, 30 Nov 22
62/81

Comments: 16 pages, 12 figures, accepted for publication on MNRAS

Exoplanet Detection by Machine Learning with Data Augmentation [EPA]

http://arxiv.org/abs/2211.15577


It has recently been demonstrated that deep learning has significant potential to automate parts of the exoplanet detection pipeline using light curve data from satellites such as Kepler \cite{borucki2010kepler} \cite{koch2010kepler} and NASA’s Transiting Exoplanet Survey Satellite (TESS) \cite{ricker2010transiting}. Unfortunately, the smallness of the available datasets makes it difficult to realize the level of performance one expects from powerful network architectures.
In this paper, we investigate the use of data augmentation techniques on light curve data from to train neural networks to identify exoplanets. The augmentation techniques used are of two classes: Simple (e.g. additive noise augmentation) and learning-based (e.g. first training a GAN \cite{goodfellow2020generative} to generate new examples). We demonstrate that data augmentation has a potential to improve model performance for the exoplanet detection problem, and recommend the use of augmentation based on generative models as more data becomes available.

Read this paper on arXiv…

K. Aydoğan
Tue, 29 Nov 22
19/80

Comments: N/A

When Spectral Modeling Meets Convolutional Networks: A Method for Discovering Reionization-era Lensed Quasars in Multi-band Imaging Data [GA]

http://arxiv.org/abs/2211.14543


Over the last two decades, around three hundred quasars have been discovered at $z\gtrsim6$, yet only one was identified as being strong-gravitationally lensed. We explore a new approach, enlarging the permitted spectral parameter space while introducing a new spatial geometry veto criterion, implemented via image-based deep learning. We made the first application of this approach in a systematic search for reionization-era lensed quasars, using data from the Dark Energy Survey, the Visible and Infrared Survey Telescope for Astronomy Hemisphere Survey, and the Wide-field Infrared Survey Explorer. Our search method consists of two main parts: (i) pre-selection of the candidates based on their spectral energy distributions (SEDs) using catalog-level photometry and (ii) relative probabilities calculation of being a lens or some contaminant utilizing a convolutional neural network (CNN) classification. The training datasets are constructed by painting deflected point-source lights over actual galaxy images to generate realistic galaxy-quasar lens models, optimized to find systems with small image separations, i.e., Einstein radii of $\theta_\mathrm{E} \leq 1$ arcsec. Visual inspection is then performed for sources with CNN scores of $P_\mathrm{lens} > 0.1$, which led us to obtain 36 newly-selected lens candidates, waiting for spectroscopic confirmation. These findings show that automated SED modeling and deep learning pipelines, supported by modest human input, are a promising route for detecting strong lenses from large catalogs that can overcome the veto limitations of primarily dropout-based SED selection approaches.

Read this paper on arXiv…

I. Andika, K. Jahnke, A. Wel, et. al.
Tue, 29 Nov 22
67/80

Comments: 24 pages, 17 figures, and 2 tables. Accepted for publication in The Astrophysical Journal. We welcome comments from the reader

Elements of effective machine learning datasets in astronomy [IMA]

http://arxiv.org/abs/2211.14401


In this work, we identify elements of effective machine learning datasets in astronomy and present suggestions for their design and creation. Machine learning has become an increasingly important tool for analyzing and understanding the large-scale flood of data in astronomy. To take advantage of these tools, datasets are required for training and testing. However, building machine learning datasets for astronomy can be challenging. Astronomical data is collected from instruments built to explore science questions in a traditional fashion rather than to conduct machine learning. Thus, it is often the case that raw data, or even downstream processed data is not in a form amenable to machine learning. We explore the construction of machine learning datasets and we ask: what elements define effective machine learning datasets? We define effective machine learning datasets in astronomy to be formed with well-defined data points, structure, and metadata. We discuss why these elements are important for astronomical applications and ways to put them in practice. We posit that these qualities not only make the data suitable for machine learning, they also help to foster usable, reusable, and replicable science practices.

Read this paper on arXiv…

B. Boscoe, T. Do, E. Jones, et. al.
Tue, 29 Nov 22
78/80

Comments: N/A

A comparative study of source-finding techniques in HI emission line cubes using SoFiA, MTObjects, and supervised deep learning [IMA]

http://arxiv.org/abs/2211.12809


The 21 cm spectral line emission of atomic neutral hydrogen (HI) is one of the primary wavelengths observed in radio astronomy. However, the signal is intrinsically faint and the HI content of galaxies depends on the cosmic environment, requiring large survey volumes and survey depth to investigate the HI Universe. As the amount of data coming from these surveys continues to increase with technological improvements, so does the need for automatic techniques for identifying and characterising HI sources while considering the tradeoff between completeness and purity. This study aimed to find the optimal pipeline for finding and masking the most sources with the best mask quality and the fewest artefacts in 3D neutral hydrogen cubes. Various existing methods were explored in an attempt to create a pipeline to optimally identify and mask the sources in 3D neutral hydrogen 21 cm spectral line data cubes. Two traditional source-finding methods were tested, SoFiA and MTObjects, as well as a new supervised deep learning approach, in which a 3D convolutional neural network architecture, known as V-Net was used. These three source-finding methods were further improved by adding a classical machine learning classifier as a post-processing step to remove false positive detections. The pipelines were tested on HI data cubes from the Westerbork Synthesis Radio Telescope with additional inserted mock galaxies. SoFiA combined with a random forest classifier provided the best results, with the V-Net-random forest combination a close second. We suspect this is due to the fact that there are many more mock sources in the training set than real sources. There is, therefore, room to improve the quality of the V-Net network with better-labelled data such that it can potentially outperform SoFiA.

Read this paper on arXiv…

J. Barkai, M. Verheijen, E. Martínez, et. al.
Thu, 24 Nov 22
51/71

Comments: N/A

Using conditional variational autoencoders to generate images from atmospheric Cherenkov telescopes [IMA]

http://arxiv.org/abs/2211.12553


High-energy particles hitting the upper atmosphere of the Earth produce extensive air showers that can be detected from the ground level using imaging atmospheric Cherenkov telescopes. The images recorded by Cherenkov telescopes can be analyzed to separate gamma-ray events from the background hadron events. Many of the methods of analysis require simulation of massive amounts of events and the corresponding images by the Monte Carlo method. However, Monte Carlo simulation is computationally expensive. The data simulated by the Monte Carlo method can be augmented by images generated using faster machine learning methods such as generative adversarial networks or conditional variational autoencoders. We use a conditional variational autoencoder to generate images of gamma events from a Cherenkov telescope of the TAIGA experiment. The variational autoencoder is trained on a set of Monte Carlo events with the image size, or the sum of the amplitudes of the pixels, used as the conditional parameter. We used the trained variational autoencoder to generate new images with the same distribution of the conditional parameter as the size distribution of the Monte Carlo-simulated images of gamma events. The generated images are similar to the Monte Carlo images: a classifier neural network trained on gamma and proton events assigns them the average gamma score 0.984, with less than 3% of the events being assigned the gamma score below 0.999. At the same time, the sizes of the generated images do not match the conditional parameter used in their generation, with the average error 0.33.

Read this paper on arXiv…

S. Polyakov, A. Kryukov, A. Demichev, et. al.
Thu, 24 Nov 22
59/71

Comments: N/A

A comparative study of source-finding techniques in HI emission line cubes using SoFiA, MTObjects, and supervised deep learning [IMA]

http://arxiv.org/abs/2211.12809


The 21 cm spectral line emission of atomic neutral hydrogen (HI) is one of the primary wavelengths observed in radio astronomy. However, the signal is intrinsically faint and the HI content of galaxies depends on the cosmic environment, requiring large survey volumes and survey depth to investigate the HI Universe. As the amount of data coming from these surveys continues to increase with technological improvements, so does the need for automatic techniques for identifying and characterising HI sources while considering the tradeoff between completeness and purity. This study aimed to find the optimal pipeline for finding and masking the most sources with the best mask quality and the fewest artefacts in 3D neutral hydrogen cubes. Various existing methods were explored in an attempt to create a pipeline to optimally identify and mask the sources in 3D neutral hydrogen 21 cm spectral line data cubes. Two traditional source-finding methods were tested, SoFiA and MTObjects, as well as a new supervised deep learning approach, in which a 3D convolutional neural network architecture, known as V-Net was used. These three source-finding methods were further improved by adding a classical machine learning classifier as a post-processing step to remove false positive detections. The pipelines were tested on HI data cubes from the Westerbork Synthesis Radio Telescope with additional inserted mock galaxies. SoFiA combined with a random forest classifier provided the best results, with the V-Net-random forest combination a close second. We suspect this is due to the fact that there are many more mock sources in the training set than real sources. There is, therefore, room to improve the quality of the V-Net network with better-labelled data such that it can potentially outperform SoFiA.

Read this paper on arXiv…

J. Barkai, M. Verheijen, E. Martínez, et. al.
Thu, 24 Nov 22
16/71

Comments: N/A

Using conditional variational autoencoders to generate images from atmospheric Cherenkov telescopes [IMA]

http://arxiv.org/abs/2211.12553


High-energy particles hitting the upper atmosphere of the Earth produce extensive air showers that can be detected from the ground level using imaging atmospheric Cherenkov telescopes. The images recorded by Cherenkov telescopes can be analyzed to separate gamma-ray events from the background hadron events. Many of the methods of analysis require simulation of massive amounts of events and the corresponding images by the Monte Carlo method. However, Monte Carlo simulation is computationally expensive. The data simulated by the Monte Carlo method can be augmented by images generated using faster machine learning methods such as generative adversarial networks or conditional variational autoencoders. We use a conditional variational autoencoder to generate images of gamma events from a Cherenkov telescope of the TAIGA experiment. The variational autoencoder is trained on a set of Monte Carlo events with the image size, or the sum of the amplitudes of the pixels, used as the conditional parameter. We used the trained variational autoencoder to generate new images with the same distribution of the conditional parameter as the size distribution of the Monte Carlo-simulated images of gamma events. The generated images are similar to the Monte Carlo images: a classifier neural network trained on gamma and proton events assigns them the average gamma score 0.984, with less than 3% of the events being assigned the gamma score below 0.999. At the same time, the sizes of the generated images do not match the conditional parameter used in their generation, with the average error 0.33.

Read this paper on arXiv…

S. Polyakov, A. Kryukov, A. Demichev, et. al.
Thu, 24 Nov 22
64/71

Comments: N/A

Can denoising diffusion probabilistic models generate realistic astrophysical fields? [CEA]

http://arxiv.org/abs/2211.12444


Score-based generative models have emerged as alternatives to generative adversarial networks (GANs) and normalizing flows for tasks involving learning and sampling from complex image distributions. In this work we investigate the ability of these models to generate fields in two astrophysical contexts: dark matter mass density fields from cosmological simulations and images of interstellar dust. We examine the fidelity of the sampled cosmological fields relative to the true fields using three different metrics, and identify potential issues to address. We demonstrate a proof-of-concept application of the model trained on dust in denoising dust images. To our knowledge, this is the first application of this class of models to the interstellar medium.

Read this paper on arXiv…

N. Mudur and D. Finkbeiner
Wed, 23 Nov 22
8/71

Comments: 8 pages, 3 figures, Accepted at the Machine Learning and the Physical Sciences workshop, NeurIPS 2022

Cosmology from Galaxy Redshift Surveys with PointNet [CEA]

http://arxiv.org/abs/2211.12346


In recent years, deep learning approaches have achieved state-of-the-art results in the analysis of point cloud data. In cosmology, galaxy redshift surveys resemble such a permutation invariant collection of positions in space. These surveys have so far mostly been analysed with two-point statistics, such as power spectra and correlation functions. The usage of these summary statistics is best justified on large scales, where the density field is linear and Gaussian. However, in light of the increased precision expected from upcoming surveys, the analysis of — intrinsically non-Gaussian — small angular separations represents an appealing avenue to better constrain cosmological parameters. In this work, we aim to improve upon two-point statistics by employing a \textit{PointNet}-like neural network to regress the values of the cosmological parameters directly from point cloud data. Our implementation of PointNets can analyse inputs of $\mathcal{O}(10^4) – \mathcal{O}(10^5)$ galaxies at a time, which improves upon earlier work for this application by roughly two orders of magnitude. Additionally, we demonstrate the ability to analyse galaxy redshift survey data on the lightcone, as opposed to previously static simulation boxes at a given fixed redshift.

Read this paper on arXiv…

S. Anagnostidis, A. Thomsen, T. Kacprzak, et. al.
Wed, 23 Nov 22
26/71

Comments: N/A

Exhaustive Symbolic Regression [CEA]

http://arxiv.org/abs/2211.11461


Symbolic Regression (SR) algorithms learn analytic expressions which both accurately fit data and, unlike traditional machine-learning approaches, are highly interpretable. Conventional SR suffers from two fundamental issues which we address in this work. First, since the number of possible equations grows exponentially with complexity, typical SR methods search the space stochastically and hence do not necessarily find the best function. In many cases, the target problems of SR are sufficiently simple that a brute-force approach is not only feasible, but desirable. Second, the criteria used to select the equation which optimally balances accuracy with simplicity have been variable and poorly motivated. To address these issues we introduce a new method for SR — Exhaustive Symbolic Regression (ESR) — which systematically and efficiently considers all possible equations and is therefore guaranteed to find not only the true optimum but also a complete function ranking. Utilising the minimum description length principle, we introduce a principled method for combining these preferences into a single objective statistic. To illustrate the power of ESR we apply it to a catalogue of cosmic chronometers and the Pantheon+ sample of supernovae to learn the Hubble rate as a function of redshift, finding $\sim$40 functions (out of 5.2 million considered) that fit the data more economically than the Friedmann equation. These low-redshift data therefore do not necessarily prefer a $\Lambda$CDM expansion history, and traditional SR algorithms that return only the Pareto-front, even if they found this successfully, would not locate $\Lambda$CDM. We make our code and full equation sets publicly available.

Read this paper on arXiv…

D. Bartlett, H. Desmond and P. Ferreira
Tue, 22 Nov 22
2/83

Comments: 14 pages, 6 figures, 2 tables. Submitted to IEEE Transactions on Pattern Analysis and Machine Intelligence

3D Detection and Characterisation of ALMA Sources through Deep Learning [IMA]

http://arxiv.org/abs/2211.11462


We present a Deep-Learning (DL) pipeline developed for the detection and characterization of astronomical sources within simulated Atacama Large Millimeter/submillimeter Array (ALMA) data cubes. The pipeline is composed of six DL models: a Convolutional Autoencoder for source detection within the spatial domain of the integrated data cubes, a Recurrent Neural Network (RNN) for denoising and peak detection within the frequency domain, and four Residual Neural Networks (ResNets) for source characterization. The combination of spatial and frequency information improves completeness while decreasing spurious signal detection. To train and test the pipeline, we developed a simulation algorithm able to generate realistic ALMA observations, i.e. both sky model and dirty cubes. The algorithm simulates always a central source surrounded by fainter ones scattered within the cube. Some sources were spatially superimposed in order to test the pipeline deblending capabilities. The detection performances of the pipeline were compared to those of other methods and significant improvements in performances were achieved. Source morphologies are detected with subpixel accuracies obtaining mean residual errors of $10^{-3}$ pixel ($0.1$ mas) and $10^{-1}$ mJy/beam on positions and flux estimations, respectively. Projection angles and flux densities are also recovered within $10\%$ of the true values for $80\%$ and $73\%$ of all sources in the test set, respectively. While our pipeline is fine-tuned for ALMA data, the technique is applicable to other interferometric observatories, as SKA, LOFAR, VLBI, and VLTI.

Read this paper on arXiv…

M. Veneri, L. Tychoniec, F. Guglielmetti, et. al.
Tue, 22 Nov 22
22/83

Comments: N/A

Finding active galactic nuclei through Fink [IMA]

http://arxiv.org/abs/2211.10987


We present the Active Galactic Nuclei (AGN) classifier as currently implemented within the Fink broker. Features were built upon summary statistics of available photometric points, as well as color estimation enabled by symbolic regression. The learning stage includes an active learning loop, used to build an optimized training sample from labels reported in astronomical catalogs. Using this method to classify real alerts from the Zwicky Transient Facility (ZTF), we achieved 98.0% accuracy, 93.8% precision and 88.5% recall. We also describe the modifications necessary to enable processing data from the upcoming Vera C. Rubin Observatory Large Survey of Space and Time (LSST), and apply them to the training sample of the Extended LSST Astronomical Time-series Classification Challenge (ELAsTiCC). Results show that our designed feature space enables high performances of traditional machine learning algorithms in this binary classification task.

Read this paper on arXiv…

E. Russeil, E. Ishida, R. Montagner, et. al.
Tue, 22 Nov 22
79/83

Comments: Accepted for the Machine learning and the Physical Sciences workshop of NeurIPS 2022

Neural Inference of Gaussian Processes for Time Series Data of Quasars [GA]

http://arxiv.org/abs/2211.10305


The study of quasar light curves poses two problems: inference of the power spectrum and interpolation of an irregularly sampled time series. A baseline approach to these tasks is to interpolate a time series with a Damped Random Walk (DRW) model, in which the spectrum is inferred using Maximum Likelihood Estimation (MLE). However, the DRW model does not describe the smoothness of the time series, and MLE faces many problems in terms of optimization and numerical precision. In this work, we introduce a new stochastic model that we call $\textit{Convolved Damped Random Walk}$ (CDRW). This model introduces a concept of smoothness to a DRW, which enables it to describe quasar spectra completely. We also introduce a new method of inference of Gaussian process parameters, which we call $\textit{Neural Inference}$. This method uses the powers of state-of-the-art neural networks to improve the conventional MLE inference technique. In our experiments, the Neural Inference method results in significant improvement over the baseline MLE (RMSE: $0.318 \rightarrow 0.205$, $0.464 \rightarrow 0.444$). Moreover, the combination of both the CDRW model and Neural Inference significantly outperforms the baseline DRW and MLE in interpolating a typical quasar light curve ($\chi^2$: $0.333 \rightarrow 0.998$, $2.695 \rightarrow 0.981$). The code is published on GitHub.

Read this paper on arXiv…

E. Danilov, A. Ćiprijanović and B. Nord
Mon, 21 Nov 22
50/66

Comments: Machine Learning and the Physical Sciences workshop, NeurIPS 2022

Locating Hidden Exoplanets in ALMA Data Using Machine Learning [EPA]

http://arxiv.org/abs/2211.09541


Exoplanets in protoplanetary disks cause localized deviations from Keplerian velocity in channel maps of molecular line emission. Current methods of characterizing these deviations are time consuming, and there is no unified standard approach. We demonstrate that machine learning can quickly and accurately detect the presence of planets. We train our model on synthetic images generated from simulations and apply it to real observations to identify forming planets in real systems. Machine learning methods, based on computer vision, are not only capable of correctly identifying the presence of one or more planets, but they can also correctly constrain the location of those planets.

Read this paper on arXiv…

J. Terry, C. Hall, S. Abreau, et. al.
Fri, 18 Nov 22
28/70

Comments: 12 pages, 9 figures, 3 tables. Accepted to ApJ

Statistical Inference for Coadded Astronomical Images [IMA]

http://arxiv.org/abs/2211.09300


Coadded astronomical images are created by stacking multiple single-exposure images. Because coadded images are smaller in terms of data size than the single-exposure images they summarize, loading and processing them is less computationally expensive. However, image coaddition introduces additional dependence among pixels, which complicates principled statistical analysis of them. We present a principled Bayesian approach for performing light source parameter inference with coadded astronomical images. Our method implicitly marginalizes over the single-exposure pixel intensities that contribute to the coadded images, giving it the computational efficiency necessary to scale to next-generation astronomical surveys. As a proof of concept, we show that our method for estimating the locations and fluxes of stars using simulated coadds outperforms a method trained on single-exposure images.

Read this paper on arXiv…

M. Wang, I. Mendoza, C. Wang, et. al.
Fri, 18 Nov 22
50/70

Comments: Accepted to the NeurIPS 2022 Machine Learning and the Physical Sciences workshop. 6 pages, 2 figures

Mapping Tropical Forest Cover and Deforestation with Planet NICFI Satellite Images and Deep Learning in Mato Grosso State (Brazil) from 2015 to 2021 [EPA]

http://arxiv.org/abs/2211.09806


Monitoring changes in tree cover for rapid assessment of deforestation is considered the critical component of any climate mitigation policy for reducing carbon. Here, we map tropical tree cover and deforestation between 2015 and 2022 using 5 m spatial resolution Planet NICFI satellite images over the state of Mato Grosso (MT) in Brazil and a U-net deep learning model. The tree cover for the state was 556510.8 km$^2$ in 2015 (58.1 % of the MT State) and was reduced to 141598.5 km$^2$ (14.8 % of total area) at the end of 2021. After reaching a minimum deforested area in December 2016 with 6632.05 km$^2$, the bi-annual deforestation area only showed a slight increase between December 2016 and December 2019. A year after, the areas of deforestation almost doubled from 9944.5 km$^2$ in December 2019 to 19817.8 km$^2$ in December 2021. The high-resolution data product showed relatively consistent agreement with the official deforestation map from Brazil (67.2%) but deviated significantly from year of forest cover loss estimates from the Global Forest change (GFC) product, mainly due to large area of fire degradation observed in the GFC data. High-resolution imagery from Planet NICFI associated with deep learning technics can significantly improve mapping deforestation extent in tropics.

Read this paper on arXiv…

F. Wagner, R. Dalagnol, C. Silva-Junior, et. al.
Fri, 18 Nov 22
66/70

Comments: 18 pages, 10 figures, submitted to Remote Sensing MDPI, Special Issue “Remote Sensing of the Amazon Region”

Adapting to noise distribution shifts in flow-based gravitational-wave inference [CL]

http://arxiv.org/abs/2211.08801


Deep learning techniques for gravitational-wave parameter estimation have emerged as a fast alternative to standard samplers $\unicode{x2013}$ producing results of comparable accuracy. These approaches (e.g., DINGO) enable amortized inference by training a normalizing flow to represent the Bayesian posterior conditional on observed data. By conditioning also on the noise power spectral density (PSD) they can even account for changing detector characteristics. However, training such networks requires knowing in advance the distribution of PSDs expected to be observed, and therefore can only take place once all data to be analyzed have been gathered. Here, we develop a probabilistic model to forecast future PSDs, greatly increasing the temporal scope of DINGO networks. Using PSDs from the second LIGO-Virgo observing run (O2) $\unicode{x2013}$ plus just a single PSD from the beginning of the third (O3) $\unicode{x2013}$ we show that we can train a DINGO network to perform accurate inference throughout O3 (on 37 real events). We therefore expect this approach to be a key component to enable the use of deep learning techniques for low-latency analyses of gravitational waves.

Read this paper on arXiv…

J. Wildberger, M. Dax, S. Green, et. al.
Thu, 17 Nov 22
21/63

Comments: N/A

Normalizing Flows for Hierarchical Bayesian Analysis: A Gravitational Wave Population Study [IMA]

http://arxiv.org/abs/2211.09008


We propose parameterizing the population distribution of the gravitational wave population modeling framework (Hierarchical Bayesian Analysis) with a normalizing flow. We first demonstrate the merit of this method on illustrative experiments and then analyze four parameters of the latest LIGO data release: primary mass, secondary mass, redshift, and effective spin. Our results show that despite the small and notoriously noisy dataset, the posterior predictive distributions (assuming a prior over the parameters of the flow) of the observed gravitational wave population recover structure that agrees with robust previous phenomenological modeling results while being less susceptible to biases introduced by less-flexible distribution models. Therefore, the method forms a promising flexible, reliable replacement for population inference distributions, even when data is highly noisy.

Read this paper on arXiv…

D. Ruhe, K. Wong, M. Cranmer, et. al.
Thu, 17 Nov 22
36/63

Comments: N/A

Energy Reconstruction in Analysis of Cherenkov Telescopes Images in TAIGA Experiment Using Deep Learning Methods [IMA]

http://arxiv.org/abs/2211.08971


Imaging Atmospheric Cherenkov Telescopes (IACT) of TAIGA astrophysical complex allow to observe high energy gamma radiation helping to study many astrophysical objects and processes. TAIGA-IACT enables us to select gamma quanta from the total cosmic radiation flux and recover their primary parameters, such as energy and direction of arrival. The traditional method of processing the resulting images is an image parameterization – so-called the Hillas parameters method. At the present time Machine Learning methods, in particular Deep Learning methods have become actively used for IACT image processing. This paper presents the analysis of simulated Monte Carlo images by several Deep Learning methods for a single telescope (mono-mode) and multiple IACT telescopes (stereo-mode). The estimation of the quality of energy reconstruction was carried out and their energy spectra were analyzed using several types of neural networks. Using the developed methods the obtained results were also compared with the results obtained by traditional methods based on the Hillas parameters.

Read this paper on arXiv…

E. Gres and A. Kryukov
Thu, 17 Nov 22
63/63

Comments: N/A

Photometric identification of compact galaxies, stars and quasars using multiple neural networks [GA]

http://arxiv.org/abs/2211.08388


We present MargNet, a deep learning-based classifier for identifying stars, quasars and compact galaxies using photometric parameters and images from the Sloan Digital Sky Survey (SDSS) Data Release 16 (DR16) catalogue. MargNet consists of a combination of Convolutional Neural Network (CNN) and Artificial Neural Network (ANN) architectures. Using a carefully curated dataset consisting of 240,000 compact objects and an additional 150,000 faint objects, the machine learns classification directly from the data, minimising the need for human intervention. MargNet is the first classifier focusing exclusively on compact galaxies and performs better than other methods to classify compact galaxies from stars and quasars, even at fainter magnitudes. This model and feature engineering in such deep learning architectures will provide greater success in identifying objects in the ongoing and upcoming surveys, such as Dark Energy Survey (DES) and images from the Vera C. Rubin Observatory.

Read this paper on arXiv…

S. Chaini, A. Bagul, A. Deshpande, et. al.
Wed, 16 Nov 22
53/76

Comments: 14 pages, 10 figures, Accepted for publication in MNRAS

Hierarchical Inference of the Lensing Convergence from Photometric Catalogs with Bayesian Graph Neural Networks [CEA]

http://arxiv.org/abs/2211.07807


We present a Bayesian graph neural network (BGNN) that can estimate the weak lensing convergence ($\kappa$) from photometric measurements of galaxies along a given line of sight. The method is of particular interest in strong gravitational time delay cosmography (TDC), where characterizing the “external convergence” ($\kappa_{\rm ext}$) from the lens environment and line of sight is necessary for precise inference of the Hubble constant ($H_0$). Starting from a large-scale simulation with a $\kappa$ resolution of $\sim$1$’$, we introduce fluctuations on galaxy-galaxy lensing scales of $\sim$1$”$ and extract random sightlines to train our BGNN. We then evaluate the model on test sets with varying degrees of overlap with the training distribution. For each test set of 1,000 sightlines, the BGNN infers the individual $\kappa$ posteriors, which we combine in a hierarchical Bayesian model to yield constraints on the hyperparameters governing the population. For a test field well sampled by the training set, the BGNN recovers the population mean of $\kappa$ precisely and without bias, resulting in a contribution to the $H_0$ error budget well under 1\%. In the tails of the training set with sparse samples, the BGNN, which can ingest all available information about each sightline, extracts more $\kappa$ signal compared to a simplified version of the traditional method based on matching galaxy number counts, which is limited by sample variance. Our hierarchical inference pipeline using BGNNs promises to improve the $\kappa_{\rm ext}$ characterization for precision TDC. The implementation of our pipeline is available as a public Python package, Node to Joy.

Read this paper on arXiv…

J. Park, S. Birrer, M. Ueland, et. al.
Wed, 16 Nov 22
62/76

Comments: 15 pages, 8 figures (+ 6 pages, 2 figures in Appendix). Submitted to ApJ. Code at this https URL

Discovering Long-period Exoplanets using Deep Learning with Citizen Science Labels [EPA]

http://arxiv.org/abs/2211.06903


Automated planetary transit detection has become vital to prioritize candidates for expert analysis given the scale of modern telescopic surveys. While current methods for short-period exoplanet detection work effectively due to periodicity in the light curves, there lacks a robust approach for detecting single-transit events. However, volunteer-labelled transits recently collected by the Planet Hunters TESS (PHT) project now provide an unprecedented opportunity to investigate a data-driven approach to long-period exoplanet detection. In this work, we train a 1-D convolutional neural network to classify planetary transits using PHT volunteer scores as training data. We find using volunteer scores significantly improves performance over synthetic data, and enables the recovery of known planets at a precision and rate matching that of the volunteers. Importantly, the model also recovers transits found by volunteers but missed by current automated methods.

Read this paper on arXiv…

S. Malik, N. Eisner, C. Lintott, et. al.
Tue, 15 Nov 22
79/103

Comments: Accepted at the Machine Learning and the Physical Sciences workshop, NeurIPS 2022

Astronomia ex machina: a history, primer, and outlook on neural networks in astronomy [IMA]

http://arxiv.org/abs/2211.03796


In recent years, deep learning has infiltrated every field it has touched, reducing the need for specialist knowledge and automating the process of knowledge discovery from data. This review argues that astronomy is no different, and that we are currently in the midst of a deep learning revolution that is transforming the way we do astronomy. We trace the history of astronomical connectionism from the early days of multilayer perceptrons, through the second wave of convolutional and recurrent neural networks, to the current third wave of self-supervised and unsupervised deep learning. We then predict that we will soon enter a fourth wave of astronomical connectionism, in which finetuned versions of an all-encompassing ‘foundation’ model will replace expertly crafted deep learning models. We argue that such a model can only be brought about through a symbiotic relationship between astronomy and connectionism, whereby astronomy provides high quality multimodal data to train the foundation model, and in turn the foundation model is used to advance astronomical research.

Read this paper on arXiv…

M. Smith and J. Geach
Wed, 9 Nov 22
36/76

Comments: 60 pages, 269 references, 29 figures. Review submitted to Royal Society Open Science. Comments and feedback welcome

A Neural Network Subgrid Model of the Early Stages of Planet Formation [EPA]

http://arxiv.org/abs/2211.04160


Planet formation is a multi-scale process in which the coagulation of $\mathrm{\mu m}$-sized dust grains in protoplanetary disks is strongly influenced by the hydrodynamic processes on scales of astronomical units ($\approx 1.5\times 10^8 \,\mathrm{km}$). Studies are therefore dependent on subgrid models to emulate the micro physics of dust coagulation on top of a large scale hydrodynamic simulation. Numerical simulations which include the relevant physical effects are complex and computationally expensive. Here, we present a fast and accurate learned effective model for dust coagulation, trained on data from high resolution numerical coagulation simulations. Our model captures details of the dust coagulation process that were so far not tractable with other dust coagulation prescriptions with similar computational efficiency.

Read this paper on arXiv…

T. Pfeil, M. Cranmer, S. Ho, et. al.
Wed, 9 Nov 22
45/76

Comments: 6 pages, 4 figures, accepted at the Machine Learning and the Physical Sciences workshop, NeurIPS 2022

Posterior samples of source galaxies in strong gravitational lenses with score-based priors [IMA]

http://arxiv.org/abs/2211.03812


Inferring accurate posteriors for high-dimensional representations of the brightness of gravitationally-lensed sources is a major challenge, in part due to the difficulties of accurately quantifying the priors. Here, we report the use of a score-based model to encode the prior for the inference of undistorted images of background galaxies. This model is trained on a set of high-resolution images of undistorted galaxies. By adding the likelihood score to the prior score and using a reverse-time stochastic differential equation solver, we obtain samples from the posterior. Our method produces independent posterior samples and models the data almost down to the noise level. We show how the balance between the likelihood and the prior meet our expectations in an experiment with out-of-distribution data.

Read this paper on arXiv…

A. Adam, A. Coogan, N. Malkin, et. al.
Wed, 9 Nov 22
66/76

Comments: 5+6 pages, 3 figures, Accepted (poster + contributed talk) for the Machine Learning and the Physical Sciences Workshop at the 36th conference on Neural Information Processing Systems (NeurIPS 2022)

Regimes of charged particle dynamics in current sheets: the machine learning approach [CL]

http://arxiv.org/abs/2211.03787


Current sheets are spatially localized almost-1D structures with intense plasma currents. They play a key role in storing the magnetic field energy and they separate different plasma populations in planetary magnetospheres, the solar wind, and the solar corona. Current sheets are primary regions for the magnetic field line reconnection responsible for plasma heating and charged particle acceleration. One of the most interesting and widely observed type of 1D current sheets is the rotational discontinuity, that can be force-free or include plasma compression. Theoretical models of such 1D current sheets are based on the assumption of adiabatic motion of ions, i.e. ion adiabatic invariants are conserved. We focus on three current sheet configurations, widely observed in the Earth magnetopause and magnetotail and in the near-Earth solar wind. Magnetic field in such current sheets is supported by currents carried by transient ions, which exist only when there is a sufficient number of invariants. In this paper, we apply a novel machine learning approach, AI Poincar’e, to determine parametrical domains where adiabatic invariants are conserved. For all three current sheet configurations, these domains are quite narrow and do not cover the entire parametrical range of observed current sheets. We discuss possible interpretation of obtained results indicating that 1D current sheets are dynamical rather than static plasma equilibria.

Read this paper on arXiv…

A. Lukin, A. Artemyev, D. Vainchtein, et. al.
Wed, 9 Nov 22
71/76

Comments: N/A

Monte Carlo Techniques for Addressing Large Errors and Missing Data in Simulation-based Inference [IMA]

http://arxiv.org/abs/2211.03747


Upcoming astronomical surveys will observe billions of galaxies across cosmic time, providing a unique opportunity to map the many pathways of galaxy assembly to an incredibly high resolution. However, the huge amount of data also poses an immediate computational challenge: current tools for inferring parameters from the light of galaxies take $\gtrsim 10$ hours per fit. This is prohibitively expensive. Simulation-based Inference (SBI) is a promising solution. However, it requires simulated data with identical characteristics to the observed data, whereas real astronomical surveys are often highly heterogeneous, with missing observations and variable uncertainties determined by sky and telescope conditions. Here we present a Monte Carlo technique for treating out-of-distribution measurement errors and missing data using standard SBI tools. We show that out-of-distribution measurement errors can be approximated by using standard SBI evaluations, and that missing data can be marginalized over using SBI evaluations over nearby data realizations in the training set. While these techniques slow the inference process from $\sim 1$ sec to $\sim 1.5$ min per object, this is still significantly faster than standard approaches while also dramatically expanding the applicability of SBI. This expanded regime has broad implications for future applications to astronomical surveys.

Read this paper on arXiv…

B. Wang, J. Leja, A. Villar, et. al.
Tue, 8 Nov 22
19/79

Comments: 8 pages, 2 figures, accepted to the Machine Learning and the Physical Sciences workshop at NeurIPS 2022

A Deep Learning Approach to Generating Photospheric Vector Magnetograms of Solar Active Regions for SOHO/MDI Using SDO/HMI and BBSO Data [SSA]

http://arxiv.org/abs/2211.02278


Solar activity is usually caused by the evolution of solar magnetic fields. Magnetic field parameters derived from photospheric vector magnetograms of solar active regions have been used to analyze and forecast eruptive events such as solar flares and coronal mass ejections. Unfortunately, the most recent solar cycle 24 was relatively weak with few large flares, though it is the only solar cycle in which consistent time-sequence vector magnetograms have been available through the Helioseismic and Magnetic Imager (HMI) on board the Solar Dynamics Observatory (SDO) since its launch in 2010. In this paper, we look into another major instrument, namely the Michelson Doppler Imager (MDI) on board the Solar and Heliospheric Observatory (SOHO) from 1996 to 2010. The data archive of SOHO/MDI covers more active solar cycle 23 with many large flares. However, SOHO/MDI data only has line-of-sight (LOS) magnetograms. We propose a new deep learning method, named MagNet, to learn from combined LOS magnetograms, Bx and By taken by SDO/HMI along with H-alpha observations collected by the Big Bear Solar Observatory (BBSO), and to generate vector components Bx’ and By’, which would form vector magnetograms with observed LOS data. In this way, we can expand the availability of vector magnetograms to the period from 1996 to present. Experimental results demonstrate the good performance of the proposed method. To our knowledge, this is the first time that deep learning has been used to generate photospheric vector magnetograms of solar active regions for SOHO/MDI using SDO/HMI and H-alpha data.

Read this paper on arXiv…

H. Jiang, Q. Li, Z. Hu, et. al.
Mon, 7 Nov 22
23/67

Comments: 15 pages, 6 figures

Towards Asteroid Detection in Microlensing Surveys with Deep Learning [EPA]

http://arxiv.org/abs/2211.02239


Asteroids are an indelible part of most astronomical surveys though only a few surveys are dedicated to their detection. Over the years, high cadence microlensing surveys have amassed several terabytes of data while scanning primarily the Galactic Bulge and Magellanic Clouds for microlensing events and thus provide a treasure trove of opportunities for scientific data mining. In particular, numerous asteroids have been observed by visual inspection of selected images. This paper presents novel deep learning-based solutions for the recovery and discovery of asteroids in the microlensing data gathered by the MOA project. Asteroid tracklets can be clearly seen by combining all the observations on a given night and these tracklets inform the structure of the dataset. Known asteroids were identified within these composite images and used for creating the labelled datasets required for supervised learning. Several custom CNN models were developed to identify images with asteroid tracklets. Model ensembling was then employed to reduce the variance in the predictions as well as to improve the generalisation error, achieving a recall of 97.67%. Furthermore, the YOLOv4 object detector was trained to localize asteroid tracklets, achieving a mean Average Precision (mAP) of 90.97%. These trained networks will be applied to 16 years of MOA archival data to find both known and unknown asteroids that have been observed by the survey over the years. The methodologies developed can be adapted for use by other surveys for asteroid recovery and discovery.

Read this paper on arXiv…

P. Cowan, I. Bond and N. Reyes
Mon, 7 Nov 22
37/67

Comments: 11 pages, 10 figures, submitted to Astronomy and Computing

Fast and robust Bayesian Inference using Gaussian Processes with GPry [CEA]

http://arxiv.org/abs/2211.02045


We present the GPry algorithm for fast Bayesian inference of general (non-Gaussian) posteriors with a moderate number of parameters. GPry does not need any pre-training, special hardware such as GPUs, and is intended as a drop-in replacement for traditional Monte Carlo methods for Bayesian inference. Our algorithm is based on generating a Gaussian Process surrogate model of the log-posterior, aided by a Support Vector Machine classifier that excludes extreme or non-finite values. An active learning scheme allows us to reduce the number of required posterior evaluations by two orders of magnitude compared to traditional Monte Carlo inference. Our algorithm allows for parallel evaluations of the posterior at optimal locations, further reducing wall-clock times. We significantly improve performance using properties of the posterior in our active learning scheme and for the definition of the GP prior. In particular we account for the expected dynamical range of the posterior in different dimensionalities. We test our model against a number of synthetic and cosmological examples. GPry outperforms traditional Monte Carlo methods when the evaluation time of the likelihood (or the calculation of theoretical observables) is of the order of seconds; for evaluation times of over a minute it can perform inference in days that would take months using traditional methods. GPry is distributed as an open source Python package (pip install gpry) and can also be found at https://github.com/jonaselgammal/GPry.

Read this paper on arXiv…

J. Gammal, N. Schöneberg, J. Torrado, et. al.
Fri, 4 Nov 22
33/84

Comments: 36 pages, 12 figures. Comments are welcome

Data-Driven Modeling of Landau Damping by Physics-Informed Neural Networks [CL]

http://arxiv.org/abs/2211.01021


Kinetic approaches are generally accurate in dealing with microscale plasma physics problems but are computationally expensive for large-scale or multiscale systems. One of the long-standing problems in plasma physics is the integration of kinetic physics into fluid models, which is often achieved through sophisticated analytical closure terms. In this study, we successfully construct a multi-moment fluid model with an implicit fluid closure included in the neural network using machine learning. The multi-moment fluid model is trained with a small fraction of sparsely sampled data from kinetic simulations of Landau damping, using the physics-informed neural network (PINN) and the gradient-enhanced physics-informed neural network (gPINN). The multi-moment fluid model constructed using either PINN or gPINN reproduces the time evolution of the electric field energy, including its damping rate, and the plasma dynamics from the kinetic simulations. For the first time, we introduce a new variant of the gPINN architecture, namely, gPINN$p$ to capture the Landau damping process. Instead of including the gradients of all the equation residuals, gPINN$p$ only adds the gradient of the pressure equation residual as one additional constraint. Among the three approaches, the gPINN$p$-constructed multi-moment fluid model offers the most accurate results. This work sheds new light on the accurate and efficient modeling of large-scale systems, which can be extended to complex multiscale laboratory, space, and astrophysical plasma physics problems.

Read this paper on arXiv…

Y. Qin, J. Ma, M. Jiang, et. al.
Thu, 3 Nov 22
17/59

Comments: 11 pages, 7 figures

Semi-Supervised Domain Adaptation for Cross-Survey Galaxy Morphology Classification and Anomaly Detection [GA]

http://arxiv.org/abs/2211.00677


In the era of big astronomical surveys, our ability to leverage artificial intelligence algorithms simultaneously for multiple datasets will open new avenues for scientific discovery. Unfortunately, simply training a deep neural network on images from one data domain often leads to very poor performance on any other dataset. Here we develop a Universal Domain Adaptation method DeepAstroUDA, capable of performing semi-supervised domain alignment that can be applied to datasets with different types of class overlap. Extra classes can be present in any of the two datasets, and the method can even be used in the presence of unknown classes. For the first time, we demonstrate the successful use of domain adaptation on two very different observational datasets (from SDSS and DECaLS). We show that our method is capable of bridging the gap between two astronomical surveys, and also performs well for anomaly detection and clustering of unknown data in the unlabeled dataset. We apply our model to two examples of galaxy morphology classification tasks with anomaly detection: 1) classifying spiral and elliptical galaxies with detection of merging galaxies (three classes including one unknown anomaly class); 2) a more granular problem where the classes describe more detailed morphological properties of galaxies, with the detection of gravitational lenses (ten classes including one unknown anomaly class).

Read this paper on arXiv…

A. Ćiprijanović, A. Lewis, K. Pedro, et. al.
Thu, 3 Nov 22
30/59

Comments: 3 figures, 1 table; accepted to Machine Learning and the Physical Sciences – Workshop at the 36th conference on Neural Information Processing Systems (NeurIPS)

A robust estimator of mutual information for deep learning interpretability [CL]

http://arxiv.org/abs/2211.00024


We develop the use of mutual information (MI), a well-established metric in information theory, to interpret the inner workings of deep learning models. To accurately estimate MI from a finite number of samples, we present GMM-MI (pronounced $“$Jimmie$”$), an algorithm based on Gaussian mixture models that can be applied to both discrete and continuous settings. GMM-MI is computationally efficient, robust to the choice of hyperparameters and provides the uncertainty on the MI estimate due to the finite sample size. We extensively validate GMM-MI on toy data for which the ground truth MI is known, comparing its performance against established mutual information estimators. We then demonstrate the use of our MI estimator in the context of representation learning, working with synthetic data and physical datasets describing highly non-linear processes. We train deep learning models to encode high-dimensional data within a meaningful compressed (latent) representation, and use GMM-MI to quantify both the level of disentanglement between the latent variables, and their association with relevant physical quantities, thus unlocking the interpretability of the latent representation. We make GMM-MI publicly available.

Read this paper on arXiv…

D. Piras, H. Peiris, A. Pontzen, et. al.
Wed, 2 Nov 22
21/67

Comments: 13 pages, 7 figures, comments welcome. GMM-MI available at this https URL

Learning to Detect Interesting Anomalies [CL]

http://arxiv.org/abs/2210.16334


Anomaly detection algorithms are typically applied to static, unchanging, data features hand-crafted by the user. But how does a user systematically craft good features for anomalies that have never been seen? Here we couple deep learning with active learning — in which an Oracle iteratively labels small amounts of data selected algorithmically over a series of rounds — to automatically and dynamically improve the data features for efficient outlier detection. This approach, AHUNT, shows excellent performance on MNIST, CIFAR10, and Galaxy-DESI data, significantly outperforming both standard anomaly detection and active learning algorithms with static feature spaces. Beyond improved performance, AHUNT also allows the number of anomaly classes to grow organically in response to Oracle’s evaluations. Extensive ablation studies explore the impact of Oracle question selection strategy and loss function on performance. We illustrate how the dynamic anomaly class taxonomy represents another step towards fully personalized rankings of different anomaly classes that reflect a user’s interests, allowing the algorithm to learn to ignore statistically significant but uninteresting outliers (e.g., noise). This should prove useful in the era of massive astronomical datasets serving diverse sets of users who can only review a tiny subset of the incoming data.

Read this paper on arXiv…

A. Sadr, B. Bassett and E. Sekyi
Tue, 1 Nov 22
39/100

Comments: 10 pages, 7 figures

ODNet: A Convolutional Neural Network for Asteroid Occultation Detection [EPA]

http://arxiv.org/abs/2210.16440


We propose to design and build an algorithm that will use a Convolutional Neural Network (CNN) and observations from the Unistellar network to reliably detect asteroid occultations. The Unistellar Network, made of more than 10,000 digital telescopes owned by citizen scientists, and is regularly used to record asteroid occultations. In order to process the increasing amount of observational produced by this network, we need a quick and reliable way to analyze occultations. In an effort to solve this problem, we trained a CNN with artificial images of stars with twenty different types of photometric signals. Inputs to the network consists of two stacks of snippet images of stars, one around the star that is supposed to be occulted and a reference star used for comparison. We need the reference star to distinguish between a true occultation and artefacts introduced by poor atmospheric condition. Our Occultation Detection Neural Network (ODNet), can analyze three sequence of stars per second with 91\% of precision and 87\% of recall. The algorithm is sufficiently fast and robust so we can envision incorporating onboard the eVscopes to deliver real-time results. We conclude that citizen science represents an important opportunity for the future studies and discoveries in the occultations, and that application of artificial intelligence will permit us to to take better advantage of the ever-growing quantity of data to categorize asteroids.

Read this paper on arXiv…

D. Cazeneuve, F. Marchis, G. Blaclard, et. al.
Tue, 1 Nov 22
57/100

Comments: 17 pages, 10 figures, 3 tables, accepted for publication in Astrophysical Journal

Deep network series for large-scale high-dynamic range imaging [IMA]

http://arxiv.org/abs/2210.16060


We propose a new approach for large-scale high-dynamic range computational imaging. Deep Neural Networks (DNNs) trained end-to-end can solve linear inverse imaging problems almost instantaneously. While unfolded architectures provide necessary robustness to variations of the measurement setting, embedding large-scale measurement operators in DNN architectures is impractical. Alternative Plug-and-Play (PnP) approaches, where the denoising DNNs are blind to the measurement setting, have proven effective to address scalability and high-dynamic range challenges, but rely on highly iterative algorithms. We propose a residual DNN series approach, where the reconstructed image is built as a sum of residual images progressively increasing the dynamic range, and estimated iteratively by DNNs taking the back-projected data residual of the previous iteration as input. We demonstrate on simulations for radio-astronomical imaging that a series of only few terms provides a high-dynamic range reconstruction of similar quality to state-of-the-art PnP approaches, at a fraction of the cost.

Read this paper on arXiv…

A. Aghabiglou, M. Terris, A. Jackson, et. al.
Mon, 31 Oct 22
9/60

Comments: 5 pages, 4 figures, 1 table

Towards solving model bias in cosmic shear forward modeling [CEA]

http://arxiv.org/abs/2210.16243


As the volume and quality of modern galaxy surveys increase, so does the difficulty of measuring the cosmological signal imprinted in galaxy shapes. Weak gravitational lensing sourced by the most massive structures in the Universe generates a slight shearing of galaxy morphologies called cosmic shear, key probe for cosmological models. Modern techniques of shear estimation based on statistics of ellipticity measurements suffer from the fact that the ellipticity is not a well-defined quantity for arbitrary galaxy light profiles, biasing the shear estimation. We show that a hybrid physical and deep learning Hierarchical Bayesian Model, where a generative model captures the galaxy morphology, enables us to recover an unbiased estimate of the shear on realistic galaxies, thus solving the model bias.

Read this paper on arXiv…

B. Remy, F. Lanusse and J. Starck
Mon, 31 Oct 22
51/60

Comments: 6 pages, accepted to the Machine Learning and the Physical Sciences Workshop at NeurIPS 2022

Interstellar Object Accessibility and Mission Design [EPA]

http://arxiv.org/abs/2210.14980


Interstellar objects (ISOs) are fascinating and under-explored celestial objects, providing physical laboratories to understand the formation of our solar system and probe the composition and properties of material formed in exoplanetary systems. This paper will discuss the accessibility of and mission design to ISOs with varying characteristics, including a discussion of state covariance estimation over the course of a cruise, handoffs from traditional navigation approaches to novel autonomous navigation for fast flyby regimes, and overall recommendations about preparing for the future in situ exploration of these targets. The lessons learned also apply to the fast flyby of other small bodies including long-period comets and potentially hazardous asteroids, which also require a tactical response with similar characteristics

Read this paper on arXiv…

B. Donitz, D. Mages, H. Tsukamoto, et. al.
Fri, 28 Oct 22
47/56

Comments: Accepted at IEEE Aerospace Conference

$\texttt{Mangrove}$: Learning Galaxy Properties from Merger Trees [GA]

http://arxiv.org/abs/2210.13473


Efficiently mapping baryonic properties onto dark matter is a major challenge in astrophysics. Although semi-analytic models (SAMs) and hydrodynamical simulations have made impressive advances in reproducing galaxy observables across cosmologically significant volumes, these methods still require significant computation times, representing a barrier to many applications. Graph Neural Networks (GNNs) have recently proven to be the natural choice for learning physical relations. Among the most inherently graph-like structures found in astrophysics are the dark matter merger trees that encode the evolution of dark matter halos. In this paper we introduce a new, graph-based emulator framework, $\texttt{Mangrove}$, and show that it emulates the galactic stellar mass, cold gas mass and metallicity, instantaneous and time-averaged star formation rate, and black hole mass — as predicted by a SAM — with root mean squared error up to two times lower than other methods across a $(75 Mpc/h)^3$ simulation box in 40 seconds, 4 orders of magnitude faster than the SAM. We show that $\texttt{Mangrove}$ allows for quantification of the dependence of galaxy properties on merger history. We compare our results to the current state of the art in the field and show significant improvements for all target properties. $\texttt{Mangrove}$ is publicly available.

Read this paper on arXiv…

C. Jespersen, M. Cranmer, P. Melchior, et. al.
Wed, 26 Oct 22
44/73

Comments: 15 pages, 9 figures, 3 tables, 10 pages of Appendices. Accepted for publication in ApJ

O-type Stars Stellar Parameter Estimation Using Recurrent Neural Networks [IMA]

http://arxiv.org/abs/2210.12791


In this paper, we present a deep learning system approach to estimating luminosity, effective temperature, and surface gravity of O-type stars using the optical region of the stellar spectra. In previous work, we compare a set of machine learning and deep learning algorithms in order to establish a reliable way to fit a stellar model using two methods: the classification of the stellar spectra models and the estimation of the physical parameters in a regression-type task. Here we present the process to estimate individual physical parameters from an artificial neural network perspective with the capacity to handle stellar spectra with a low signal-to-noise ratio (S/N), in the $<$20 S/N boundaries. The development of three different recurrent neural network systems, the training process using stellar spectra models, the test over nine different observed stellar spectra, and the comparison with estimations in previous works are presented. Additionally, characterization methods for stellar spectra in order to reduce the dimensionality of the input data for the system and optimize the computational resources are discussed.

Read this paper on arXiv…

M. R., L. Corral, C. Fierro-Santillán, et. al.
Tue, 25 Oct 22
12/111

Comments: N/A

Removing Radio Frequency Interference from Auroral Kilometric Radiation with Stacked Autoencoders [IMA]

http://arxiv.org/abs/2210.12931


Radio frequency data in astronomy enable scientists to analyze astrophysical phenomena. However, these data can be corrupted by a host of radio frequency interference (RFI) sources that limit the ability to observe underlying natural processes. In this study, we extended recent work in image processing to remove RFI from time-frequency spectrograms containing auroral kilometric radiation (AKR), a coherent radio emission originating from the Earth’s auroral zones that is used to study astrophysical plasmas. We present a Denoising Autoencoder for Auroral Radio Emissions (DAARE) trained with synthetic spectrograms to denoise AKR spectrograms collected at the South Pole Station. DAARE achieved 42.2 peak-signal-to-noise ratio (PSNR) and 0.981 structural similarity (SSIM) on synthesized AKR observations, improving PSNR by 3.9 and SSIM by 0.064 compared to state-of-the-art filtering and denoising networks. Qualitative comparisons demonstrate DAARE’s denoising capability to effectively remove RFI from real AKR observations, despite being trained completely on a dataset of simulated AKR. The framework for simulating AKR, training DAARE, and employing DAARE can be accessed at https://github.com/Cylumn/daare.

Read this paper on arXiv…

A. Chang, M. Knapp, J. LaBelle, et. al.
Tue, 25 Oct 22
82/111

Comments: 5 pages, 3 figures, 48th International Conference on Acoustics, Speech and Signal Processing (ICASSP 2023)