Searcharxiv⌕ Search

arXiv subjects

Daniel Muthukrishna

Publications and source records attributed to Daniel Muthukrishna.

At least 19 recordsLinked to original sources
arXiv2026

Deep Learning for Astrophysics: An Open Textbook from the NASA Cosmic Origins AI/ML Science and Technology Interest Group

Recent community assessments identify education as a principal barrier to adopting modern machine learning in astronomy. We present Deep Learning for Astrophysics, a freely available textbook at https://deeplearning4astro.com, curated from the NASA Cosmic Origins Artificial Intelligence and Machine Learning Science and Technology Interest Group (AI/ML STIG) lecture series. The book collects 23 chapters by 17 lecturers across six parts, moving from computational foundations and deep-learning architectures through generative modeling, simulation-based inference, reinforcement learning, and large-language-model agents to the practice of AI-laden science. Many include executable notebooks using astronomical data.

astro-ph.IM↗
arXiv2026

Learning What's Real: Disentangling Signal and Measurement Artifacts in Multi-Sensor Data, with Applications to Astrophysics

Data collected from the physical world is always a combination of multiple sources: an underlying signal from the physical process of interest and a signal from measurement-dependent artifacts from the sensor or instrument. This secondary signal acts as a confounding factor, limiting our ability to extract information about the physics underlying the phenomena we observe. Furthermore, it complicates the combination of observations in heterogeneous or multi-instrument settings. We propose a deep learning framework that leverages overlapping observations, a dual-encoder architecture, and a counterfactual generation objective to disentangle these factors of variation. The resulting representations explicitly separate intrinsic signals from sensor-specific distortions and noise, and can be used for counterfactual view generation, parameter inference unconfounded by measurement distortions, and instrument-independent similarity search. We demonstrate the effectiveness of our approach on astrophysical galaxy images from the DESI Legacy Imaging Survey (Legacy) and the Hyper Suprime-Cam (HSC) Survey as a representative multi-instrument setting. This framework provides a general recipe for scientific and multi-modal self-supervised pretraining: construct training pairs from overlapping observations of the same physical system, treat sensor- or modality-specific effects as augmentations, and learn invariant representations through counterfactual generation.

astro-ph.IM↗
arXiv2026

ASTRAFier: A Novel and Scalable Transformer-based Stellar Variability Classifier

Photometric missions such as Kepler and TESS have generated millions of light curves covering almost the entire sky, offering unprecedented opportunities to study stellar variability and advance our understanding of the Universe. In this data-rich environment, machine learning has emerged as a powerful tool to efficiently and accurately process and classify light curves according to their type of stellar variability. In this work, we introduce ASTRAFier: a novel Transformer-based model for variability classification that integrates Bidirectional Long Short-Term Memory (BiLSTM) and Convolutional Neural Networks (CNNs). The model operates directly on time series without requiring feature engineering, creating an easy-to-maintain and efficient end-to-end classification framework. We train and validate our model using both Kepler and TESS light curves and, respectively, achieve a classification accuracy of $94.26\%$ on Kepler and $88.22\%$ on TESS. We demonstrate scalability by deploying our model on $\sim 2.8$ million TESS light curves from sectors 14, 15, and 26 (Kepler Field-of-View) delivered by MIT's Quick-look Pipeline (QLP) and release the resulting stellar variability catalog.

astro-ph.IM↗
arXiv2026

QLP Data Release Notes 004: TESS-Gaia Light Curve Photometry Implementation

The Quick-Look Pipeline (QLP; Huang et al. 2020, Kunimoto et al. 2021 and references therein) generates light curves for up to 2 million stars every 27.4 days observed by TESS as part of its planet search. As machine learning methods enable deeper searches and scientific priorities shift toward fainter stars, there is a motivation for QLP to perform better at fainter magnitudes. We have adopted the photometry methods employed by the TESS-Gaia Light Curve package (Han & Brandt 2023), which has been shown to have better noise characteristics than the original QLP photometry from 10.5 $<$ $T$ $<$ 13.5. We still perform aperture photometry and deliver 3 apertures, and 3 levels of detrending for all stars brighter than $T$ = 13.5, so the changes should be seamless for external users. This method is implemented as of Sector 94 in QLP light curves and is providing users with higher precision light curves and allows detection of fainter signals in our planet searches.

astro-ph.EP↗
arXiv2025

Simulation-Based Pretraining and Domain Adaptation for Astronomical Time Series with Minimal Labeled Data

Astronomical time-series analysis faces a critical limitation: the scarcity of labeled observational data. We present a pre-training approach that leverages simulations, significantly reducing the need for labeled examples from real observations. Our models, trained on simulated data from multiple astronomical surveys (ZTF and LSST), learn generalizable representations that transfer effectively to downstream tasks. Using classifier-based architectures enhanced with contrastive and adversarial objectives, we create domain-agnostic models that demonstrate substantial performance improvements over baseline methods in classification, redshift estimation, and anomaly detection when fine-tuned with minimal real data. Remarkably, our models exhibit effective zero-shot transfer capabilities, achieving comparable performance on future telescope (LSST) simulations when trained solely on existing telescope (ZTF) data. Furthermore, they generalize to very different astronomical phenomena (namely variable stars from NASA's \textit{Kepler} telescope) despite being trained on transient events, demonstrating cross-domain capabilities. Our approach provides a practical solution for building general models when labeled data is scarce, but domain knowledge can be encoded in simulations.

astro-ph.IM↗
arXiv2025

ABC-SN: Attention Based Classifier for Supernova Spectra

While significant advances have been made in photometric classification ahead of the millions of transient events and hundreds of supernovae (SNe) each night that the Vera C. Rubin Observatory Legacy Survey of Space and Time (LSST) will discover, classifying SNe spectroscopically remains the best way to determine most subtypes of SNe. Traditional spectrum classification tools use template matching techniques (eg., SNID, SuperFit) and require significant human supervision. Two deep learning spectral classifiers, DASH and SNIascore, define the state of the art, but SNIascore is a binary classifier devoted to maximizing the purity of the SN Ia-norm sample, while DASH is no longer maintained and the original work suffers from contamination of multi-epoch spectra in the training and test sets. We have explored several neural network architectures in order to create a new automated method for classifying SN subtypes, settling on an attention-based model we call ABC-SN. We benchmark our results against an updated version of DASH, thus providing the community with an up-to-date general-purpose SN classifier. Our dataset is comprised of ten different SN subtypes, including subtypes of SN Ia, core collapse, and interacting SNe. We find that ABC-SN outperforms DASH for nearly all classes, including an improvement of $26\%$ in SN Ia completeness ($\sim88\%$) and $2.4\%$ in SN Ia purity ($\sim95\%$) when unthresholded (improvements for each class can further be obtained by tuned thresholds), and we discuss the limitations of current SN datasets for benchmarking performance.

astro-ph.IM↗
arXiv2025

Causal Foundation Models: Disentangling Physics from Instrument Properties

Foundation models for structured time series data must contend with a fundamental challenge: observations often conflate the true underlying physical phenomena with systematic distortions introduced by measurement instruments. This entanglement limits model generalization, especially in heterogeneous or multi-instrument settings. We present a causally-motivated foundation model that explicitly disentangles physical and instrumental factors using a dual-encoder architecture trained with structured contrastive learning. Leveraging naturally occurring observational triplets (i.e., where the same target is measured under varying conditions, and distinct targets are measured under shared conditions) our model learns separate latent representations for the underlying physical signal and instrument effects. Evaluated on simulated astronomical time series designed to resemble the complexity of variable stars observed by missions like NASA's Transiting Exoplanet Survey Satellite (TESS), our method significantly outperforms traditional single-latent space foundation models on downstream prediction tasks, particularly in low-data regimes. These results demonstrate that our model supports key capabilities of foundation models, including few-shot generalization and efficient adaptation, and highlight the importance of encoding causal structure into representation learning for structured data.

cs.LG↗
arXiv2025

Transfer Learning for Transient Classification: From Simulations to Real Data and ZTF to LSST

Machine learning has become essential for automated classification of astronomical transients, but current approaches face significant limitations: classifiers trained on simulations struggle with real data, models developed for one survey cannot be easily applied to another, and new surveys require prohibitively large amounts of labelled training data. These challenges are particularly pressing as we approach the era of the Vera C. Rubin Observatory's Legacy Survey of Space and Time (LSST), where existing classification models will need to be retrained using LSST observations. We demonstrate that transfer learning can overcome these challenges by repurposing existing models trained on either simulations or data from other surveys. Starting with a model trained on simulated Zwicky Transient Facility (ZTF) light curves, we show that transfer learning reduces the amount of labelled real ZTF transients needed by 95% while maintaining equivalent performance to models trained from scratch. Similarly, when adapting ZTF models for LSST simulations, transfer learning achieves 94% of the baseline performance while requiring only 30% of the training data. These findings have significant implications for the early operations of LSST, suggesting that reliable automated classification will be possible soon after the survey begins, rather than waiting months or years to accumulate sufficient training data.

astro-ph.IM↗
arXiv2025

A Disintegrating Rocky Planet with Prominent Comet-like Tails Around a Bright Star

We report the discovery of BD+05$\,$4868$\,$Ab, a transiting exoplanet orbiting a bright ($V=10.16$) K-dwarf (TIC 466376085) with a period of 1.27 days. Observations from NASA's Transiting Exoplanet Survey Satellite (TESS) reveal variable transit depths and asymmetric transit profiles that are characteristic of comet-like tails formed by dusty effluents emanating from a disintegrating planet. Unique to BD+05$\,$4868$\,$Ab is the presence of prominent dust tails in both the trailing and leading directions that contribute to the extinction of starlight from the host star. By fitting the observed transit profile and analytically modeling the drift of dust grains within both dust tails, we infer large grain sizes ($\sim1-10\,\mu$m) and a mass loss rate of $10\,M_{\rm \oplus}\,$Gyr$^{-1}$, suggestive of a lunar-mass object with a disintegration timescale of only several Myr. The host star is probably older than the Sun and is accompanied by an M-dwarf companion at a projected physical separation of 130 AU. The brightness of the host star, combined with the planet's relatively deep transits ($0.8-2.0\%$), presents BD+05$\,$4868$\,$Ab as a prime target for compositional studies of rocky exoplanets and investigations into the nature of catastrophically evaporating planets.

astro-ph.EP↗
arXiv2024

A Classifier-Based Approach to Multi-Class Anomaly Detection Applied to Astronomical Time-Series

Automating anomaly detection is an open problem in many scientific fields, particularly in time-domain astronomy, where modern telescopes generate millions of alerts per night. Currently, most anomaly detection algorithms for astronomical time-series rely either on hand-crafted features or on features generated through unsupervised representation learning, coupled with standard anomaly detection algorithms. In this work, we introduce a novel approach that leverages the latent space of a neural network classifier for anomaly detection. We then propose a new method called Multi-Class Isolation Forests (MCIF), which trains separate isolation forests for each class to derive an anomaly score for an object based on its latent space representation. This approach significantly outperforms a standard isolation forest when distinct clusters exist in the latent space. Using a simulated dataset emulating the Zwicky Transient Facility (54 anomalies and 12,040 common), our anomaly detection pipeline discovered $46\pm3$ anomalies ($\sim 85\%$ recall) after following up the top 2,000 ($\sim 15\%$) ranked objects. Furthermore, our classifier-based approach outperforms or approaches the performance of other state-of-the-art anomaly detection pipelines. Our novel method demonstrates that existing and new classifiers can be effectively repurposed for real-time anomaly detection. The code used in this work, including a Python package, is publicly available, https://github.com/Rithwik-G/AstroMCAD.

cs.LG↗
arXiv2024

A Classifier-Based Approach to Multi-Class Anomaly Detection for Astronomical Transients

Automating real-time anomaly detection is essential for identifying rare transients, with modern survey telescopes generating tens of thousands of alerts per night, and future telescopes, such as the Vera C. Rubin Observatory, projected to increase this number dramatically. Currently, most anomaly detection algorithms for astronomical transients rely either on hand-crafted features extracted from light curves or on features generated through unsupervised representation learning, coupled with standard anomaly detection algorithms. In this work, we introduce an alternative approach: using the penultimate layer of a neural network classifier as the latent space for anomaly detection. We then propose a novel method, Multi-Class Isolation Forests (\texttt{MCIF}), which trains separate isolation forests for each class to derive an anomaly score for a light curve from its latent space representation. This approach significantly outperforms a standard isolation forest. We also use a simpler input method for real-time transient classifiers which circumvents the need for interpolation and helps the neural network handle irregular sampling and model inter-passband relationships. Our anomaly detection pipeline identifies rare classes including kilonovae, pair-instability supernovae, and intermediate luminosity transients shortly after trigger on simulated Zwicky Transient Facility light curves. Using a sample of our simulations matching the population of anomalies expected in nature (54 anomalies and 12,040 common transients), our method discovered $41\pm3$ anomalies (~75% recall) after following up the top 2000 (~15%) ranked transients. Our novel method shows that classifiers can be effectively repurposed for real-time anomaly detection.

astro-ph.IM↗
arXiv2023

Predicting the Age of Astronomical Transients from Real-Time Multivariate Time Series

Astronomical transients, such as supernovae and other rare stellar explosions, have been instrumental in some of the most significant discoveries in astronomy. New astronomical sky surveys will soon record unprecedented numbers of transients as sparsely and irregularly sampled multivariate time series. To improve our understanding of the physical mechanisms of transients and their progenitor systems, early-time measurements are necessary. Prioritizing the follow-up of transients based on their age along with their class is crucial for new surveys. To meet this demand, we present the first method of predicting the age of transients in real-time from multi-wavelength time-series observations. We build a Bayesian probabilistic recurrent neural network. Our method can accurately predict the age of a transient with robust uncertainties as soon as it is initially triggered by a survey telescope. This work will be essential for the advancement of our understanding of the numerous young transients being detected by ongoing and upcoming astronomical surveys.

astro-ph.IM↗
arXiv2023

Four years of Type Ia Supernovae Observed by TESS: Early Time Light Curve Shapes and Constraints on Companion Interaction Models

We present 307 Type Ia supernova (SN) light curves from the first four years of the TESS mission. We use this sample to characterize the shapes of the early time light curves, measure the rise times from first light to peak, and search for companion star interactions. Using simulations, we show that light curves must have noise $<$10% of the peak to avoid biases in the early time light curve shape, restricting our quantitative analysis to 74 light curves. We find that the mean power law index $t^{\beta_1}$ of the early time light curves is 1.93$\pm$ 0.57 and the mean rise time to peak is 15.7 $\pm$ 3.5 days. We also estimate the underlying population distribution and find a Gaussian component with mean $\beta_1 = 2.29$, width 0.34, and a tail extending to values less than 1.0. We use model comparison techniques to test for the presence of companion interactions. In contrast to recent results in the literature, we find that the data can rarely distinguish between models with and without companion interactions, and caution is needed when claiming detections of early time flux excesses. Nevertheless, we find three high-quality SN light curves that tentatively prefer the addition of a companion interaction model, but the statistical evidence is not robust. We also find two SNe that disfavor the addition of a companion interaction model to a curved power law model. Taking the 74 SNe together, we calculate 3$\sigma$ upper limits on the presence of companion signatures to control for orientation effects that can hide companions in individual light curves. Our results rule out common progenitor systems with companions having Roche lobe radii $>$ 31 R$_{\odot}$ (99.9% confidence level) and disfavor companions having Roche lobe radii $>$ 10 R$_{\odot}$ (95% confidence level). Lastly, we discuss the implications of our results for the intrinsic fraction of single degenerate progenitor systems.

astro-ph.HE↗
arXiv2023

Applications of Deep Learning to physics workflows

Modern large-scale physics experiments create datasets with sizes and streaming rates that can exceed those from industry leaders such as Google Cloud and Netflix. Fully processing these datasets requires both sufficient compute power and efficient workflows. Recent advances in Machine Learning (ML) and Artificial Intelligence (AI) can either improve or replace existing domain-specific algorithms to increase workflow efficiency. Not only can these algorithms improve the physics performance of current algorithms, but they can often be executed more quickly, especially when run on coprocessors such as GPUs or FPGAs. In the winter of 2023, MIT hosted the Accelerating Physics with ML at MIT workshop, which brought together researchers from gravitational-wave physics, multi-messenger astrophysics, and particle physics to discuss and share current efforts to integrate ML tools into their workflows. The following white paper highlights examples of algorithms and computing frameworks discussed during this workshop and summarizes the expected computing needs for the immediate future of the involved fields.

hep-ex↗
arXiv2023

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

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).

astro-ph.EP↗
arXiv2021

Real-time Detection of Anomalies in Multivariate Time Series of Astronomical Data

Astronomical transients are stellar objects that become temporarily brighter on various timescales and have led to some of the most significant discoveries in cosmology and astronomy. Some of these transients are the explosive deaths of stars known as supernovae while others are rare, exotic, or entirely new kinds of exciting stellar explosions. New astronomical sky surveys are observing unprecedented numbers of multi-wavelength transients, making standard approaches of visually identifying new and interesting transients infeasible. To meet this demand, we present two novel methods that aim to quickly and automatically detect anomalous transient light curves in real-time. Both methods are based on the simple idea that if the light curves from a known population of transients can be accurately modelled, any deviations from model predictions are likely anomalies. The first approach is a probabilistic neural network built using Temporal Convolutional Networks (TCNs) and the second is an interpretable Bayesian parametric model of a transient. We show that the flexibility of neural networks, the attribute that makes them such a powerful tool for many regression tasks, is what makes them less suitable for anomaly detection when compared with our parametric model.

cs.LG↗
arXiv2021

Real-Time Detection of Anomalies in Large-Scale Transient Surveys

New time-domain surveys, such as the Vera C. Rubin Observatory Legacy Survey of Space and Time (LSST), will observe millions of transient alerts each night, making standard approaches of visually identifying new and interesting transients infeasible. We present two novel methods of automatically detecting anomalous transient light curves in real-time. Both methods are based on the simple idea that if the light curves from a known population of transients can be accurately modelled, any deviations from model predictions are likely anomalies. The first modelling approach is a probabilistic neural network built using Temporal Convolutional Networks (TCNs) and the second is an interpretable Bayesian parametric model of a transient. We demonstrate our methods' ability to provide anomaly scores as a function of time on light curves from the Zwicky Transient Facility. We show that the flexibility of neural networks, the attribute that makes them such a powerful tool for many regression tasks, is what makes them less suitable for anomaly detection when compared with our parametric model. The parametric model is able to identify anomalies with respect to common supernova classes with high precision and recall scores, achieving area under the precision-recall curves (AUCPR) above 0.79 for most rare classes such as kilonovae, tidal disruption events, intermediate luminosity transients, and pair-instability supernovae. Our ability to identify anomalies improves over the lifetime of the light curves. Our framework, used in conjunction with transient classifiers, will enable fast and prioritised followup of unusual transients from new large-scale surveys.

astro-ph.IM↗
arXiv2021

El-CID: A filter for Gravitational-wave Electromagnetic Counterpart Identification

As gravitational-wave (GW) interferometers become more sensitive and probe ever more distant reaches, the number of detected binary neutron star mergers will increase. However, detecting more events farther away with GWs does not guarantee corresponding increase in the number of electromagnetic counterparts of these events. Current and upcoming wide-field surveys that participate in GW follow-up operations will have to contend with distinguishing the kilonova from the ever increasing number of transients they detect, many of which will be consistent with the GW sky-localization. We have developed a novel tool based on a temporal convolutional neural network architecture, trained on sparse early-time photometry and contextual information for Electromagnetic Counterpart Identification (El-CID). The overarching goal for El-CID is to slice through list of new transient candidates that are consistent with the GW sky localization, and determine which sources are consistent with kilonovae, allowing limited target-of-opportunity resources to be used judiciously. In addition to verifying the performance of our algorithm on an extensive testing sample, we validate it on AT2017gfo - the only EM counterpart of a binary neutron star merger discovered to date - and AT2019npv - a supernova that was initially suspected as a counterpart of the gravitational-wave event, GW190814, but was later ruled out after further analysis.

astro-ph.HE↗