Daniel Muthukrishna

Evan Tey, Dan Moldovan, Michelle Kunimoto et al.

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 (Kovács 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).

Rithwik Gupta, Daniel Muthukrishna, Michelle Lochner

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.

Hali Huang, Daniel Muthukrishna, Prajna Nair et al.

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.

Pablo Mercader-Perez, Carolina Cuesta-Lazaro, Daniel Muthukrishna et al.

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.

Daniel Muthukrishna, Gautham Narayan, Kaisey S. Mandel et al.

We present RAPID (Real-time Automated Photometric IDentification), a novel time-series classification tool capable of automatically identifying transients from within a day of the initial alert, to the full lifetime of a light curve. Using a deep recurrent neural network with Gated Recurrent Units (GRUs), we present the first method specifically designed to provide early classifications of astronomical time-series data, typing 12 different transient classes. Our classifier can process light curves with any phase coverage, and it does not rely on deriving computationally expensive features from the data, making RAPID well-suited for processing the millions of alerts that ongoing and upcoming wide-field surveys such as the Zwicky Transient Facility (ZTF), and the Large Synoptic Survey Telescope (LSST) will produce. The classification accuracy improves over the lifetime of the transient as more photometric data becomes available, and across the 12 transient classes, we obtain an average area under the receiver operating characteristic curve of 0.95 and 0.98 at early and late epochs, respectively. We demonstrate RAPID's ability to effectively provide early classifications of observed transients from the ZTF data stream. We have made RAPID available as an open-source software package (https://astrorapid.readthedocs.io) for machine learning-based alert-brokers to use for the autonomous and quick classification of several thousand light curves within a few seconds.

Rithwik Gupta, Daniel Muthukrishna, Michelle Lochner

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.

Rithwik Gupta, Daniel Muthukrishna, Nabeel Rehemtulla et al.

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.

Jeroen Audenaert, Daniel Muthukrishna, Paul F. Gregory et al.

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.

Rithwik Gupta, Daniel Muthukrishna, Jeroen Audenaert

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.

Daniel Muthukrishna, Kaisey S. Mandel, Michelle Lochner et al.

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.

Daniel Muthukrishna, Kaisey S. Mandel, Michelle Lochner et al.

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.