arXiv subjects

Ved G. Shah

Publications and source records attributed to Ved G. Shah.

10 recordsLinked to original sources

arXiv2026

StarEmbed: Benchmarking Time Series Foundation Models on Astronomical Observations of Variable Stars

Current time series foundation model (TSFM) training corpora largely omit data with certain complexities like irregular temporal sampling. Astronomical time series of stellar fluxes (light curves) are available in immense quantities and exhibit irregular sampling, multiple variates, and heteroskedasticity. We introduce StarEmbed, the first public benchmark for light curves comprised of real observations of ~40,000 stars expert-labeled across seven classes and evaluations in clustering, classification, and out-of-distribution (OOD) source detection. We benchmark TSFMs with differing architecture and training strategies as well as domain-specific transformers. Our results demonstrate that the Chronos family, despite being pre-trained on regularly sampled non-astronomical data, yields state-of-the-art (SOTA) performance in light curve clustering and OOD detection. While no TSFM strictly surpasses the classification performance of the long-established domain baseline, they do demonstrate excellent generalization abilities. StarEmbed marks a step toward universal light curve embeddings and improved TSFM performance on challenging data.

astro-ph.SR↗

arXiv2026

Leveraging Multimodality for Real-Time Classification of Transients and Variables found by the Zwicky Transient Facility

Modern time-domain surveys such as the Zwicky Transient Facility (ZTF) generate hundreds of thousands of alerts each night, making real-time decisions for follow-up observations a central challenge in time-domain astronomy. Robust early classification is crucial for making informed decisions, but is hindered by sparse light curves and degeneracies between classes. In this work, we leverage multimodality to substantially improve real-time classification and demonstrate the practicality of our approach by deploying our model on the ZTF alert stream. Building on the Online Ranked Astrophysical CLass Estimator (ORACLE), we introduce the ORACLE-2 models, which combine light curves, metadata, and images for real-time hierarchical classification. Using both real and simulated datasets, we show that incorporating additional modalities consistently improves classification performance. On observations from ZTF's Bright Transient Survey, our best-performing model, ORACLE-2 Omni, achieves a macro F1 score of 0.73 -- an improvement of up to 11% over models using light curves and metadata alone, and up to 40% over light-curve-only models, with the strongest gains realized at early times. To demonstrate applicability to the Legacy Survey of Space and Time, which will increase alert volume by more than an order of magnitude, we train a light curve + metadata variant on the simulated ELAsTiCC dataset. This model achieves a macro F1 score of 0.88, an improvement of up to 13% over the light-curve-only variant, matching the performance of other state-of-the-art models. Finally, we quantify the trade-offs between performance and throughput, identifying regimes where multimodal approaches offer the greatest benefit. These results show that combining multiple modalities improves early-time classification, enabling more effective triage of high-volume alert streams for current and future time-domain surveys.

astro-ph.IM↗

arXiv2026

Pre-training vision models for the classification of alerts from wide-field time-domain surveys

Modern wide-field time-domain surveys facilitate the study of transient, variable and moving phenomena by conducting image differencing and relaying alerts to their communities. Machine learning tools have been used on data from these surveys and their precursors for more than a decade, and convolutional neural networks (CNNs), which make predictions directly from input images, saw particularly broad adoption through the 2010s. Since then, continually rapid advances in computer vision have transformed the standard practices around using such models. It is now commonplace to use standardized architectures pre-trained on large corpora of everyday images (e.g., ImageNet). In contrast, time-domain astronomy studies still typically design custom CNN architectures and train them from scratch. Here, we explore the effects of adopting various pre-training regimens and standardized model architectures on the performance of alert classification. We find that the resulting models match or outperform a custom, specialized CNN like what is typically used for filtering alerts. Moreover, our results show that pre-training on galaxy images from Galaxy Zoo tends to yield better performance than pre-training on ImageNet or training from scratch. We observe that the design of standardized architectures are much better optimized than the custom CNN baseline, requiring significantly less time and memory for inference despite having more trainable parameters. On the eve of the Legacy Survey of Space and Time and other image-differencing surveys, these findings advocate for a paradigm shift in the creation of vision models for alerts, demonstrating that greater performance and efficiency, in time and in data, can be achieved by adopting the latest practices from the computer vision field.

astro-ph.IM↗

arXiv2026

SELDON: Supernova Explosions Learned by Deep ODE Networks

The discovery rate of optical transients will explode to 10 million public alerts per night once the Vera C. Rubin Observatory's Legacy Survey of Space and Time comes online, overwhelming the traditional physics-based inference pipelines. A continuous-time forecasting AI model is of interest because it can deliver millisecond-scale inference for thousands of objects per day, whereas legacy MCMC codes need hours per object. In this paper, we propose SELDON, a new continuous-time variational autoencoder for panels of sparse and irregularly time-sampled (gappy) astrophysical light curves that are nonstationary, heteroscedastic, and inherently dependent. SELDON combines a masked GRU-ODE encoder with a latent neural ODE propagator and an interpretable Gaussian-basis decoder. The encoder learns to summarize panels of imbalanced and correlated data even when only a handful of points are observed. The neural ODE then integrates this hidden state forward in continuous time, extrapolating to future unseen epochs. This extrapolated time series is further encoded by deep sets to a latent distribution that is decoded to a weighted sum of Gaussian basis functions, the parameters of which are physically meaningful. Such parameters (e.g., rise time, decay rate, peak flux) directly drive downstream prioritization of spectroscopic follow-up for astrophysical surveys. Beyond astronomy, the architecture of SELDON offers a generic recipe for interpretable and continuous-time sequence modeling in any time domain where data are multivariate, sparse, heteroscedastic, and irregularly spaced.

astro-ph.IM↗

arXiv2026

Searching for Neutron Star Mergers in the Absence of Gravitational Waves with Optical Afterglow Emission

With the forth observing run of the LIGO-Virgo-KAGRA gravitational-wave network, which enabled the discovery of the kilonova (KN) counterpart to GW170817, ending with no new confirmed neutron star mergers, the intrinsic rate of these events must be even lower than previously estimated. As a result, building a sample of KNe will remain challenging even with continued GW observations, motivating complementary discovery strategies that do not rely on gravitational-wave triggers. In this work, we consider how leveraging bright short gamma-ray burst afterglows can aid in the discovery on KNe with the Rubin Observatory's upcoming Legacy Survey of Space and Time (LSST), whose unprecedented depth will make such detections feasible. We find that nearly on-axis ($θ_{\rm view} \leq 30°$) afterglows can enhance KN detection rates in the LSST $g$-band from $29^{+51}_{-21} \ \rm yr^{-1}$ to $91^{+160}_{-65} \ \rm yr^{-1}$. We further show how the colors of the observed events can be used to distinguish between neutron star merger counterparts with and without KN emission. This study demonstrates how critical multi-wavelength and multi-survey observations are for these rare events, especially without context from gravitational waves. Fortunately, detectable events will likely be discovered near peak with LSST, allowing for rapid follow-up and confirmation. We discuss key uncertainties in our study, particularly volume rate of merger events, and the degeneracy between the empirically determined explosion energy and ambient medium density.

astro-ph.HE↗

arXiv2026

Opportunities in AI/ML for the Rubin LSST Dark Energy Science Collaboration

The Vera C. Rubin Observatory's Legacy Survey of Space and Time (LSST) will produce unprecedented volumes of heterogeneous astronomical data (images, catalogs, and alerts) that challenge traditional analysis pipelines. The LSST Dark Energy Science Collaboration (DESC) aims to derive robust constraints on dark energy and dark matter from these data, requiring methods that are statistically powerful, scalable, and operationally reliable. Artificial intelligence and machine learning (AI/ML) are already embedded across DESC science workflows, from photometric redshifts and transient classification to weak lensing inference and cosmological simulations. Yet their utility for precision cosmology hinges on trustworthy uncertainty quantification, robustness to covariate shift and model misspecification, and reproducible integration within scientific pipelines. This white paper surveys the current landscape of AI/ML across DESC's primary cosmological probes and cross-cutting analyses, revealing that the same core methodologies and fundamental challenges recur across disparate science cases. Since progress on these cross-cutting challenges would benefit multiple probes simultaneously, we identify key methodological research priorities, including Bayesian inference at scale, physics-informed methods, validation frameworks, and active learning for discovery. With an eye on emerging techniques, we also explore the potential of the latest foundation model methodologies and LLM-driven agentic AI systems to reshape DESC workflows, provided their deployment is coupled with rigorous evaluation and governance. Finally, we discuss critical software, computing, data infrastructure, and human capital requirements for the successful deployment of these new methodologies, and consider associated risks and opportunities for broader coordination with external actors.

astro-ph.IM↗

arXiv2025

ORACLE: A Real-Time, Hierarchical, Deep-Learning Photometric Classifier for the LSST

We present ORACLE, the first hierarchical deep-learning model for real-time, context-aware classification of transient and variable astrophysical phenomena. ORACLE is a recurrent neural network with Gated Recurrent Units (GRUs), and has been trained using a custom hierarchical cross-entropy loss function to provide high-confidence classifications along an observationally-driven taxonomy with as little as a single photometric observation. Contextual information for each object, including host galaxy photometric redshift, offset, ellipticity and brightness, is concatenated to the light curve embedding and used to make a final prediction. Training on $\sim$0.5M events from the Extended LSST Astronomical Time-Series Classification Challenge, we achieve a top-level (Transient vs Variable) macro-averaged precision of 0.96 using only 1 day of photometric observations after the first detection in addition to contextual information, for each event; this increases to $>$0.99 once 64 days of the light curve has been obtained, and 0.83 at 1024 days after first detection for 19-way classification (including supernova sub-types, active galactic nuclei, variable stars, microlensing events, and kilonovae). We also compare ORACLE with other state-of-the-art classifiers and report comparable performance for the 19-way classification task, in addition to delivering accurate top-level classifications much earlier. The code and model weights used in this work are publicly available at our associated GitHub repository (https://github.com/uiucsn/ELAsTiCC-Classification).

astro-ph.IM↗

arXiv2025

The La Silla Schmidt Southern Survey

We present the La Silla Schmidt Southern Survey (LS4), a new wide-field, time-domain survey to be conducted with the 1 m ESO Schmidt telescope. The 268 megapixel LS4 camera mosaics 32 2k$\times$4k fully depleted CCDs, providing a $\sim$20 deg$^2$ field of view with $1''$ pixel$^{-1}$ resolution. The LS4 camera will have excellent performance at longer wavelengths: in a standard 45 s exposure the expected 5$σ$ limiting magnitudes in $g$, $i$, $z$ are $\sim$21.5, $\sim$20.9, and $\sim$20.3 mag (AB), respectively. The telescope design requires a novel filter holder that fixes different bandpasses over each quadrant of the detector. Two quadrants will have $i$ band, while the other two will be $g$ and $z$ band and color information will be obtained by dithering targets across the different quadrants. The majority (90%) of the observing time will be used to conduct a public survey that monitors the extragalactic sky at both moderate (3 d) and high (1 d) cadence, as well as focused observations within the Galactic bulge and plane. Alerts from the public survey will be broadcast to the community via established alert brokers. LS4 will run concurrently with the Vera C. Rubin Observatory's Legacy Survey of Space and Time (LSST). The combination of LS4+LSST will enable detailed holistic monitoring of many nearby transients: high-cadence LS4 observations will resolve the initial rise and peak of the light curve while less-frequent but deeper observations by LSST will characterize the years before and after explosion. Here, we summarize the primary science objectives of LS4 including microlensing events in the Galaxy, extragalactic transients, the search for electromagnetic counterparts to multi-messenger events, and cosmology.

astro-ph.IM↗

arXiv2024

The Fastest Path to Discovering the Second Electromagnetic Counterpart to a Gravitational Wave Event

The discovery of a second electromagnetic counterpart to a gravitational wave event represents a critical goal in the field of multi-messenger astronomy. In order to determine the optimal strategy for achieving this goal, we perform comprehensive simulations comparing two potential paths forward: continuing the current LIGO-Virgo-KAGRA (LVK) observing run, O4, versus temporarily shutting down the detectors for upgrades before beginning the next observing run, O5. Our simulations incorporate current O4 instrument sensitivities and duty cycles, as well as projected configurations for O5, while accounting for variables such as binary neutron star merger rates, system properties, viewing angles, dust extinction, and kilonova (KN) observables. Our results indicate that a KN discovery would occur $125^{+253}_{-125}$~days (middle 50\% interval) sooner in O5 compared to O4, suggesting that extending O4 would lead to faster discovery if the shutdown period between runs is $>$4~months. Moreover, for 88\% of our simulations, continuing O4 results in earlier KN discovery when compared to the expected two-year shutdown between O4 and O5. Given these findings and the critical importance of avoiding a $>$10 year gap between first and second electromagnetic counterpart discoveries, we suggest LVK consider extending O4 operations for as long as feasible prior to shutting down for critical upgrades.

astro-ph.HE↗

arXiv2023

Predictions for Electromagnetic Counterparts to Neutron Star Mergers Discovered during LIGO-Virgo-KAGRA Observing Runs 4 and 5

We present a comprehensive, configurable open-source framework for estimating the rate of electromagnetic detection of kilonovae (KNe) associated with gravitational wave detections of binary neutron star (BNS) mergers. We simulate the current LIGO-Virgo-KAGRA (LVK) observing run (O4) using up-to-date sensitivity and up-time values as well as the next observing run (O5) using predicted sensitivities. We find the number of discoverable kilonovae during LVK O4 to be ${ 1}_{- 1}^{+ 4}$ or ${ 2 }_{- 2 }^{+ 3 }$, (at 90% confidence) depending on the distribution of NS masses in coalescing binaries, with the number increasing by an order of magnitude during O5 to ${ 19 }_{- 11 }^{+ 24 }$. Regardless of mass model, we predict at most five detectable KNe (at 95% confidence) in O4. We also produce optical and near-infrared light curves that correspond to the physical properties of each merging system. We have collated important information for allocating observing resources and directing search and follow-up observations including distributions of peak magnitudes in several broad bands and timescales for which specific facilities can detect each KN. The framework is easily adaptable, and new simulations can quickly be produced as input information such as merger rates and NS mass distributions are refined. Finally, we compare our suite of simulations to the thus-far completed portion of O4 (as of October 14, 2023), finding a median number of discoverable KNe of 0 and a 95-percentile upper limit of 2, consistent with no detection so far in O4.

astro-ph.HE↗