Saved in:
Bibliographic Details
Main Authors: Li, Weijian, Chen, Hong-Yu, Rehemtulla, Nabeel, Shah, Ved G., Wu, Dennis, Kim, Dongho, Lin, Qinjie, Miller, Adam A., Liu, Han
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2510.06200
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866908838652805120
author Li, Weijian
Chen, Hong-Yu
Rehemtulla, Nabeel
Shah, Ved G.
Wu, Dennis
Kim, Dongho
Lin, Qinjie
Miller, Adam A.
Liu, Han
author_facet Li, Weijian
Chen, Hong-Yu
Rehemtulla, Nabeel
Shah, Ved G.
Wu, Dennis
Kim, Dongho
Lin, Qinjie
Miller, Adam A.
Liu, Han
contents Time series foundation models (TSFMs) are increasingly being adopted as highly-capable general-purpose time series representation learners. Although their training corpora are vast, they exclude astronomical time series data. Observations of stars produce peta-scale time series with unique challenges including irregular sampling and heteroskedasticity. We introduce StarEmbed, the first public benchmark for rigorous and standardized evaluation of state-of-the-art TSFMs on stellar time series observations (``light curves''). We benchmark on three scientifically-motivated downstream tasks: unsupervised clustering, supervised classification, and out-of-distribution source detection. StarEmbed integrates a catalog of expert-vetted labels with multi-variate light curves from the Zwicky Transient Facility, yielding ~40k hand-labeled light curves spread across seven astrophysical classes. We evaluate the zero-shot representation capabilities of three TSFMs (MOIRAI, Chronos, Chronos-Bolt) and a domain-specific transformer (Astromer) against handcrafted feature extraction, the long-standing baseline in the astrophysics literature. Our results demonstrate that these TSFMs, especially the Chronos models, which are trained on data completely unlike the astronomical observations, can outperform established astrophysics-specific baselines in some tasks and effectively generalize to entirely new data. In particular, TSFMs deliver state-of-the-art performance on our out-of-distribution source detection benchmark. With the first benchmark of TSFMs on astronomical time series data, we test the limits of their generalization and motivate a paradigm shift in time-domain astronomy from using task-specific, fully supervised pipelines toward adopting generic foundation model representations for the analysis of peta-scale datasets from forthcoming observatories.
format Preprint
id arxiv_https___arxiv_org_abs_2510_06200
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle StarEmbed: Benchmarking Time Series Foundation Models on Astronomical Observations of Variable Stars
Li, Weijian
Chen, Hong-Yu
Rehemtulla, Nabeel
Shah, Ved G.
Wu, Dennis
Kim, Dongho
Lin, Qinjie
Miller, Adam A.
Liu, Han
Solar and Stellar Astrophysics
Instrumentation and Methods for Astrophysics
Artificial Intelligence
Time series foundation models (TSFMs) are increasingly being adopted as highly-capable general-purpose time series representation learners. Although their training corpora are vast, they exclude astronomical time series data. Observations of stars produce peta-scale time series with unique challenges including irregular sampling and heteroskedasticity. We introduce StarEmbed, the first public benchmark for rigorous and standardized evaluation of state-of-the-art TSFMs on stellar time series observations (``light curves''). We benchmark on three scientifically-motivated downstream tasks: unsupervised clustering, supervised classification, and out-of-distribution source detection. StarEmbed integrates a catalog of expert-vetted labels with multi-variate light curves from the Zwicky Transient Facility, yielding ~40k hand-labeled light curves spread across seven astrophysical classes. We evaluate the zero-shot representation capabilities of three TSFMs (MOIRAI, Chronos, Chronos-Bolt) and a domain-specific transformer (Astromer) against handcrafted feature extraction, the long-standing baseline in the astrophysics literature. Our results demonstrate that these TSFMs, especially the Chronos models, which are trained on data completely unlike the astronomical observations, can outperform established astrophysics-specific baselines in some tasks and effectively generalize to entirely new data. In particular, TSFMs deliver state-of-the-art performance on our out-of-distribution source detection benchmark. With the first benchmark of TSFMs on astronomical time series data, we test the limits of their generalization and motivate a paradigm shift in time-domain astronomy from using task-specific, fully supervised pipelines toward adopting generic foundation model representations for the analysis of peta-scale datasets from forthcoming observatories.
title StarEmbed: Benchmarking Time Series Foundation Models on Astronomical Observations of Variable Stars
topic Solar and Stellar Astrophysics
Instrumentation and Methods for Astrophysics
Artificial Intelligence
url https://arxiv.org/abs/2510.06200