FALCO: Foundation Model of Astronomical Light Curves for Time Domain Astronomy. Implementation and Applications on Kepler Data
Open Access
- 3 December 2025
- journal article
- Published by American Astronomical Society in The Astronomical Journal
- Vol. 171 (1)
Abstract
Time-domain surveys have advanced astronomical research by revealing diverse variable phenomena, from stellar flares to transient events. The scale and complexity of survey data, along with the demand for rapid classification, present significant challenges for analysis. While machine learning offers solutions, most existing models are tailored to single tasks, struggle to generalize, and depend heavily on large, accurately labeled datasets. This paper presents an initial implementation of FALCO, a foundation model trained on Kepler light curves via self-supervised learning using a Transformer-based architecture. The model has been evaluated on Kepler data across three distinct light-curve analysis tasks, and it demonstrates robust performance in all tasks, achieving an accuracy of 95% for stellar variability classification across eight classes, an overall RMSE of 0.1305 dex in surface gravity estimation (with significantly improved precision of RMSE < 0.08 dex at the low-gravity end where log g < 1, and 0.02 dex near log g ≈ 3), and a precision of 87% in flare identification. These results highlight the versatility of the foundation model in extracting generalizable representations from light curves, enabling easy adaptation to diverse tasks and making it a promising tool for time-domain analysis. Further analysis of model scaling and input light-curve sequence length reveals that larger models and longer input sequences improve performance. We have also applied the model to produce a comprehensive catalog of surface gravity (log g ) measurements for 179,732 Kepler stellar targets, using their light curves.Keywords
Funding Information
- MOST ∣ National Key Research and Development Program of China (2022YFF0711500)
- MOST ∣ National Natural Science Foundation of China (12403102)
- MOST ∣ National Natural Science Foundation of China (12373110)
- MOST ∣ National Natural Science Foundation of China (12273077)
- MOST ∣ National Natural Science Foundation of China (12103070)
- Strategic Priority Research Program of the Chinese Academy of Sciences (XDB0550101)
- Key R&D Program of Zhejiang (2024SSYS0006)
- MOST ∣ National Key Research and Development Program of China (2019YFA0405503)
- MOST ∣ National Natural Science Foundation of China (12422303)
- Strategic Priority Research Program of the Chinese Academy of Sciences (XDB0550103)
- MOST ∣ National Natural Science Foundation of China (12573111)
This publication has 68 references indexed in Scilit:
- Light curve classification with DistClassiPy: A new distance-based classifierAstronomy and Computing, 2024
- Discovery of two rotational modulation periods from a young hierarchical triple systemScience China Physics, Mechanics & Astronomy, 2023
- The Einstein Probe Mission2022
- Finding flares in Kepler and TESS data with recurrent deep neural networksAstronomy & Astrophysics, 2021
- Array programming with NumPyNature, 2020
- Flares in open clusters with K2Astronomy & Astrophysics, 2019
- A kilonova as the electromagnetic counterpart to a gravitational-wave sourceNature, 2017
- Astropy: A community Python package for astronomyAstronomy & Astrophysics, 2013
- Data challenges of time domain astronomyDistributed and Parallel Databases, 2012
- Breakthroughs in Statistics1992