FLARE: A Framework for Stellar Flare Forecasting Using Stellar Physical Properties and Historical Records

Zhu, Bingke; Wang, Xiaoxiao; Jia, Minghui; Tao, Yihan; Kong, Xiao; Luo, Ali; Chen, Yingying; Tang, Ming; Wang, Jinqiao

doi:10.24963/ijcai.2025/1056

FLARE: A Framework for Stellar Flare Forecasting Using Stellar Physical Properties and Historical Records

Bingke Zhu, Xiaoxiao Wang, Minghui Jia, Yihan Tao, Xiao Kong, Ali Luo, Yingying Chen, Ming Tang, Jinqiao Wang

Download BibTeX Cite

Proceedings of the Thirty-Fourth International Joint Conference on Artificial Intelligence. AI4Tech: AI Enabling Technologies. Pages 9501-9509.

https://doi.org/10.24963/ijcai.2025/1056

Keywords

Advanced AI4Tech: Data-driven AI4Tech
Domain-specific AI4Tech: Other AI4Tech applications

Abstract

Stellar flare events are critical observational samples for astronomical research; however, recorded flare events remain limited. Stellar flare forecasting can provide additional flare event samples to support research efforts. Despite this potential, no specialized models for stellar flare forecasting have been proposed to date. In this paper, we present extensive experimental evidence demonstrating that both stellar physical properties and historical flare records are valuable inputs for flare forecasting tasks. We then introduce FLARE (Forecasting Light-curve-based Astronomical Records via features Ensemble), the first-of-its-kind large model specifically designed for stellar flare forecasting. FLARE integrates stellar physical properties and historical flare records through a novel Soft Prompt Module and Residual Record Fusion Module. Experiments on the Kepler light curve dataset demonstrate that FLARE achieves superior performance compared to other methods across all evaluation metrics. Finally, we validate the forecast capability of our model through a comprehensive case study.

Bingke Zhu, Xiaoxiao Wang, Minghui Jia, Yihan Tao, Xiao Kong, Ali Luo, Yingying Chen, Ming Tang, and Jinqiao Wang. 2025. FLARE: A Framework for Stellar Flare Forecasting Using Stellar Physical Properties and Historical Records. In Proceedings of the Thirty-Fourth International Joint Conference on Artificial Intelligence, IJCAI-25. IJCAI, 9501–9509. https://doi.org/10.24963/ijcai.2025/1056

@inproceedings{ijcai2025p1056,
  title     = {FLARE: A Framework for Stellar Flare Forecasting Using Stellar Physical Properties and Historical Records},
  author    = {Zhu, Bingke and Wang, Xiaoxiao and Jia, Minghui and Tao, Yihan and Kong, Xiao and Luo, Ali and Chen, Yingying and Tang, Ming and Wang, Jinqiao},
  booktitle = {Proceedings of the Thirty-Fourth International Joint Conference on
               Artificial Intelligence, {IJCAI-25}},
  publisher = {International Joint Conferences on Artificial Intelligence Organization},
  editor    = {James Kwok},
  pages     = {9501--9509},
  year      = {2025},
  month     = {8},
  note      = {AI4Tech: AI Enabling Technologies},
  doi       = {10.24963/ijcai.2025/1056},
  url       = {https://doi.org/10.24963/ijcai.2025/1056},
}

TY  - CPAPER
TI  - FLARE: A Framework for Stellar Flare Forecasting Using Stellar Physical Properties and Historical Records
AU  - Zhu, Bingke
AU  - Wang, Xiaoxiao
AU  - Jia, Minghui
AU  - Tao, Yihan
AU  - Kong, Xiao
AU  - Luo, Ali
AU  - Chen, Yingying
AU  - Tang, Ming
AU  - Wang, Jinqiao
T2  - Proceedings of the Thirty-Fourth International Joint Conference on Artificial Intelligence, IJCAI-25
PB  - International Joint Conferences on Artificial Intelligence Organization
PY  - 2025
SP  - 9501
EP  - 9509
DO  - 10.24963/ijcai.2025/1056
UR  - https://doi.org/10.24963/ijcai.2025/1056
ER  -