Operational Solar Flare Forecasting System Using an Explainable Large Language Model
Authors:
- Xuebao LiXLXuebao Li
- Yongshang LvYLYongshang Lv
- Jinfang WeiJWJinfang Wei
- Yanfang ZhengYZYanfang Zheng
- Ting LiTLTing Li
- Rui WangRWRui Wang
- Zixian WuZWZixian Wu
- Hongwei YeHYHongwei Ye
- Pengchao YanPYPengchao Yan
- Zamri Zainal AbidinZAZamri Zainal Abidin
- Noraisyah Mohamed ShahNSNoraisyah Mohamed Shah
- Changtian XiangCXChangtian Xiang
Preprint
Abstract
This study focuses on forecasting major (>=M-class) solar flares that can severely impact the near-Earth environment. We construct two types of datasets using the Space Weather HMI Active Region Patches (SHARP), and develop a flare prediction network based on large language model (LLMFlareNet). We apply SHapley Additive exPlanations (SHAP) to explain the model predictions. We develop an operational forecasting system based on the LLMFlareNet model. We adopt a daily mode for performance comparison across various operational forecasting systems under identical active region (AR) number and prediction date, using daily operational observational data. The main results are as follows. (1) Through ablation experiments and comparison with baseline models, LLMFlareNet achieves the best TSS scores of 0.720 +/- 0.040 on the ten cross-validation (CV) dataset with mixed ARs. (2) By both global and local SHAP analyses, we identify that R_VALUE is the most influential physical feature for the prediction of LLMFlareNet, aligning with flare magnetic reconnection theory. (3) In daily mode, LLMFlareNet achieves TSS scores of 0.680/0.571 (0.689/0.661, respectively) on the dataset with single/mixed ARs, markedly outperforming NASA/CCMC (SolarFlareNet, respectively). This work introduces the first application of a large language model as a universal computation engine with explainability method in this domain, and presents the first comparison between operational flare forecasting systems in daily mode. The proposed LLMFlareNet-based system demonstrates substantial improvements over existing systems.Keywords
All Related Versions
This publication has 37 references indexed in Scilit:
- Transformer Model for Multivariate Time Series Classification: A Case Study of Solar Flare Prediction2024
- A real-time solar flare forecasting system with deep learning methodsAstrophysics and Space Science, 2024
- The influence of magnetic field parameters and time step on deep learning models of solar flare predictionAstrophysics and Space Science, 2024
- Comparative analysis of machine learning models for solar flare predictionAstrophysics and Space Science, 2023
- Flare Transformer: Solar Flare Prediction Using Magnetograms and Sunspot Physical Features2023
- A review on the long short-term memory modelArtificial Intelligence Review, 2020
- The Helioseismic and Magnetic Imager (HMI) Vector Magnetic Field Pipeline: SHARPs – Space-Weather HMI Active Region PatchesSolar Physics, 2014
- Design and Ground Calibration of the Helioseismic and Magnetic Imager (HMI) Instrument on the Solar Dynamics Observatory (SDO)Solar Physics, 2011
- The Solar Dynamics Observatory (SDO)2011
- The magnetic nature of solar flaresThe Astronomy and Astrophysics Review, 2001