Prediction of Major Solar Flares Using Interpretable Class-dependent Reward Framework with Active Region Magnetograms and Domain Knowledge

2026-02-18

AI Summary

This study addresses the challenge of improving both the accuracy and interpretability of predictions for solar flares of magnitude ≥M within a 24-hour window. It proposes the first Category-Dependent Reward (CDR) framework, which integrates physics-informed features with deep learning architectures—including CNN, CNN-BiLSTM, and Transformer—using line-of-sight magnetograms and vector magnetic field data for classification. Experimental results demonstrate that the CDR-Transformer model achieves superior performance when leveraging knowledge-driven features, significantly outperforming current operational systems from NASA/CCMC and exhibiting robustness to variations in reward design. Furthermore, SHAP-based interpretability analysis successfully identifies key physical predictors such as R_VALUE and TOTUSJH, confirming the model’s scientific consistency and enhancing its explanatory power.

Technology Category

• Machine Learning: Feature Construction/Reformulation
• Cognitive Modeling & Cognitive Systems: Neural Spike Coding
• Computer Vision: Interpretability, Explainability, and Transparency

Application Category

• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Web Mining and Content Analysis: Large pretrained models with web data
• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions

Abstract

In this work, we develop, for the first time, a supervised classification framework with class-dependent rewards (CDR) to predict $\geq$MM flares within 24 hr. We construct multiple datasets, covering knowledge-informed features and line-of sight (LOS) magnetograms. We also apply three deep learning models (CNN, CNN-BiLSTM, and Transformer) and three CDR counterparts (CDR-CNN, CDR-CNN-BiLSTM, and CDR-Transformer). First, we analyze the importance of LOS magnetic field parameters with the Transformer, then compare its performance using LOS-only, vector-only, and combined magnetic field parameters. Second, we compare flare prediction performance based on CDR models versus deep learning counterparts. Third, we perform sensitivity analysis on reward engineering for CDR models. Fourth, we use the SHAP method for model interpretability. Finally, we conduct performance comparison between our models and NASA/CCMC. The main findings are: (1)Among LOS feature combinations, R_VALUE and AREA_ACR consistently yield the best results. (2)Transformer achieves better performance with combined LOS and vector magnetic field data than with either alone. (3)Models using knowledge-informed features outperform those using magnetograms. (4)While CNN and CNN-BiLSTM outperform their CDR counterparts on magnetograms, CDR-Transformer is slightly superior to its deep learning counterpart when using knowledge-informed features. Among all models, CDR-Transformer achieves the best performance. (5)The predictive performance of the CDR models is not overly sensitive to the reward choices.(6)Through SHAP analysis, the CDR model tends to regard TOTUSJH as more important, while the Transformer tends to prioritize R_VALUE more.(7)Under identical prediction time and active region (AR) number, the CDR-Transformer shows superior predictive capabilities compared to NASA/CCMC.

Problem

• solar flare prediction
• M-class flares
• active region magnetograms
• space weather forecasting
• flare classification

Innovation

• Class-dependent Reward
• Solar Flare Prediction
• Interpretable Deep Learning
• Magnetogram Fusion
• SHAP Interpretability