Prediction of Major Solar Flares Using Interpretable Class-dependent Reward Framework with Active Region Magnetograms and Domain Knowledge
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , , , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866911454071881728 |
|---|---|
| author | Wu, Zixian Li, Xuebao Zheng, Yanfang Wang, Rui Zhang, Shunhuang Wei, Jinfang Lv, Yongshang Dong, Liang Abidin, Zamri Zainal Shah, Noraisyah Mohamed Ye, Hongwei Yan, Pengchao Li, Xuefeng Ji, Xiaojia Huang, Xusheng Wang, Xiaotian Jin, Honglei |
| author_facet | Wu, Zixian Li, Xuebao Zheng, Yanfang Wang, Rui Zhang, Shunhuang Wei, Jinfang Lv, Yongshang Dong, Liang Abidin, Zamri Zainal Shah, Noraisyah Mohamed Ye, Hongwei Yan, Pengchao Li, Xuefeng Ji, Xiaojia Huang, Xusheng Wang, Xiaotian Jin, Honglei |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2602_16264 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Prediction of Major Solar Flares Using Interpretable Class-dependent Reward Framework with Active Region Magnetograms and Domain Knowledge Wu, Zixian Li, Xuebao Zheng, Yanfang Wang, Rui Zhang, Shunhuang Wei, Jinfang Lv, Yongshang Dong, Liang Abidin, Zamri Zainal Shah, Noraisyah Mohamed Ye, Hongwei Yan, Pengchao Li, Xuefeng Ji, Xiaojia Huang, Xusheng Wang, Xiaotian Jin, Honglei Machine Learning Solar and Stellar Astrophysics 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. |
| title | Prediction of Major Solar Flares Using Interpretable Class-dependent Reward Framework with Active Region Magnetograms and Domain Knowledge |
| topic | Machine Learning Solar and Stellar Astrophysics |
| url | https://arxiv.org/abs/2602.16264 |