Enhancing Explainability in Solar Energetic Particle Event Prediction: A Global Feature Mapping Approach

2025-11-12

AI Summary

Existing solar energetic particle (SEP) event prediction models are predominantly black-box systems, hindering physical interpretation and limiting solar physicists’ understanding and trust in their outputs. To address this, we propose an explainability-enhanced framework that integrates global feature importance analysis with a solar-physics-informed, custom feature mapping strategy, thereby rendering model decision-making transparent and interpretable. The framework tightly couples machine learning interpretability techniques with multi-timescale solar observational data. Evaluated systematically on 341 SEP events, it not only substantially improves predictive explainability but also—through representative case studies—reveals direct correspondences between key model features and underlying physical mechanisms, including magnetic reconnection and shock acceleration. This advances data-driven SEP forecasting toward physically grounded, interpretable modeling.

Technology Category

• Machine Learning: Transparent, Interpretable, Explainable ML
• Reasoning under Uncertainty: Relational Probabilistic Models
• Humans and AI: Explainable AI (XAI) for Human Understanding

Application Category

• User Modeling, Personalization and Recommendation: Explainable and interpretable methods for personalization
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• Web Mining and Content Analysis: Large pretrained models with web data

Abstract

Solar energetic particle (SEP) events, as one of the most prominent manifestations of solar activity, can generate severe hazardous radiation when accelerated by solar flares or shock waves formed aside from coronal mass ejections (CMEs). However, most existing data-driven methods used for SEP predictions are operated as black-box models, making it challenging for solar physicists to interpret the results and understand the underlying physical causes of such events rather than just obtain a prediction. To address this challenge, we propose a novel framework that integrates global explanations and ad-hoc feature mapping to enhance model transparency and provide deeper insights into the decision-making process. We validate our approach using a dataset of 341 SEP events, including 244 significant (>=10 MeV) proton events exceeding the Space Weather Prediction Center S1 threshold, spanning solar cycles 22, 23, and 24. Furthermore, we present an explainability-focused case study of major SEP events, demonstrating how our method improves explainability and facilitates a more physics-informed understanding of SEP event prediction.

Problem

• Enhancing explainability in solar energetic particle event prediction models
• Addressing black-box limitations in SEP prediction through feature mapping
• Providing physics-informed understanding of solar radiation hazard causes

Innovation

• Global explanations integrated with feature mapping
• Enhanced model transparency for decision-making insights
• Explainability-focused framework validated on SEP events