Explainable AI in Deep Learning-Based Prediction of Solar Storms

2025-08-22

AI Summary

To address the limited interpretability of deep learning models in forecasting coupled solar storm events (solar flares and coronal mass ejections, CMEs), this paper proposes the first interpretable solar storm prediction framework tailored for LSTM architectures. Methodologically, we design an attention-augmented LSTM model to process multi-source time-series data from solar active regions and, for the first time in solar physics, integrate model-agnostic post-hoc explanation techniques—particularly SHAP—to enable attribution analysis and visualization of critical time steps and physically meaningful features. Our contributions are threefold: (1) systematic integration of interpretability into solar physics forecasting; (2) identification of key pre-CME magnetohydrodynamic evolution patterns and dominant predictive features—such as longitudinal magnetic field gradients and duration of shear motion—while maintaining high predictive accuracy; and (3) provision of trustworthy, traceable decision-support evidence for space weather forecasting.

Technology Category

• Machine Learning: Transparent, Interpretable, Explainable ML
• Natural Language Processing: Interpretability, Analysis, and Evaluation of NLP Models
• Computer Vision: Interpretability, Explainability, and Transparency

Application Category

• Web Mining and Content Analysis: Large pretrained models with web data
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• Search and Retrieval-Augmented AI: Web query analysis, representation and understanding

Abstract

A deep learning model is often considered a black-box model, as its internal workings tend to be opaque to the user. Because of the lack of transparency, it is challenging to understand the reasoning behind the model's predictions. Here, we present an approach to making a deep learning-based solar storm prediction model interpretable, where solar storms include solar flares and coronal mass ejections (CMEs). This deep learning model, built based on a long short-term memory (LSTM) network with an attention mechanism, aims to predict whether an active region (AR) on the Sun's surface that produces a flare within 24 hours will also produce a CME associated with the flare. The crux of our approach is to model data samples in an AR as time series and use the LSTM network to capture the temporal dynamics of the data samples. To make the model's predictions accountable and reliable, we leverage post hoc model-agnostic techniques, which help elucidate the factors contributing to the predicted output for an input sequence and provide insights into the model's behavior across multiple sequences within an AR. To our knowledge, this is the first time that interpretability has been added to an LSTM-based solar storm prediction model.

Problem

• Making deep learning solar storm prediction interpretable
• Explaining LSTM model predictions for solar flares and CMEs
• Applying post hoc techniques to understand black-box model behavior

Innovation

• LSTM network with attention mechanism
• Post hoc model-agnostic interpretability techniques
• Time series modeling of active region data