# Exploring Deep Learning for Full-disk Solar Flare Prediction with Empirical Insights from Guided Grad-CAM Explanations

arXiv: https://arxiv.org/abs/2308.15712 · HTML: https://mlsanity.com/paper/2308.15712/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- Builds on 14 of its 56 references that are in the map.
- First posted on arXiv 30 Aug 2023.

## Builds on (most cited first, 14 of 14)

- [Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localization](https://mlsanity.com/paper/1610.02391/) (2016)
- [Axiomatic Attribution for Deep Networks](https://mlsanity.com/paper/1703.01365/) (2017)
- [Visualizing and Understanding Convolutional Networks](https://mlsanity.com/paper/1311.2901/) (2013)
- [Learning Important Features Through Propagating Activation Differences](https://mlsanity.com/paper/1704.02685/) (2017)
- [Striving for Simplicity: The All Convolutional Net](https://mlsanity.com/paper/1412.6806/) (2014)
- [Grad-CAM++: Improved Visual Explanations for Deep Convolutional Networks](https://mlsanity.com/paper/1710.11063/) (2017)
- [Captum: A unified and generic model interpretability library for PyTorch](https://mlsanity.com/paper/2009.07896/) (2020)
- [One weird trick for parallelizing convolutional neural networks](https://mlsanity.com/paper/1404.5997/) (2014)
- [Robust Explainability: A Tutorial on Gradient-Based Attribution Methods for Deep Neural Networks](https://mlsanity.com/paper/2107.11400/) (2021)
- [Towards Coupling Full-disk and Active Region-based Flare Prediction for Operational Space Weather Forecasting](https://mlsanity.com/paper/2209.07406/) (2022)
- [Predicting Solar Flares Using CNN and LSTM on Two Solar Cycles of Active Region Data](https://mlsanity.com/paper/2204.03710/) (2022)
- [All-Clear Flare Prediction Using Interval-based Time Series Classifiers](https://mlsanity.com/paper/2105.01202/) (2021)
- [Explaining Full-disk Deep Learning Model for Solar Flare Prediction using Attribution Methods](https://mlsanity.com/paper/2307.15878/) (2023)
- [Explainable Deep Learning-based Solar Flare Prediction with post hoc Attention for Operational Forecasting](https://mlsanity.com/paper/2308.02682/) (2023)

## Built on by (most cited first, 6 of 6)

- [Towards Interpretable Solar Flare Prediction with Attention-based Deep Neural Networks](https://mlsanity.com/paper/2309.04558/) (2023)
- [Advancing Solar Flare Prediction using Deep Learning with Active Region Patches](https://mlsanity.com/paper/2406.11054/) (2024)
- [Embedding Ordinality to Binary Loss Function for Improving Solar Flare Forecasting](https://mlsanity.com/paper/2408.11768/) (2024)
- [Unveiling the Potential of Deep Learning Models for Solar Flare Prediction in Near-Limb Regions](https://mlsanity.com/paper/2309.14483/) (2023)
- [Large Scale Evaluation of Deep Learning-based Explainable Solar Flare Forecasting Models with Attribution-based Proximity Analysis](https://mlsanity.com/paper/2411.18070/) (2024)
- [Enhancing Explainability in Solar Energetic Particle Event Prediction: A Global Feature Mapping Approach](https://mlsanity.com/paper/2511.09475/) (2025)

## Abstract (arXiv)

This study progresses solar flare prediction research by presenting a full-disk deep-learning model to forecast ≥M-class solar flares and evaluating its efficacy on both central (within ±70^circ) and near-limb (beyond ±70^circ) events, showcasing qualitative assessment of post hoc explanations for the model's predictions, and providing empirical findings from human-centered quantitative assessments of these explanations. Our model is trained using hourly full-disk line-of-sight magnetogram images to predict ≥M-class solar flares within the subsequent 24-hour prediction window. Additionally, we apply the Guided Gradient-weighted Class Activation Mapping (Guided Grad-CAM) attribution method to interpret our model's predictions and evaluate the explanations. Our analysis unveils that full-disk solar flare predictions correspond with active region characteristics. The following points represent the most important findings of our study: (1) Our deep learning models achieved an average true skill statistic (TSS) of ~0.51 and a Heidke skill score (HSS) of ~0.38, exhibiting skill to predict solar flares where for central locations the average recall is ~0.75 (recall values for X- and M-class are 0.95 and 0.73 respectively) and for the near-limb flares the average recall is ~0.52 (recall values for X- and M-class are 0.74 and 0.50 respectively); (2) qualitative examination of the model's explanations reveals that it discerns and leverages features linked to active regions in both central and near-limb locations within full-disk magnetograms to produce respective predictions. In essence, our models grasp the shape and texture-based properties of flaring active regions, even in proximity to limb areas -- a novel and essential capability with considerable significance for operational forecasting systems.