Accurate and reliable predictions of solar flares are essential due to their potentially significant impact on Earth and space-based infrastructure. Although deep learning models have shown notable predictive capabilities in this domain, current evaluations often focus on accuracy while neglecting interpretability and reliability—factors that are especially critical in operational settings. To address this gap, we propose a novel proximity-based framework for analyzing post hoc explanations to assess the interpretability of deep learning models for solar flare prediction. Our study compares two models trained on full-disk line-of-sight (LoS) magnetogram images to predict ≥M-class solar flares within a 24-hour window. We employ the Guided Gradient-weighted Class Activation Mapping (Guided Grad-CAM) method to generate attribution maps from these models, which we then analyze to gain insights into their decision-making processes. To support the evaluation of explanations in operational systems, we introduce a proximity-based metric that quantitatively assesses the accuracy and relevance of local explanations when regions of interest are known. Our findings indicate that the models’ predictions align with active region characteristics to varying degrees, offering valuable insights into their behavior. This framework enhances the evaluation of model interpretability in solar flare forecasting and supports the development of more transparent and reliable operational systems.

Several natural phenomena, such as floods, earth-quakes, volcanic eruptions, or extreme space weather events often come with severity indexes. While these indexes, whether linear or logarithmic are vital, data-driven predictive models for these events rather use a fixed threshold. In this paper, we explore encoding this ordinality to enhance the performance of data-driven models, with specific application in solar flare forecasting. The prediction of solar flares is commonly approached as a binary forecasting problem, categorizing events as either Flare (FL) or No-Flare (NF) based on a chosen threshold (e.g., >C-class, > M-class, or >X-class). However, this binary formulation overlooks the inherent ordinality between the sub-classes within each binary class (FL and NF). In this paper, we propose a novel loss function aimed at optimizing the binary flare prediction problem by embedding the intrinsic ordinal flare characteristics into the binary cross-entropy (BCE) loss function. This modification is intended to provide the model with better guidance based on the ordinal characteristics of the data and improve the overall performance of the models. For our experiments, we employ a ResNet34-based model with transfer learning to predict 2:M-class flares by utilizing the shape-based features of magnetograms of active region (AR) patches spanning from -90° to +90°of solar longitude as our input data. We use a composite skill score (CSS) as our evaluation metric, which is calculated as the geometric mean of the True Skill Score (TSS) and the Heidke Skill Score (HSS) to rank and compare our models' performance. The primary contributions of this work are as follows: (i) We introduce a novel approach to encode ordinality into a binary loss function showing an application to solar flare prediction, (ii) We enhance solar flare forecasting by enabling flare predictions for each AR across the entire solar disk, without any longitudinal restrictions, and evaluate and compare performance. (iii) Our candidate model, optimized with the proposed loss function, shows an improvement of (~17%, (~14%, and (~13% for AR patches within ±30°, ±60°, and ±90° of solar longitude, respectively in terms of CSS, when compared with standard BCE. Additionally, we demonstrate the ability to issue flare forecasts for ARs in near-limb regions (regions between ±60° to ±90°) with a CSS=0.34 (TSS=0.50 and HSS=0.23), expanding the scope of AR-based models for solar flare prediction. This advances the reliability of solar flare forecasts, leading to more effective prediction capabilities.

This study progresses solar flare prediction research by presenting a full-disk deep-learning model to forecast $\geq\mathrm{M}$-class solar flares and evaluating its efficacy on both central (within ±70°) and near-limb beyond ±70°) events, showcasing qualitative assessment of post hoc explanations for the model’s predictions, and providing empirical findings fro human-centered quantitative assessments of these explanations. Our model is trained using hourly full-disk line-of-sight magnetogram images to predict $\geq{\mathrm{M}}$-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 $\sim 0.51$ and a Heidke skill score (HSS) of $\sim.38$, exhibiting skill to predict solar flares where for central locations the average recall is $\sim 0.75$ (recall values for X- and M-class are 0.95 and 0.73 respectively) and for the near-limb flares the average recall is $\sim 0.52$ (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.

Prediction of solar flares is a challenging problem in space weather forecasting that has piqued the interest of many researchers in recent years due to improved data availability and the advancements in the field of machine learning and deep learning. In this paper, we present a solution to full-disk flare prediction using compressed magnetogram images, which was performed by training a set of Convolutional Neural Networks to perform operations-ready flare forecasts. W e s elected two prediction modes, which are both binary for predicting the occurrence of ≥M1.0 and ≥C1.0 class flares within the next 24 hours. For this, we use a simple yet powerful pre-trained AlexNet model and we collect compressed images derived from solar magnetograms provided by the Helioseismic and Magnetic Imager (HMI) instrument onboard Solar Dynamics Observatory (SDO). We followed two time-segmented cross-validation strategies: chronological and non-chronological, to effectively understand the predictive skill of our models. We also trained our models using data-augmentation and oversampling to address the existing class-imbalance issue and used true skill statistic (TSS) and Heidke skill score (HSS) as metrics to compare and evaluate. The major results of this study are (1) we successfully implemented an efficient and effective full-disk flare predictor ready for operational forecasting using 8-bit compressed images of solar magnetograms without further preprocessing; (2) Our candidate model achieves an average TSS of 0.47±0.06 for ≥M1.0 mode and 0.63±0.05 for ≥C1.0 mode, and HSS of 0.35±0.05 for ≥M1.0 and 0.62±0.05 for ≥C1.0 mode. Our experimental evaluation also suggests that training a flare prediction model is heavily influenced by the sampling strategies involved due to the imbalanced nature of the datasets and predicting ≥M1.0 class flares is a more challenging task compared to ≥C1.0 ones.