Active Region-based Flare Forecasting with Sliding Window Multivariate Time Series Forest Classifiers

Over the past few decades, many applications of physics-based simulations and data-driven techniques (including machine learning and deep learning) have emerged to analyze and predict solar flares. These approaches are pivotal in understanding the dynamics of solar flares, primarily aiming to forecast these events and minimize potential risks they may pose to Earth. Although current methods have made significant progress, there are still limitations to these data-driven approaches. One prominent drawback is the lack of consideration for the temporal evolution characteristics in the active regions from which these flares originate. This oversight hinders the ability of these methods to grasp the relationships between high-dimensional active region features, thereby limiting their usability in operations. This study centers on the development of interpretable classifiers for multivariate time series and the demonstration of a novel feature ranking method with sliding window-based sub-interval ranking. The primary contribution of our work is to bridge the gap between complex, less understandable black-box models used for high-dimensional data and the exploration of relevant sub-intervals from multivariate time series, specifically in the context of solar flare forecasting. Our findings demonstrate that our sliding-window time series forest classifier performs effectively in solar flare prediction (with a True Skill Statistic of over 85\%) while also pinpointing the most crucial features and sub-intervals for a given learning task.

Towards Interpretable Solar Flare Prediction with Attention-based Deep Neural Networks

Solar flare prediction is a central problem in space weather forecasting and recent developments in machine learning and deep learning accelerated the adoption of complex models for data-driven solar flare forecasting. In this work, we developed an attention-based deep learning model as an improvement over the standard convolutional neural network (CNN) pipeline to perform full-disk binary flare predictions for the occurrence of $\geq$M1.0-class flares within the next 24 hours. For this task, we collected compressed images created from full-disk line-of-sight (LoS) magnetograms. We used data-augmented oversampling to address the class imbalance issue and used true skill statistic (TSS) and Heidke skill score (HSS) as the evaluation metrics. Furthermore, we interpreted our model by overlaying attention maps on input magnetograms and visualized the important regions focused on by the model that led to the eventual decision. The significant findings of this study are: (i) We successfully implemented an attention-based full-disk flare predictor ready for operational forecasting where the candidate model achieves an average TSS=0.54$\pm$0.03 and HSS=0.37$\pm$0.07. (ii) we demonstrated that our full-disk model can learn conspicuous features corresponding to active regions from full-disk magnetogram images, and (iii) our experimental evaluation suggests that our model can predict near-limb flares with adept skill and the predictions are based on relevant active regions (ARs) or AR characteristics from full-disk magnetograms.

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

This study progresses solar flare prediction research by presenting a full-disk deep-learning model to forecast $\geq$M-class solar flares and evaluating its efficacy on both central (within $\pm$70$^\circ$) and near-limb (beyond $\pm$70$^\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 $\geq$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$0.38, 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.

All-Clear Flare Prediction Using Interval-based Time Series Classifiers

An all-clear flare prediction is a type of solar flare forecasting that puts more emphasis on predicting non-flaring instances (often relatively small flares and flare quiet regions) with high precision while still maintaining valuable predictive results. While many flare prediction studies do not address this problem directly, all-clear predictions can be useful in operational context. However, in all-clear predictions, finding the right balance between avoiding false negatives (misses) and reducing the false positives (false alarms) is often challenging. Our study focuses on training and testing a set of interval-based time series classifiers named Time Series Forest (TSF). These classifiers will be used towards building an all-clear flare prediction system by utilizing multivariate time series data. Throughout this paper, we demonstrate our data collection, predictive model building and evaluation processes, and compare our time series classification models with baselines using our benchmark datasets. Our results show that time series classifiers provide better forecasting results in terms of skill scores, precision and recall metrics, and they can be further improved for more precise all-clear forecasts by tuning model hyperparameters.