MEMPSEP I : Forecasting the Probability of Solar Energetic Particle Event Occurrence using a Multivariate Ensemble of Convolutional Neural Networks

TL;DR

This paper introduces MEMPSEP I, a probabilistic forecasting model using an ensemble of CNNs to predict solar energetic particle events, improving reliability and providing uncertainty measures for space weather prediction.

Contribution

It presents a novel ensemble CNN-based model for probabilistic SEP occurrence forecasting, addressing class imbalance and offering flexible risk thresholds.

Findings

Achieved 2.5% improvement in forecast reliability

Attained a Brier score of 0.14

Provides uncertainty quantification in predictions

Abstract

The Sun continuously affects the interplanetary environment through a host of interconnected and dynamic physical processes. Solar flares, Coronal Mass Ejections (CMEs), and Solar Energetic Particles (SEPs) are among the key drivers of space weather in the near-Earth environment and beyond. While some CMEs and flares are associated with intense SEPs, some show little to no SEP association. To date, robust long-term (hours-days) forecasting of SEP occurrence and associated properties (e.g., onset, peak intensities) does not effectively exist and the search for such development continues. Through an Operations-2-Research support, we developed a self-contained model that utilizes a comprehensive dataset and provides a probabilistic forecast for SEP event occurrence and its properties. The model is named Multivariate Ensemble of Models for Probabilistic Forecast of Solar Energetic Particles (MEMPSEP). MEMPSEP workhorse is an ensemble of Convolutional Neural Networks that ingests a comprehensive dataset (MEMPSEP III - (Moreland et al., 2023)) of full-disc magnetogram-sequences and in-situ data from different sources to forecast the occurrence (MEMPSEP I - this work) and properties (MEMPSEP II - Dayeh et al. (2023)) of a SEP event. This work focuses on estimating true SEP occurrence probabilities achieving a 2.5% improvement in reliability and a Brier score of 0.14. The outcome provides flexibility for the end-users to determine their own acceptable level of risk, rather than imposing a detection threshold that optimizes an arbitrary binary classification metric. Furthermore, the model-ensemble, trained to utilize the large class-imbalance between events and non-events, provides a clear measure of uncertainty in our forecast