Interpretable Deep Learning for Solar Flare Prediction
Document Type
Conference Proceeding
Publication Date
1-1-2024
Abstract
We propose to incorporate three interpretable methods, namely SHAP (SHapley Additive exPlanations), PDP (partial dependence plots) and Anchors, into a deep learning-based model, called SolarFlareNet, for operational flare forecasting. SolarFlareNet takes as input a sample of SHARP (Space-weather HMI Active Region Patches) magnetic parameters and predicts as output whether a solar flare would occur within the next 24 hours. We analyze flare events that occurred from May 2010 to December 2022 using the Geostationary Operational Environmental Satellite's X-ray flare catalogs and construct a database of flares with identified active regions in the catalogs. This database, together with the SHARP magnetic parameters, is used to train and test the SolarFlareNet model. Our experimental results describe the use of the three proposed methods (SHAP, PDP, and Anchors) to interpret the SolarFlareNet model and demonstrate the effectiveness of the methods.
Identifier
85217382166 (Scopus)
ISBN
[9798331527235]
Publication Title
Proceedings - International Conference on Tools with Artificial Intelligence, ICTAI
External Full Text Location
https://doi.org/10.1109/ICTAI62512.2024.00078
ISSN
10823409
First Page
509
Last Page
514
Recommended Citation
Gazula, Vinay Ram; Herbert, Katherine G.; Abduallah, Yasser; and Wang, Jason T.L., "Interpretable Deep Learning for Solar Flare Prediction" (2024). Faculty Publications. 728.
https://digitalcommons.njit.edu/fac_pubs/728