A CNN-based fusion model trained on multi-instrument solar observations predicts geoeffective CMEs, achieving mean TSS of 0.703 and Brier score of 0.095 via five-fold cross-validation.
Title resolution pending
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
fields
astro-ph.SR 3years
2026 3verdicts
UNVERDICTED 3representative citing papers
Deep learning on magnetic field features predicts solar flares, with SHAP values and PDPs added to reveal feature importance and trends.
3D MHD modeling of candle-flame solar flares reveals Y-points do not coincide with apparent cusp tips and observed downflow speeds underestimate reconnection Alfvén speeds by 2-10x.
citing papers explorer
-
Deep Learning-Enabled Prediction of Geoeffective CMEs Using SOHO and SDO Observations
A CNN-based fusion model trained on multi-instrument solar observations predicts geoeffective CMEs, achieving mean TSS of 0.703 and Brier score of 0.095 via five-fold cross-validation.
-
Prediction of Solar Flares Using Photospheric Magnetic Field Parameters with Deep Learning
Deep learning on magnetic field features predicts solar flares, with SHAP values and PDPs added to reveal feature importance and trends.
-
On the Nature of Candle-Flame-Shaped Solar Flares and Sub-Alfv\'enic Supra-Arcade Plasma Downflows
3D MHD modeling of candle-flame solar flares reveals Y-points do not coincide with apparent cusp tips and observed downflow speeds underestimate reconnection Alfvén speeds by 2-10x.