Deep Learning-Based Prediction of CME-Driven Shock Standoff Distances in Metric Type II Radio Emissions

Résumé

Abstract Type II radio emissions are events followed by coronal mass ejections (CMEs) and accelerated by the CME-driven shock in the heliosphere. This study reports on an estimate of CME-shock standoff distance at the commencement of metric type II radio emissions by combining the CME- deprojected speed and spectra features of the radio bursts using a robust TensorFlow Deep- Learning Sequential (TFDLS) technique. The data set of CMEs at the commencement of type II radio burst was used between Solar cycle 24 and the ascending phase of Solar Cycle 25. The measured root mean squared error (RMSE) was 0.145 (Rs), with an average height difference of 0.096 Rs between the observed and predicted CME-shock height. Five (5) CMEs/radio bursts energetic events associated with solar flare were selected from the test data and forecasted the CME shock stand-off heights using the TFDLS and the flare-onset (FL) method. The data were used to compare the Leading-edge (LE) and Dynamic Spectra (DS) methods. The RMSE measured between the FL and LE was 0.35 Rs, and the RMSE estimated between the TFDLS and LE approach was 0.04 Rs. The RMSE between the FL and DS was 0.34 Rs, and the RMSE between the TFDLS and the DS was 0.04 Rs. We also used the findings gained from the five selected events and compared them to the 3D shock-fitting (3D-SF) approach. The RMSE found between the TFDLS and the 3D-SF was 0.18 Rs, while the RMSE estimated between the FL and the 3D-SF was 0.23 Rs. This shows that the TFDLS has solid performance.

Citer ce document

Accès au document

Texte intégral en lecture en ligne, réservé aux abonnés SPHAERO et aux membres de l'institution. Se connecter

Auteur(s)

Statistiques

Consultations : 1

Téléchargements : 0