Automatic Burst Detection in Solar Radio Spectrograms Using Deep Learning: deARCE Method

We present in detail an automatic radio-burst detection system, based on the AlexNet con- volutional neural network, for use with any kind of solar spectrogram. A full methodology for model training, performance evaluation, and feedback to the model generator has been developed with special emphasis...

Descripción completa

Detalles Bibliográficos
Autores: Bussons Gordo, Javier|||0000-0002-8275-592X, Fernández Ruiz, Mario, Prieto Mateo, Manuel|||0000-0003-3050-3445, Alvarado Díaz, Jorge, Chávez de la O, Francisco, Hidalgo, Juan Ignacio, Monstein, Christian
Tipo de recurso: artículo
Fecha de publicación:2023
País:España
Institución:Universidad de Alcalá (UAH)
Repositorio:e_Buah Biblioteca Digital Universidad de Alcalá
Idioma:inglés
OAI Identifier:oai:ebuah.uah.es:10017/59269
Acceso en línea:http://hdl.handle.net/10017/59269
https://dx.doi.org/10.1007/s11207-023-02171-0
Access Level:acceso abierto
Descripción
Sumario:We present in detail an automatic radio-burst detection system, based on the AlexNet con- volutional neural network, for use with any kind of solar spectrogram. A full methodology for model training, performance evaluation, and feedback to the model generator has been developed with special emphasis on i) robustness tests against stochastic and overfitting ef- fects, ii) specific metrics adapted to the unbalanced nature of the solar-burst scenario, iii) tunable parameters for probability-threshold optimization, and iv) burst-coincidence cross match among e-Callisto stations and with external observatories (NOAA-SWPC). The re- sulting neural network configuration has been designed to accept data from observatories other than e-Callisto, either ground- or spacecraft-based. Typical False Negative and False Positive Scores in single-observatory mode are, respectively, in the 10 ? 16% and 6 ? 8% ranges, which improve further in cross-match mode. This mode includes new services ( deARCE , Xmatch ) allowing the end-user to check at a glance if a solar radio burst has taken place with a high level of confidence.