Solar Radio Bursts Pattern Recognition by Supervised Machine Learning.

Type III bursts are intense, non-thermal sporadic solar radio emissions and can becharacterized by their rapid development in time and frequency in the dynamic spectrum.Produced by accelerated electron beams which propagate along open magnetic field linesduring the impulsive phase of a flare via the plasma emission mechanism and generated at thelocal electron plasma frequency fp ≃ 9√ne kHz (ne as the plasma density: number ofelectrons per volume cm−3) and/or its harmonic 2fp, their frequency ranges from ∼ 1 GHzto ∼ 20 kHz thus making them observable also by ground-based radio telescopes. Beside afast drift from high to low frequencies, bursts duration increases simultaneously as the driftrate decreases at lower frequencies. These strong relations between features and type IIIbursts are very distinct to other bursts that are accompanying the periods of solaractivities and represent an excellent candidate for pattern recognition by supervisedmachine learning. Convolutional Neural Networks (CNNs) enjoy a great success inlarge scale image and video recognition and will in the present work be used toscan as a sliding window along the time axis over a dynamic spectrum. The dataare provided by accompanied large ground based low frequency radio astronomyfacilities like UTR-2, URAN-2 or GURT as well as from space-borne observationslike STEREO/WAVES and will be stacked along the frequency axis, covering anoverall frequency range from 0.1 MHz up to 80 MHz, to extract type III features. [ABSTRACT FROM AUTHOR]