Predicting the arrival time of CME associated with type-II radio burst using neural networks technique

Abstract

Type-II radio bursts have been extensively studied as it is considered as a means of inspecting the coronal shock speeds effectively. In this paper, we study the type-II radio burst that occurred on 2 May 2013 through combined observations from the Solar and Heliospheric Observatory (SOHO) and the Solar Terrestrial Relations Observatory (STEREO), in parallel with the ground-based observation from the DARO-CALLISTO station in Germany. We calculate the shock parameters by employing the clear band-splitting of the type-II burst. By using the Newkirk electron density model, we trace the height at which the emission has been produced. Then we trace the shock speed, the Alfven speed, and the coronal magnetic field strength at heights ranging from 1.96–1.99 Rs. We trace the evolution of the accompanied partial-halo Coronal Mass Ejection (CME) event in the inner corona through combined observations from STEREO-A and SOHO. Finally, we establish a prediction model based on artificial Neural Networks (NN) to estimate the arrival time of the CME (May 4th, 20:18), which is close to the actual arrival time (May 5th, ∼ 08:00).