Machine Learning Approach to Determining a Solar Wind Index for Space Weather Prediction

Abstract:

It is well known that the interaction of solar wind with the magnetosphere gives rise to various space weather events. There exists more than a couple of dozens of physical parameters associated with solar wind and only a few are used in geospace models built from first-principles. Using machine learning (ML) techniques, we developed a method to determine a subset of the solar wind properties that can be used to reconstruct the solar wind pattern (solar wind index, SWI). This has been done for solar wind of different origin (such as ejecta, coronal holes, streamers and sector reversal: Camporeale et al., JGR 122, 2017) separately to infer the dependence, if any, of the source region on SWI. We present the ML method we adopted and the results.

This project has received funding from the European Union's Horizon 2020 research and innovation Program under grant agreement 776262 (AIDA).