Input parameter ranking for neural networks in a space weather regression problem

Abstract

Geomagnetic storms are multi-day events characterised by significant perturbations to the magnetic field of the Earth, driven by so-lar activity. Numerous efforts have been undertaken to utilise in-situ mea-surements of the solar wind plasma to predict perturbations to the geo-magnetic field measured on the ground. Typically, solar wind measure-ments are used as input parameters to a regression problem tasked with predicting a perturbation index such as the 1-minute cadence symmetric-H (Sym-H) index. We re-visit this problem, with two important twists: (i) An adapted feedforward neural network topology is designed to en-able the pairwise analysis of input parameter weights. This enables the ranking of input parameters in terms of importance to output accu-racy, without the need to train numerous models. (ii) Geomagnetic storm phase information is incorporated as model inputs and shown to increase performance. This is motivated by the fact that different physical phe-nomena are at play during different phases of a geomagnetic storm.