Simultaneously forecasting global geomagnetic activity using Recurrent Networks

TL;DR

This paper introduces a sequence-to-sequence recurrent network model that simultaneously forecasts multiple key proxies of global geomagnetic activity up to 6 hours ahead, improving early warning capabilities for space weather events.

Contribution

It presents a novel multi-proxy forecasting approach using recurrent networks for global space weather prediction, outperforming existing predictors and baselines.

Findings

Improved prediction accuracy over current models.

Effective multi-proxy forecasting up to 6 hours ahead.

Outperforms persistence baseline in early warning.

Abstract

Many systems used by society are extremely vulnerable to space weather events such as solar flares and geomagnetic storms which could potentially cause catastrophic damage. In recent years, many works have emerged to provide early warning to such systems by forecasting these events through some proxy, but these approaches have largely focused on a specific phenomenon. We present a sequence-to-sequence learning approach to the problem of forecasting global space weather conditions at an hourly resolution. This approach improves upon other work in this field by simultaneously forecasting several key proxies for geomagnetic activity up to 6 hours in advance. We demonstrate an improvement over the best currently known predictor of geomagnetic storms, and an improvement over a persistence baseline several hours in advance.