Improving the Lead Time of Geomagnetic Index Forecasts using Solar Wind Forecasts and Deep Learning

Abstract:

Historically, the solar wind and interplanetary magnetic field (IMF) measurements gathered by the Advanced Composition Explorer (ACE) satellites have driven the study and prediction of geomagnetic activity indices. Results have demonstrated the ability to forecast these indices with high correlation a few hours in advance. In this work, we seek to simultaneously forecast 4 proxies for magnetic activity around Earth. Specifically, we employ Long Short-Term Memory neural networks to forecast the Auroral Electrojet indices (AE, AU, and AL), as well as the Disturbance Storm-Time index from several hours to several days in advance. The enclosed figure demonstrates that with a clairvoyant forecast of solar wind measurements taken by the ACE satellite, we can forecast these geomagnetic indices very well out to 3 days in advance. We use real-world forecasts of the solar wind as a proxy for these forecasted measurements, such as the WSA-Enlil Solar Wind Forecast, to drive out the effective lead time of these geomagnetic index forecasts.