Forecasting GICs and geoelectric fields from solar wind data using LSTMs: application in Austria

TL;DR

This study employs LSTM neural networks to directly forecast geoelectric fields and GICs from solar wind data, improving prediction accuracy for space weather effects in Austria.

Contribution

It introduces a machine learning approach using LSTMs to directly predict GICs and geoelectric fields from solar wind data, a novel method in this context.

Findings

LSTM models achieved a correlation of around 0.6 with actual GIC measurements.

The models predicted mild GIC activity with about 50% probability.

Prediction accuracy for large GICs was limited, correctly forecasting only a fraction of the largest events.

Abstract

The forecasting of local GIC effects has largely relied on the forecasting of dB/dt as a proxy and, to date, little attention has been paid to directly forecasting the geoelectric field or GICs themselves. We approach this problem with machine learning tools, specifically recurrent neural networks or LSTMs by taking solar wind observations as input and training the models to predict two different kinds of output: first, the geoelectric field components Ex and Ey; and second, the GICs in specific substations in Austria. The training is carried out on the geoelectric field and GICs modelled from 26 years of one-minute geomagnetic field measurements, and results are compared to GIC measurements from recent years. The GICs are generally predicted better by an LSTM trained on values from a specific substation, but only a fraction of the largest GICs are correctly predicted. This model had a correlation with measurements of around 0.6, and a root-mean-square error of 0.7 A. The probability of detecting mild activity in GICs is around 50%, and 15% for larger GICs.