Forecasting the Probability of Large Rates of Change of the Geomagnetic Field in the UK: Timescales, Horizons and Thresholds

Smith, A. W., Forsyth, C., Rae, Jonathan, Garton, T. M., Bloch, T., Jackman, C. M. and Bakrania, M. (2021) Forecasting the Probability of Large Rates of Change of the Geomagnetic Field in the UK: Timescales, Horizons and Thresholds. Space Weather, 19 (9). e2021SW002788. ISSN 1542-7390

[img]
Preview
Text
2021SW002788.pdf - Published Version
Available under License Creative Commons Attribution 4.0.

Download (3MB) | Preview
[img]
Preview
Text
2021SW002788.pdf - Accepted Version

Download (1MB) | Preview
Official URL: https://doi.org/10.1029/2021sw002788

Abstract

Large Geomagnetically Induced Currents (GICs) pose a risk to ground based infrastructure such as power networks. Large GICs may be induced when the rate of change of the ground magnetic field is significantly elevated. We assess the ability of three different machine learning model architectures to process the time history of the incoming solar wind and provide a probabilistic forecast as to whether the rate of change of the ground magnetic field will exceed specific high thresholds at a location in the UK. The three models tested represent feed forward, convolutional and recurrent neural networks.

We find all three models are reliable and skillful, with Brier skill scores, ROC scores and PR scores of approximately 0.25, 0.95 and 0.45, respectively. When evaluated during two example magnetospheric storms we find that all scores increase significantly, indicating that the models work better during active intervals. The models perform excellently through the majority of the storms, however they do not fully capture the ground response around the initial sudden commencements. We attribute this to the use of propagated solar wind data not allowing the models notice to forecast impulsive phenomenon.

Increasing the volume of solar wind data provided to the models does not produce appreciable increases in model performance, possibly due to the fixed model structures and limited training data. However, increasing the horizon of the forecast from 30 minutes to 3 hours increases the performance of the models, presumably as the models need not be as precise about timing.

Item Type: Article
Additional Information: Funding information: A. W. Smith and C. Forsyth were supported by STFC consolidated grant ST/S000240/1, and NERC grants NE/P017150/1 and NE/V002724/1. C. Forsyth was also supported by the NERC Independent Research Fellowship NE/N014480/1. I. J. Rae was supported by STFC consolidated grant ST/V006320/1. C. M. Jackman's work was supported by the Science Foundation Ireland grant 18/FRL/6199. M. R. Bakrania was supported by a UCL Impact Studentship, joint funded by the ESA NPI program.
Uncontrolled Keywords: GICs, Space Weather, Forecasting, Machine Learning, Neural Networks, Model Validation
Subjects: F300 Physics
F500 Astronomy
F800 Physical and Terrestrial Geographical and Environmental Sciences
Department: Faculties > Engineering and Environment > Mathematics, Physics and Electrical Engineering
Depositing User: Elena Carlaw
Date Deposited: 19 Aug 2021 08:12
Last Modified: 28 Sep 2021 08:30
URI: http://nrl.northumbria.ac.uk/id/eprint/46942

Actions (login required)

View Item View Item

Downloads

Downloads per month over past year

View more statistics