Vision transformers and techniques for improving solar wind speed forecasts using solar EUV images

Svoboda, F.; Brown, E.; Meredith, N.P. ORCID: https://orcid.org/0000-0001-5032-3463; Lane, N.D.. 2021 Vision transformers and techniques for improving solar wind speed forecasts using solar EUV images. In: Fourth Workshop on Machine Learning and the Physical Sciences (NeurIPS 2021), Online, 13 December 2021. Online, The Neural Information Processing Systems Foundation.

Full text not available from this repository. (Request a copy)

Official URL: https://ml4physicalsciences.github.io/2021/files/N...

Abstract/Summary

Extreme-ultraviolet images taken by the Atmospheric Imaging Assembly make it possible to use deep vision techniques in the prediction of solar wind speed - a difficult, high-impact, and unsolved problem. This study uses vision transformers and a set of methodological and modelling improvements to deliver an 11.1% lower RMSE error, and a 17.4% higher prediction correlation compared to the previous state of the art models. Furthermore, our analysis shows that vision transformers combined with our pipeline consistently outperform convolutional alternatives. Additionally, the best vision transformer outperforms the best convolutional model by 1.8% in RMSE and 2.6% in correlation with the ground truth solar wind speed.

Item Type:	Publication - Conference Item (Paper)
Related URLs:	Publisher Organisation
Date made live:	20 Dec 2021 11:03 +0 (UTC)
URI:	https://nora.nerc.ac.uk/id/eprint/531598

Item Type:

Publication - Conference Item (Paper)

Related URLs:

Date made live:

20 Dec 2021 11:03 +0 (UTC)

URI:

https://nora.nerc.ac.uk/id/eprint/531598