Enhancing Solar Driver Forecasting with Multivariate Transformers

TL;DR

This paper introduces a Transformer-based framework for solar driver forecasting that improves accuracy during high activity periods by using a custom loss function and an 18-day lookback window.

Contribution

It presents a novel Transformer-based model with a custom loss function for balanced solar activity prediction, outperforming existing benchmarks.

Findings

Lower mean error compared to benchmarks

Improved accuracy during high solar activity periods

Effective use of a custom loss function for balanced training

Abstract

In this work, we develop a comprehensive framework for F10.7, S10.7, M10.7, and Y10.7 solar driver forecasting with a time series Transformer (PatchTST). To ensure an equal representation of high and low levels of solar activity, we construct a custom loss function to weight samples based on the distance between the solar driver's historical distribution and the training set. The solar driver forecasting framework includes an 18-day lookback window and forecasts 6 days into the future. When benchmarked against the Space Environment Technologies (SET) dataset, our model consistently produces forecasts with a lower standard mean error in nearly all cases, with improved prediction accuracy during periods of high solar activity. All the code is available on Github https://github.com/ARCLab-MIT/sw-driver-forecaster.