Enhancing Solar Driver Forecasting with Multivariate Transformers
This work addresses forecasting accuracy for solar drivers, which is important for space weather prediction, but it is incremental as it applies an existing method to a specific domain with modifications.
The paper tackles solar driver forecasting by developing a Transformer-based framework with a custom loss function to handle varying solar activity levels, resulting in lower standard mean error compared to a benchmark dataset, especially during high activity periods.
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.