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.
@article{arxiv.2406.15847,
title = {Enhancing Solar Driver Forecasting with Multivariate Transformers},
author = {Sergio Sanchez-Hurtado and Victor Rodriguez-Fernandez and Julia Briden and Peng Mun Siew and Richard Linares},
journal= {arXiv preprint arXiv:2406.15847},
year = {2024}
}
Comments
Short paper accepted for oral presentation at the SPAICE Conference 2024 (https://spaice.esa.int/)