Enhancing Solar Driver Forecasting with Multivariate Transformers
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866929446399770624 |
|---|---|
| author | Sanchez-Hurtado, Sergio Rodriguez-Fernandez, Victor Briden, Julia Siew, Peng Mun Linares, Richard |
| author_facet | Sanchez-Hurtado, Sergio Rodriguez-Fernandez, Victor Briden, Julia Siew, Peng Mun Linares, Richard |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2406_15847 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Enhancing Solar Driver Forecasting with Multivariate Transformers Sanchez-Hurtado, Sergio Rodriguez-Fernandez, Victor Briden, Julia Siew, Peng Mun Linares, Richard Space Physics Artificial Intelligence Machine Learning 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. |
| title | Enhancing Solar Driver Forecasting with Multivariate Transformers |
| topic | Space Physics Artificial Intelligence Machine Learning |
| url | https://arxiv.org/abs/2406.15847 |