Solaris: A Foundation Model of the Sun
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2024
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866913585227104256 |
|---|---|
| author | Majid, Harris Abdul Sittoni, Pietro Tudisco, Francesco |
| author_facet | Majid, Harris Abdul Sittoni, Pietro Tudisco, Francesco |
| contents | Foundation models have demonstrated remarkable success across various scientific domains, motivating our exploration of their potential in solar physics. In this paper, we present Solaris, the first foundation model for forecasting the Sun's atmosphere. We leverage 13 years of full-disk, multi-wavelength solar imagery from the Solar Dynamics Observatory, spanning a complete solar cycle, to pre-train Solaris for 12-hour interval forecasting. Solaris is built on a large-scale 3D Swin Transformer architecture with 109 million parameters. We demonstrate Solaris' ability to generalize by fine-tuning on a low-data regime using a single wavelength (1700 Å), that was not included in pre-training, outperforming models trained from scratch on this specific wavelength. Our results indicate that Solaris can effectively capture the complex dynamics of the solar atmosphere and transform solar forecasting. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2411_16339 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Solaris: A Foundation Model of the Sun Majid, Harris Abdul Sittoni, Pietro Tudisco, Francesco Solar and Stellar Astrophysics Instrumentation and Methods for Astrophysics Machine Learning Space Physics Foundation models have demonstrated remarkable success across various scientific domains, motivating our exploration of their potential in solar physics. In this paper, we present Solaris, the first foundation model for forecasting the Sun's atmosphere. We leverage 13 years of full-disk, multi-wavelength solar imagery from the Solar Dynamics Observatory, spanning a complete solar cycle, to pre-train Solaris for 12-hour interval forecasting. Solaris is built on a large-scale 3D Swin Transformer architecture with 109 million parameters. We demonstrate Solaris' ability to generalize by fine-tuning on a low-data regime using a single wavelength (1700 Å), that was not included in pre-training, outperforming models trained from scratch on this specific wavelength. Our results indicate that Solaris can effectively capture the complex dynamics of the solar atmosphere and transform solar forecasting. |
| title | Solaris: A Foundation Model of the Sun |
| topic | Solar and Stellar Astrophysics Instrumentation and Methods for Astrophysics Machine Learning Space Physics |
| url | https://arxiv.org/abs/2411.16339 |