Saved in:
| Main Authors: | , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2410.02530 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866914963569770496 |
|---|---|
| author | Walsh, James Gass, Daniel G. Pollan, Raul Ramos Wright, Paul J. Galvez, Richard Kasmanoff, Noah Naradowsky, Jason Spalding, Anne Parr, James Baydin, Atılım Güneş |
| author_facet | Walsh, James Gass, Daniel G. Pollan, Raul Ramos Wright, Paul J. Galvez, Richard Kasmanoff, Noah Naradowsky, Jason Spalding, Anne Parr, James Baydin, Atılım Güneş |
| contents | SDO-FM is a foundation model using data from NASA's Solar Dynamics Observatory (SDO) spacecraft; integrating three separate instruments to encapsulate the Sun's complex physical interactions into a multi-modal embedding space. This model can be used to streamline scientific investigations involving SDO by making the enormous datasets more computationally accessible for heliophysics research and enable investigations that require instrument fusion. We discuss four key components: an ingestion pipeline to create machine learning ready datasets, the model architecture and training approach, resultant embeddings and fine-tunable models, and finally downstream fine-tuned applications. A key component of this effort has been to include subject matter specialists at each stage of development; reviewing the scientific value and providing guidance for model architecture, dataset, and training paradigm decisions. This paper marks release of our pretrained models and embedding datasets, available to the community on Hugging Face and sdofm.org. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2410_02530 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | A Foundation Model for the Solar Dynamics Observatory Walsh, James Gass, Daniel G. Pollan, Raul Ramos Wright, Paul J. Galvez, Richard Kasmanoff, Noah Naradowsky, Jason Spalding, Anne Parr, James Baydin, Atılım Güneş Solar and Stellar Astrophysics Computer Vision and Pattern Recognition SDO-FM is a foundation model using data from NASA's Solar Dynamics Observatory (SDO) spacecraft; integrating three separate instruments to encapsulate the Sun's complex physical interactions into a multi-modal embedding space. This model can be used to streamline scientific investigations involving SDO by making the enormous datasets more computationally accessible for heliophysics research and enable investigations that require instrument fusion. We discuss four key components: an ingestion pipeline to create machine learning ready datasets, the model architecture and training approach, resultant embeddings and fine-tunable models, and finally downstream fine-tuned applications. A key component of this effort has been to include subject matter specialists at each stage of development; reviewing the scientific value and providing guidance for model architecture, dataset, and training paradigm decisions. This paper marks release of our pretrained models and embedding datasets, available to the community on Hugging Face and sdofm.org. |
| title | A Foundation Model for the Solar Dynamics Observatory |
| topic | Solar and Stellar Astrophysics Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2410.02530 |