A Foundation Model for the Solar Dynamics Observatory

TL;DR

SDO-FM is a multi-modal foundation model that integrates data from NASA's Solar Dynamics Observatory to facilitate advanced heliophysics research and instrument fusion, making large datasets more accessible.

Contribution

This work introduces a novel foundation model for SDO data, including datasets, architecture, and applications, with community access and expert-guided development.

Findings

Pretrained models and embeddings released for community use

Model effectively fuses multi-instrument solar data

Enables new scientific investigations in heliophysics

Abstract

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.