# A Foundation Model for the Solar Dynamics Observatory

arXiv: https://arxiv.org/abs/2410.02530 · HTML: https://mlsanity.com/paper/2410.02530/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 6 of its 15 references that are in the map.
- First posted on arXiv 3 Oct 2024.

## Builds on (most cited first, 6 of 6)

- [Masked Autoencoders Are Scalable Vision Learners](https://mlsanity.com/paper/2111.06377/) (2021)
- [NVAE: A Deep Hierarchical Variational Autoencoder](https://mlsanity.com/paper/2007.03898/) (2020)
- [Masked Autoencoders As Spatiotemporal Learners](https://mlsanity.com/paper/2205.09113/) (2022)
- [Foundation Models for Generalist Geospatial Artificial Intelligence](https://mlsanity.com/paper/2310.18660/) (2023)
- [A Machine Learning Dataset Prepared From the NASA Solar Dynamics Observatory Mission](https://mlsanity.com/paper/1903.04538/) (2019)
- [High-Cadence Thermospheric Density Estimation enabled by Machine Learning on Solar Imagery](https://mlsanity.com/paper/2312.06845/) (2023)

## Built on by (most cited first, 3 of 3)

- [Surya: Foundation Model for Heliophysics](https://mlsanity.com/paper/2508.14112/) (2025)
- [Predicting partially observable dynamical systems via diffusion models with a multiscale inference scheme](https://mlsanity.com/paper/2511.19390/) (2025)
- [Contrastive Heliophysical Image Pretraining for Solar Dynamics Observatory Records](https://mlsanity.com/paper/2511.22958/) (2025)

## Abstract (arXiv)

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.