# Surya: Foundation Model for Heliophysics

arXiv: https://arxiv.org/abs/2508.14112 · HTML: https://mlsanity.com/paper/2508.14112/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- Builds on 27 of its 88 references that are in the map.
- First posted on arXiv 18 Aug 2025.

## Builds on (most cited first, 27 of 27)

- [A Simple Framework for Contrastive Learning of Visual Representations](https://mlsanity.com/paper/2002.05709/) (2020)
- [Masked Autoencoders Are Scalable Vision Learners](https://mlsanity.com/paper/2111.06377/) (2021)
- [FourCastNet: A Global Data-driven High-resolution Weather Model using Adaptive Fourier Neural Operators](https://mlsanity.com/paper/2202.11214/) (2022)
- [GraphCast: Learning skillful medium-range global weather forecasting](https://mlsanity.com/paper/2212.12794/) (2022)
- [Foundation Models for Generalist Geospatial Artificial Intelligence](https://mlsanity.com/paper/2310.18660/) (2023)
- [Prithvi-EO-2.0: A Versatile Multi-Temporal Foundation Model for Earth Observation Applications](https://mlsanity.com/paper/2412.02732/) (2024)
- [Scaling transformer neural networks for skillful and reliable medium-range weather forecasting](https://mlsanity.com/paper/2312.03876/) (2023)
- [TerraMind: Large-Scale Generative Multimodality for Earth Observation](https://mlsanity.com/paper/2504.11171/) (2025)
- [Long-Short Transformer: Efficient Transformers for Language and Vision](https://mlsanity.com/paper/2107.02192/) (2021)
- [SpectFormer: Frequency and Attention is what you need in a Vision Transformer](https://mlsanity.com/paper/2304.06446/) (2023)
- [Prithvi WxC: Foundation Model for Weather and Climate](https://mlsanity.com/paper/2409.13598/) (2024)
- [How to Train Your Flare Prediction Model: Revisiting Robust Sampling of Rare Events](https://mlsanity.com/paper/2103.07542/) (2021)
- [Explaining Full-disk Deep Learning Model for Solar Flare Prediction using Attribution Methods](https://mlsanity.com/paper/2307.15878/) (2023)
- [Enhancing SDO/HMI images using deep learning](https://mlsanity.com/paper/1706.02933/) (2017)
- [Challenges with Extreme Class-Imbalance and Temporal Coherence: A Study on Solar Flare Data](https://mlsanity.com/paper/1911.09061/) (2019)
- [Machine learning in solar physics](https://mlsanity.com/paper/2306.15308/) (2023)
- [Identifying and Tracking Solar Magnetic Flux Elements with Deep Learning](https://mlsanity.com/paper/2008.12080/) (2020)
- [Fast Solar Image Classification Using Deep Learning and its Importance for Automation in Solar Physics](https://mlsanity.com/paper/1905.13575/) (2019)
- [Solar Coronal Magnetic Field Extrapolation from Synchronic Data with AI-generated Farside](https://mlsanity.com/paper/2010.07553/) (2020)
- [SCSS-Net: Solar Corona Structures Segmentation by Deep Learning](https://mlsanity.com/paper/2109.10834/) (2021)
- [Global geomagnetic perturbation forecasting using Deep Learning](https://mlsanity.com/paper/2205.12734/) (2022)
- [Embedding Ordinality to Binary Loss Function for Improving Solar Flare Forecasting](https://mlsanity.com/paper/2408.11768/) (2024)
- [Solaris: A Foundation Model of the Sun](https://mlsanity.com/paper/2411.16339/) (2024)
- [A Foundation Model for the Solar Dynamics Observatory](https://mlsanity.com/paper/2410.02530/) (2024)
- [AI Foundation Model for Heliophysics: Applications, Design, and Implementation](https://mlsanity.com/paper/2410.10841/) (2024)
- [Machine Learning in Heliophysics and Space Weather Forecasting: A White Paper of Findings and Recommendations](https://mlsanity.com/paper/2006.12224/) (2020)
- [SPACE-SUIT: An Artificial Intelligence Based Chromospheric Feature Extractor and Classifier for SUIT](https://mlsanity.com/paper/2412.08589/) (2024)

## Built on by (most cited first, 6 of 6)

- [Towards a Foundation Model for the Martian Atmosphere](https://mlsanity.com/paper/2605.28851/) (2026)
- [Contrastive Heliophysical Image Pretraining for Solar Dynamics Observatory Records](https://mlsanity.com/paper/2511.22958/) (2025)
- [Deterministic and probabilistic neural surrogates of global hybrid-Vlasov simulations](https://mlsanity.com/paper/2601.12614/) (2026)
- [Review of Machine Learning Models for Solar Energetic Particle Prediction](https://mlsanity.com/paper/2606.19539/) (2026)
- [Neural Operator based Multi-Field Reconstruction of Inner Solar Boundary State](https://mlsanity.com/paper/2608.22782/) (2026)
- [Cross-Modal Solar Image Synthesis: Adapting the Surya Foundation Model from He I 10830 AA to EUV Translation and Coronal Hole Segmentation](https://mlsanity.com/paper/2610.04553/) (2026)

## Abstract (arXiv)

Heliophysics is central to understanding and forecasting space weather events and solar activity. Despite decades of high-resolution observations from the Solar Dynamics Observatory (SDO), most models remain task-specific and constrained by scarce labeled data, limiting their capacity to generalize across solar phenomena. We introduce Surya, a 366M parameter foundation model for heliophysics designed to learn general-purpose solar representations from multi-instrument SDO observations, including eight Atmospheric Imaging Assembly (AIA) channels and five Helioseismic and Magnetic Imager (HMI) products. Surya employs a spatiotemporal transformer architecture with spectral gating and long--short range attention, pretrained on high-resolution solar image forecasting tasks and further optimized through autoregressive rollout tuning. Zero-shot evaluations demonstrate its ability to forecast solar dynamics and flare events, while downstream fine-tuning with parameter-efficient Low-Rank Adaptation (LoRA) shows strong performance on solar wind forecasting, active region segmentation, solar flare forecasting, and EUV spectra. Surya is the first foundation model in heliophysics that uses time advancement as a pretext task on full-resolution SDO data. Its novel architecture and performance suggest that the model is able to learn the underlying physics behind solar evolution.