Download
Surya is an open‑source, AI‑based foundation model for heliophysics developed collaboratively by NASA (via the IMPACT AI team) and IBM. Named after the Sanskrit word for “sun,” Surya is trained on nine years of high‑resolution solar imagery from NASA’s Solar Dynamics Observatory (SDO). It is designed to forecast solar phenomena—such as flares, solar wind, irradiance, and active region behavior—by predicting future solar images with a sophisticated long–short vision transformer architecture, thereby enabling improved space weather forecasting. Foresees solar flares, wind, EUV spectra, and active region formation in advance. Achieves approximately 16% improvement in forecasting accuracy over traditional methods. 366-million‑parameter foundation model capturing general-purpose solar representations.
Features
- 366-million‑parameter foundation model capturing general-purpose solar representations
- Employs long–short range transformer with spectral gating for spatiotemporal modeling
- Foresees solar flares, wind, EUV spectra, and active region formation in advance
- Achieves approximately 16% improvement in forecasting accuracy over traditional methods
- Offers up to two hours of lead time for solar flare predictions
- Released as open-source (code on GitHub, model on Hugging Face) with accompanying dataset benchmarks (SuryaBench)
Project Samples
