IBM and NASA Launch Open-Source AI Model to Predict Solar Storms

IBM and NASA have unveiled Surya, the most advanced open-source foundation model to date designed for solar weather forecasting and space-based technology protection.

Named after the Sanskrit word for the Sun, Surya uses high-resolution solar data and artificial intelligence to analyse, predict, and visualise solar activity—offering a critical new tool to shield satellites, power grids, and navigation systems from space weather disruptions.

“Think of this as a weather forecast for space,” said Juan Bernabe-Moreno, Director of IBM Research Europe, UK and Ireland. “Just as we work to prepare for hazardous weather events, we need to do the same for solar storms. Surya gives us unprecedented capability to anticipate what's coming and is not just a technological achievement, but a critical step toward protecting our technological civilization from the star that sustains us.”

Surya was trained on nine years of solar imagery from NASA’s Solar Dynamics Observatory, addressing the challenge of working with data 10 times larger than typical AI inputs. The model enhances solar flare classification by 16% and can predict solar flare locations up to two hours in advance, visually highlighting where flares may emerge.

“We are advancing data-driven science by embedding NASA's deep scientific expertise into cutting-edge AI models,” said Kevin Murphy, Chief Science Data Officer at NASA. “By developing a foundation model trained on NASA's heliophysics data, we're making it easier to analyze the complexities of the Sun's behavior with unprecedented speed and precision.”

Solar storms can cause massive disruptions—from airline navigation issues and satellite damage to power outages and agricultural challenges. By releasing Surya on Hugging Face, IBM and NASA aim to democratize access and enable researchers to adapt the model globally. Surya joins IBM and NASA’s growing Prithvi model family, including AI for weather and geospatial forecasting.