IBM and NASA Develop AI Model to Predict Solar Storms and Protect Space-Based Technology

IBM and NASA have unveiled "Surya," an AI model that uses artificial intelligence to predict solar storms and protect satellites, GPS, power grids, and telecommunications from their impacts. The model applies AI to solar image interpretation and space weather forecasting research, offering a novel way to protect Earth's technological infrastructure from solar flares and coronal mass ejections.

NASA and IBM have jointly developed "Surya," an advanced AI model designed to predict solar storms and mitigate their impacts on Earth's technological infrastructure. Surya leverages artificial intelligence to analyze vast amounts of solar data, providing early warnings and enhancing space weather forecasting capabilities.

The AI model, trained on nine years of observations from NASA’s Solar Dynamics Observatory, can predict solar flares two hours into the future, surpassing existing benchmarks by 16% [1]. Surya's ability to generate visual predictions of solar flares marks a significant step towards operational space weather prediction.

Surya's architecture allows it to adapt quickly to new tasks and applications, including tracking active regions, forecasting flare activity, and predicting solar wind speed. This adaptability makes it a versatile tool for various scientific domains, from planetary science to Earth observation.

The model's success is built on the Solar Dynamics Observatory's long-term database, which has provided an unbroken, high-resolution record of the Sun since 2010. This stable dataset, spanning an entire solar cycle, is uniquely suited for training AI models like Surya, enabling them to detect subtle patterns in solar behavior.

Surya is part of a broader NASA push to develop open-access, AI-powered science tools. Both the model and training datasets are freely available online, lowering barriers to participation and sparking new discoveries. The model is accessible on HuggingFace and the code is available on GitHub, encouraging the science and applications community to test and explore its capabilities.

The development of Surya was supported by the National Artificial Intelligence Research Resource (NAIRR) Pilot, a National Science Foundation (NSF)-led initiative that provides researchers with access to advanced computing, datasets, and AI tools. The NAIRR Pilot brought together federal and industry resources to accelerate scientific breakthroughs.

Surya's AI architecture was jointly developed by the Interagency Implementation and Advanced Concepts Team (IMPACT) under the Office of Data Science and Informatics at NASA’s Marshall Space Flight Center, IBM, and a collaborative science team consisting of experts from various universities and NASA centers.

For more information about the development and applications of Surya, visit the NASA Science Data Portal: [1] https://science.data.nasa.gov/features-events/inside-surya-solar-ai-model

References:

[1] https://science.nasa.gov/science-research/artificial-intelligence-model-heliophysics/