NASA and IBM have jointly developed Surya, a new open-source artificial intelligence model that predicts solar flares with greater speed and accuracy, analyzing solar activity to forecast events and their potential impact on Earth.
Current solar flare forecasting relies on instruments monitoring the sun and NOAA’s Space Weather Prediction Center. When a solar flare erupts, NOAA predicts whether it will impact Earth. Surya aims to improve upon these existing methods by leveraging AI to analyze solar data more efficiently.
The 366M-parameter AI model, whose the Sanskrit word for the Sanskrit word for “Sun,” learns general-purpose solar representations through spatiotemporal transformers. This enables state-of-the-art performance in solar flare forecasting, active region segmentation, solar wind prediction, and EUV spectra modeling, as stated on its GitHub page. The model is trained using data from NASA’s Solar Dynamic Observatory (SDO), which has been monitoring the sun since 2010, along with data from eight other research centers.
Andrés Muñoz-Jaramillo, a solar physicist at Southwest Research Institute and lead researcher on Surya, stated, “We want to give Earth the longest lead time possible. Our hope is that the model has learned all the critical processes behind our star’s evolution through time so that we can extract actionable insights.” The researchers hope Surya will provide longer lead times for warnings about geomagnetic storms, which can affect Earth.
One potential benefit of improved solar flare prediction is the ability to forecast auroras further in advance. Aurora borealis, or the Northern Lights, are a result of geomagnetic storms interacting with the Earth’s magnetic field. By predicting these storms earlier, scientists can give a better estimate on when and where auroras might be visible.
IBM emphasizes the potential for Surya to enhance existing prediction methods. Prior to Surya, NASA used methods like observing flashes of light in the sun’s corona to predict solar flares. NOAA also has its own prediction methods, but these have limitations. IBM believes that Surya can improve the accuracy and timeliness of these predictions.
Juan Bernabé-Moreno, IBM’s director in charge of scientific collaboration with NASA, said, “We’ve been on this journey of pushing the limits of technology with NASA since 2023, delivering pioneering foundational AI models to gain an unprecedented understanding of our planet Earth. With Surya, we have created the first foundation model to look the sun in the eye and forecast its moods.”
NASA’s Solar Dynamic Observatory was created to understand the underlying physics of the sun, but this process has been slow with many unanswered questions. Surya represents a step forward in harnessing AI to accelerate our understanding of solar activity and its impact on Earth.
