NextFin news, Scientists at New York University Abu Dhabi (NYUAD) announced on this Wednesday that they have developed an artificial intelligence (AI) model capable of predicting solar wind speeds up to four days in advance with significantly improved accuracy. This breakthrough was achieved at NYU Abu Dhabi, United Arab Emirates, and the findings were published in The Astrophysical Journal Supplement Series.
The AI system, led by Postdoctoral Associate Dattaraj Dhuri and Co-Principal Investigator Shravan Hanasoge from the Center for Space Science (CASS) at NYUAD, analyzes high-resolution ultraviolet images of the Sun taken by NASA's Solar Dynamics Observatory. Unlike conventional AI models that process text, this model interprets solar images to detect patterns linked to changes in solar wind.
Solar wind is a continuous stream of charged particles emitted by the Sun. When intensified, these particles can cause space weather events that disrupt Earth's atmosphere, damage satellite electronics, interfere with navigation systems, and affect power grids. A notable incident in 2022 saw a strong solar wind event destroy 40 SpaceX Starlink satellites, highlighting the critical need for improved forecasting.
The NYUAD AI model demonstrated a 45 percent improvement in forecast accuracy compared to current operational models and a 20 percent improvement over previous AI-based approaches. This enhanced predictive capability allows for earlier warnings, helping to safeguard critical infrastructure on Earth and in space.
"This is a major step forward in protecting the satellites, navigation systems, and power infrastructure that modern life depends on," said Dattaraj Dhuri, lead author of the study. "By combining advanced AI with solar observations, we can give early warnings that help safeguard critical technology on Earth and in space."
The research underscores the potential of AI to address one of space science's most challenging problems: forecasting solar wind. With more reliable predictions, scientists and engineers can better prepare for disruptive space weather events, thereby strengthening resilience against potential damage to essential technology and services worldwide.
NYU Abu Dhabi, ranked among the world's top universities, has established over 90 faculty labs and projects, producing more than 9,200 internationally recognized research publications.
The study referenced is titled "A Multimodal Encoder–Decoder Neural Network for Forecasting Solar Wind Speed at L1," authored by Dattaraj B. Dhuri, Shravan M. Hanasoge, and colleagues, and is accessible via DOI: 10.3847/1538-4365/adf436.
Explore more exclusive insights at nextfin.ai.