Can a hybrid AI-physics model address the challenges of typhoon forecasting? New study shows significant accuracy gains
Peer-Reviewed Publication
Updates every hour. Last Updated: 19-Sep-2025 14:11 ET (19-Sep-2025 18:11 GMT/UTC)
A research team has studied the development of the Shanghai Typhoon Model from a traditional physics-based regional model toward a data-driven, machine-learning typhoon forecasting system. They summarize the model’s performance in Typhoon Danas in 2025, noting that a hybrid Shanghai Typhoon Model provides a significant advancement in forecast accuracy. Their paper outlines a roadmap for evolving the physically driven Shanghai Typhoon Model into a purely data-driven, regional machine-learning weather-prediction model designed for typhoon prediction.
716-645-4614
Tiny solid particles – like pollutants, cloud droplets and medicine powders – form highly concentrated clusters in turbulent environments like smokestacks, clouds and pharmaceutical mixers. What causes these extreme clusters – which make it more difficult to predict everything from the spread of wildfire smoke to finding the right combination of ingredients for more effective drugs – has puzzled scientists. A new University at Buffalo study, published Sept. 19 in Proceedings of the National Academy of Sciences, suggests the answer lies within the electric forces between particles.