CAIG: Unraveling the Extreme Near-Global Marine Heatwaves of 2023: Using Artificial Intelligence to Understand the Physics and Implications for the Future

Marine heatwaves, periods of unusually warm ocean temperatures, significantly threaten marine ecosystems, biodiversity, and human activities. In 2023, extreme marine heatwaves in the North Atlantic and other ocean basins contributed to record-breaking global temperatures from June to September. This project will use observational data, climate models, and artificial intelligence to understand the roles of surface heat, clouds, and ocean currents in causing marine heatwaves. Given the severe impacts of marine heatwaves on ecosystems and coastal economies, this work will have important impacts on climate models and long-term forecasts. The 2023 marine heatwaves were more intense than expected from steady human-induced ocean warming. One hypothesis is that extreme marine heatwaves result from both natural variability and human impact and arise from combinations of atmospheric circulation anomalies, reduced mixing of cool water from below, and anomalous warm advection by ocean currents. This project will test whether the strikingly weak North Atlantic subtropical high in 2023 was critical to driving the extreme heat. This project will use machine learning to integrate observations and model simulations in order to formulate hypotheses of drivers of record-shattering extremes. This will determine if the 2023 events are anomalous or part of a pattern of higher ocean temperatures. The project will involve a postdoctoral researcher and build workforce capacity through a collaboration with Columbia University’s Learning the Earth with Artificial Intelligence and Physics Center. This award by the Division of Research, Innovation, Synergies, and Education within the Directorate for Geosciences is jointly supported by the National Discovery Cloud for Climate initiative within the Office of Advanced Cyberinfrastructure within the Directorate for Computer and Information Science and Engineering. This award reflects NSF's statutory mission and has been deemed worthy of support through evaluation using the Foundation's intellectual merit and broader impacts review criteria.