Jonghyun “Harry” Lee of the Water Resources Research Center (WRRC) has been awarded a $500,000 grant from the National Science Foundation (NSF) under its Collaborations in Artificial Intelligence and Geosciences (CAIG) program. The University of Hawaiʻi at Mānoa will serve as the lead institution on a three-year, nearly $1 million collaborative project, alongside the University of Texas at Austin, to advance artificial intelligence applications in geoscience.
Rising seas, stronger storms, saltwater contamination of freshwater resources, and coastal ecosystem degradation pose increasing threats to coastal communities. These environmental pressures impact drinking water supplies, agriculture, infrastructure, local economies, and daily life for millions of people.
To address these challenges, the joint project will develop fast, accessible AI models to better understand how water exchanges between coastal aquifers and the ocean. By combining recent advances in artificial intelligence with traditional environmental modeling, the team aims to predict critical coastal risks—such as seawater intrusion into freshwater aquifers and submarine groundwater discharge—faster and more accurately.
“This project will improve our understanding and prediction of how groundwater and the ocean interact in Hawaiʻi’s coastal aquifers, helping communities better protect freshwater resources and coastal ecosystems from challenges, such as seawater intrusion and coastal inundation,” principal investigator Lee said.
Advancing Coastal Science Through Next-Generation AI
The researchers will build a computational framework that pairs neural networks with established physics models. This approach creates high-speed “surrogate models” capable of running complex, computationally heavy simulations of groundwater and ocean interactions at a fraction of the cost, while preserving essential physics laws at the land–sea boundary.
Key features and goals of the project include:
- Flexible AI architecture: Combining specialized neural network modules using a “mixture-of-experts” framework to process both long-term ocean circulation patterns and brief, high-intensity events, like storm surges.
- Real-world testing: Validating models on benchmark applications in Hawaiʻi and Texas coastal systems.
- Near-real-time forecasts: Enabling rapid assessments of seawater intrusion and coastal groundwater discharge to support digital twin models of complex ecosystems.
- Practical decision tools: Providing actionable insights to guide water management, infrastructure planning, and long-term coastal resilience.
- Open science and education: Developing open-source software, interactive visualization tools, and interdisciplinary training for students and early-career researchers.
“Students and postdocs working on this project will be supported by hands-on research and training at the intersection of groundwater hydrology, coastal science, computational modeling, and artificial intelligence, preparing them for careers addressing Hawaiʻi’s water and environmental challenges,” Lee stated.
The resulting tools and predictions will give local leaders and resource managers the data needed to make informed decisions about water management and infrastructure planning in vulnerable coastal regions.