RESEARCH PROJECT

As the impact of climate change grows, affecting ecosystems, economies, and communities worldwide, the need for effective mitigation and adaptation strategies becomes critical. A key element in these efforts is the ability to forecast the future impacts of climate change accurately. While global climate models (GCMs) offer climate projections, their coarse spatial resolution falls short in capturing regional characteristics accurately, which are crucial for managing risks related to climate hazards like floods, droughts, and heatwaves.

Dynamic downscaling, which includes regional climate models, offers more detailed projections but is resource-intensive and cannot generate the ensemble of projections that GCMs can, thus limiting its usefulness for risk assessment and uncertainty analysis. Alternatively, statistical downscaling provides a computationally efficient way to achieve high-resolution climate projections. Recent breakthroughs in generative artificial intelligence (AI) with neural networks, or generative machine learning, offer a range of new possibilities for statistical downscaling.

This project will leverage advancements in generative AI to generate high-resolution (1km) precipitation maps at daily and sub-daily scales for the Hawaiian Islands and use these to quantify the risk of flooding events. The models developed in this project will be used to improve historical rainfall maps for Hawaiʻi and projections of future rainfall under global general circulation models (GCM) climate scenarios. Improving these risk estimates will significantly enhance the ability of local decision-makers to plan for climate change impacts.