Project Grant 2427579

This Project Grant award from the National Science Foundation's Geosciences Program (CFDA 47.050) provides $202,000 to support research aimed at developing data-driven methods for predicting extreme weather events under climate change. The key products to be delivered under this 2-year award include:

1. Developing neural network models capable of capturing the statistics of extreme events in future climate projections. This will involve addressing challenges such as spectral bias and the ability to represent rare extreme events not well represented in training data.

2. Testing the neural network models using a hierarchy of climate models, from simple quasi-geostrophic systems to complex global climate models from the Coupled Model Intercomparison Project (CMIP).

3. Providing summer research opportunities for undergraduate students at the University of Chicago, where the Principal Investigator works with two faculty mentors.

The research aims to advance the use of data-driven methods as a computationally efficient approach to studying the impacts of climate change on extreme weather events, with potential applications in planning for and adapting to such events.