EMBRACE-AGS-Seed: Harnessing the Power of Machine Learning to Generate Ensembles of Regional Climate Projections

Northern Illinois University, Dekalb IL

Investigators

Abstract

This project aims to advance our understanding of how extreme weather events, such as heavy rainfall and flooding, may change in response to future climate scenarios. Current methods rely on advanced computer models capable of simulating the complex atmospheric processes that drive these events. However, these models require significant computational resources, which limits their ability to explore a wide range of possible outcomes. This research will evaluate whether artificial intelligence and machine learning can provide a faster, more efficient alternative for simulating rainfall patterns. The objective is to determine whether these modern approaches can replicate the detail and accuracy of traditional climate models while using fewer resources. The project will train students and help build capacity at the investigator's institutions by creating local computational capabilities for testing and implementing modern artificial intelligence and machine learning models. The significance of this work lies in its potential to make climate modeling more accessible and practical. Improving our understanding of how extreme events may change can help communities, policymakers, and researchers better anticipate and respond to their impacts. Additionally, the project places a strong emphasis on education by involving students at an emerging research institution in advanced climate and data science research. By offering hands-on training and access to computational tools, this project aims to prepare the next generation of experts in climate-related fields. 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.