Project Grant 2348495

This $173,657 Project Grant awarded by the National Science Foundation's (NSF) Computer and Information Science and Engineering (CISE) program supports fundamental research by Northern Arizona University (NAU) to develop a novel computational framework for discovering parsimonious governing equations that describe the behavior of complex physical systems under uncertainty. The framework leverages interpretable deep learning and incorporates prior knowledge from simplified models to enable more computationally efficient analysis. The research will be evaluated through testbed problems such as modeling building behavior and turbulence, with the resulting framework also applied to other critical challenges like wildfire spread and enzyme reactions. The project aims to advance the state-of-the-art in understanding the fundamental principles governing complex physical systems and provide the research community with a powerful analytical tool. Key educational and outreach activities are also planned, including mentoring a graduate student and incorporating findings into undergraduate coursework.