Project Grant 2225507

The National Science Foundation awarded a $586,319 Project Grant to the Texas A&M Engineering Experiment Station to support research and development under the Computer and Information Science and Engineering federal grant program (CFDA 47.070). The three-year award will fund the development of a Bayesian paradigm for physics-informed machine learning algorithms. Key products include new probabilistic methods with quantified uncertainty, computational and analytical methods, and unsupervised machine learning algorithms that incorporate scientific laws into models. The research aims to reduce data requirements and enable extrapolation for applications in petroleum engineering, aerospace engineering, materials science, and astronomy. A $100,000 subaward was provided to the Illinois Institute of Technology to support related research efforts. The funding will advance scientific machine learning and help solve physics-informed problems in fields such as reservoir simulation, computational fluid dynamics, and radiative transfer modeling.