Project Grant 2514584

This Project Grant award, provided by the National Science Foundation (NSF) under the Computer and Information Science and Engineering (CFDA 47.070) program, supports the development of new methods, algorithms, and software to seamlessly integrate machine learning (ML) and artificial intelligence (AI) with traditional physical knowledge for modeling cyber-physical systems (CPS). The overarching goal is to create a comprehensive, flexible, and synergistic cyberinfrastructure for composite physics-informed machine learning (PIML) and active learning of dynamic systems. Key objectives include: (1) establishing a unified PIML theoretical framework, (2) developing a framework and software for composing heterogeneous PIML models, and (3) creating physics-informed active learning methods to improve the sample efficiency and accuracy of learning. This $477,585 award to the University of Central Florida, with a period of performance from October 1, 2024 to July 31, 2028, aims to advance the state of knowledge in integrating physics and ML to enable high-performance data-driven prediction, simulation, optimization, and control methods for CPS, benefiting a broad range of scientific and engineering applications.