Physics-Informed Machine Learning, Section 2 - Case Study on Heat Transfer, Part 2

Building on the previous lecture, we develop several physics-informed machine learning models using techniques such as Physics-Informed Features, Physics-Informed Loss, Physics-Informed Domain Transformation, and Physics-Informed Neural Networks (PINNs). This session examines how these methods improve model generalization beyond the training zone. Instructor: Dr. Navid Zobeiry, Associate Professor of Materials Science and Engineering, and Adjunct Professor of Aeronautics and Astronautics, University of Washington Accompanying Codes and Slides: https://composites.uw.edu/AI/ This video was produced at the University of Washington, and we acknowledge funding support from The Boeing Company. Keywords: Heat Transfer, Physics-Based Machine Learning, Physics-Informed Neural Network for Heat Transfer