PIMS Lunchbox Lecture - Vakhtang Putkaradze
Topic
Physics-Informed Neural Networks - How they work, when they work, and when they fail.
Speakers
Details
Abstract: Recently, Machine Learning (ML) approaches to data assimilation and modeling have been very successful in interpreting large amounts of data, such as human behavior prediction, marketing, etc. However, direct applications of machine learning methods without understanding the underlying engineering and physics can be challenging. This happens because, on the one hand, the datasets may be too small for the application of ML methods suitable for large data, while, on the other hand, the reliability and accuracy of the pure ML-based prediction may not be acceptable in high-responsibility industrial settings. To address some of these problems, the Physics Informed Neural Networks (PINNs) have been developed. PINNs incorporate learning on the data and match the differential equations and boundary conditions describing the system. PINNs may be superior to standard ML methods in constructing digital twins of engineering problems and operating on small datasets. PINNs have been used successfully in many industrial and scientific applications due to their unmatched computational speed and efficiency.
The use of PINNs relies on the knowledge of mathematics, physics, and engineering underlying the particular problem and the understanding of how to implement PINNs successfully. We discuss some of the successes of PINNs, together with some of the cautionary tales regarding their applications.
Additional Information
Prof. Vakhtang Putkaradze received his PhD at the University of Copenhagen, Denmark, and held faculty positions in New Mexico, Colorado State University, and, most recently, at the University of Alberta, where he was a Centennial Professor between 2012-2019. From 2019 to 2022, he led the science and tech part of the Transformation Team at ATCO Ltd, first as a Senior Director and then as a Vice-President. He is now back to the University of Alberta, where he is currently researching applications of mathematical methods to neural networks. His main topic of interest is using mathematical methods in mechanics and various applications, including satellites, fluids, molecules and other fields. He has received numerous prizes and awards for research and teaching, including Humboldt Fellowship, Senior JSPS fellowship, CAIMS-Fields industrial math prize and G. I. Zaslavsky prize.