About

Paris Perdikaris is an Associate Professor of Mechanical Engineering and Applied Mechanics at the University of Pennsylvania, where he also directs the Predictive Intelligence Lab. His research is at the global forefront of AI for Science, specifically in the development of Physics-Informed Machine Learning (PIML). Dr. Perdikaris is a co-creator of Physics-Informed Neural Networks (PINNs), a transformative deep learning framework that embeds the laws of physics—typically expressed as partial differential equations—directly into neural network architectures to solve complex forward and inverse engineering problems. His current work focuses on building Foundation Models for physical systems, utilizing Neural Operators (such as DeepONets) to accelerate multi-scale simulations in fluid dynamics, climate modeling, and materials science. A key pillar of his methodology is Uncertainty Quantification, where he employs Bayesian inference and probabilistic programming to ensure that AI-driven scientific discoveries are both reliable and physically consistent.

Research Performance Summary

Last 10 Years Publication Activity

This timeline shows the professor's yearly publication activity.

Publication Venues and Collaboration

Research Impact by Period

Contact and Professional Links

Detected Research Keywords