NEUP CINR-24-31807: Concurrent Surrogate Model Development with Uncertainty Quantification in the MOOSE Framework Using Physics-Informed Gaussian-Process Machine Learning

The objective of this project is to develop a general capability for concurrent generation and use of physics-informed Gaussian process (GP)-based surrogate models to facilitate multiscale and multiphysics modeling. We will implement this new capability as part of the Multiphysics Object-Oriented Simulation Environment (MOOSE) so that every application based on the MOOSE framework will have access to it.

Additional Info

Field	Value
Awarded Institution	University of Florida
PI	Michael Tonks