Inverse Uncertainty Quantification with Machine Learning for Nuclear Reactor Simulations

with Xu Wu,
Assistant Professor of Nuclear Engineering, 
North Carolina State University

October 27, 2023, 10:10 am,
Foggy Bottom Room, VTRC, Arlington

Please register to access via zoom

The concept of Uncertainty Quantification (UQ) in the nuclear community generally means forward UQ, in which the information flow is from the inputs to the outputs. Inverse UQ, in which the information flow is from the model outputs and experimental data to the inputs, is an equally important component of UQ but has been significantly underrated until recently. In this seminar, we will present an inverse UQ methodology that quantifies the parameter uncertainties based on experimental data while taking into account all sources of quantifiable uncertainties from model, code and measurement. Machine learning approaches are widely used in this process for surrogate modeling and dimensionality reduction. The presentation will also include some work on UQ of deep neural network-based surrogate models.

Xu Wu is an Assistant Professor of Nuclear Engineering at North Carolina State University. Dr. Wu's main research interests include: uncertain quantification, Bayesian inverse problems, model discrepancy analysis, scientific machine learning and data-driven modeling. Dr. Wu received his BS in Nuclear Engineering from Shanghai Jiao Tong University in 2011 and PhD in Nuclear Engineering from University of Illinois at Urbana - Champaign in 2017. Prior to joining NC State in 2019, he worked as a Postdoctoral Research Associate at MIT.