Inverse Uncertainty Quantification with Machine Learning for Nuclear Reactor Simulations

Speaker: Dr. Xu Wu, Assistant Professor, North Carolina State University

A brief abstract of presentation:  Uncertainty Quantification (UQ) is an essential step in computational model validation because assessment of the model accuracy requires a concrete, quantifiable measure of uncertainty in the model predictions. The concept of 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. Forward UQ requires knowledge in the input uncertainties which has been specified by expert opinion or user self-evaluation. Inverse UQ is defined as the process to inversely quantify the input uncertainties based on experimental data.
In this seminar, we will present an inverse UQ methodology that quantifies the parameter uncertainties based on experimental data while taking into account uncertainties from model, code and measurement. We will also introduce a comprehensive framework that integrates inverse UQ and quantitative Bayesian validation to improve prediction while accounting for all major sources of quantifiable uncertainties in modeling and simulation. This framework leverages supervised machine learning to reduce the computational cost and unsupervised machine learning for dimensionality reduction. A few applications will be demonstrated on system thermal-hydraulics code TRACE and fuel performance code BISON.

A brief bio: Dr. Xu Wu is an Assistant Professor of Nuclear Engineering at North Carolina State University. His research interests include Uncertainty Quantification, Sensitivity Analysis, Calibration, Validation and Scientific Machine Learning. Dr. Wu received his PhD degree in Nuclear Engineering from University of Illinois at Urbana – Champaign in 2017. Prior to joining NC State in 2019, he was a Postdoctoral Research Associate at Massachusetts Institute of Technology.