Xu Wu

Assistant Professor of Nuclear Engineering

Dr. Wu received his B.S. degree in nuclear engineering from the Shanghai Jiao Tong University in China in 2011. He obtained his Ph.D. degree in nuclear engineering in 2017 from the University of Illinois at Urbana – Champaign. Prior to joining NCSU, he was a Postdoctoral Research Associate in the Department of Nuclear Science and Engineering at Massachusetts Institute of Technology. Dr. Wu is the principal investigator (PI) of the ARTISANS (ARTificial Intelligence for Simulation of Advanced Nuclear Systems) research group at NCSU-NE. The research in the ARTISANS group revolves around uncertainty quantification (UQ) and scientific machine learning (SciML). The goal is to combine SciML, experimentation and modeling & simulation (M&S) into a unified approach to improve the predictive capabilities of computer models and enable reduced reliance on expensive measurement data. Additionally, the application of such research will be focused on risk and economics evaluations of advanced nuclear reactors, such as small modular reactors and micro-reactors. The ultimate goal is to dramatically reduce the capital and operating costs of nuclear systems to maintain global technology leadership for nuclear energy.

Education

B.S. 2011

Nuclear Engineering

Shanghai Jiao Tong University

M.S. 2013

Nuclear, Plasma and Radiological Engineering

University of Illinois at Urbana - Champaign

Ph.D. 2017

Nuclear, Plasma and Radiological Engineering

University of Illinois at Urbana - Champaign

Postdoc 2019

Nuclear Science and Engineering

Massachusetts Institute of Technology

Research Description

Dr. Wu's research interests include: (1) calibration, validation, data assimilation, uncertainty and sensitivity analysis; (2) computational statistics, reduced order modeling; (3) Bayesian inverse problems; (4) scientific machine learning and deep generative learning; (5) system thermal-hydraulics, nuclear fuel performance modeling, multi-physics coupled simulation; (6) advanced reactors, small modular reactors, micro-reactors.

Publications

Functional PCA and deep neural networks-based Bayesian inverse uncertainty quantification with transient experimental data
Xie, Z., Yaseen, M., & Wu, X. (2024), COMPUTER METHODS IN APPLIED MECHANICS AND ENGINEERING, 420. https://doi.org/10.1016/j.cma.2023.116721
Deep generative modeling-based data augmentation with demonstration using the BFBT benchmark void fraction datasets
Alsafadi, F., & Wu, X. (2023), NUCLEAR ENGINEERING AND DESIGN, 415. https://doi.org/10.1016/j.nucengdes.2023.112712
Inverse Uncertainty Quantification by Hierarchical Bayesian Modeling and Application in Nuclear System Thermal-Hydraulics Codes
Wang, C., Wu, X., & Kozlowski, T. (2023). , (ArXiv Preprint No. 2305.16622). https://doi.org/10.48550/arXiv.2305.16622
Prediction and uncertainty quantification of SAFARI-1 axial neutron flux profiles with neural networks
Moloko, L. E., Bokov, P. M., Wu, X., & Ivanov, K. N. (2023), ANNALS OF NUCLEAR ENERGY, 188. https://doi.org/10.1016/j.anucene.2023.109813
Scalable Inverse Uncertainty Quantification by Hierarchical Bayesian Modeling and Variational Inference
Wang, C., Wu, X., Xie, Z., & Kozlowski, T. (2023), ENERGIES, 16(22). https://doi.org/10.3390/en16227664
Bayesian inverse uncertainty quantification of a MOOSE-based melt pool model for additive manufacturing using experimental data
Xie, Z., Jiang, W., Wang, C., & Wu, X. (2022), ANNALS OF NUCLEAR ENERGY, 165. https://doi.org/10.1016/j.anucene.2021.108782
Quantification of Deep Neural Network Prediction Uncertainties for VVUQ of Machine Learning Models
Yaseen, M., & Wu, X. (2022, November 4), NUCLEAR SCIENCE AND ENGINEERING, Vol. 11. https://doi.org/10.1080/00295639.2022.2123203
A comprehensive survey of inverse uncertainty quantification of physical model parameters in nuclear system thermal-hydraulics codes
Wu, X., Xie, Z., Alsafadi, F., & Kozlowski, T. (2021), NUCLEAR ENGINEERING AND DESIGN, 384. https://doi.org/10.1016/j.nucengdes.2021.111460
Application of Kriging and Variational Bayesian Monte Carlo method for improved prediction of doped UO2 fission gas release
Che, Y., Wu, X., Pastore, G., Li, W., & Shirvan, K. (2021), ANNALS OF NUCLEAR ENERGY, 153. https://doi.org/10.1016/j.anucene.2020.108046
Enhancing the One-Dimensional SFR Thermal Stratification Model via Advanced Inverse Uncertainty Quantification Methods
Lu, C., Wu, Z., & Wu, X. (2021), Nuclear Technology, 10, 1–19. https://doi.org/10.1080/00295450.2020.1805259

View all publications via NC State Libraries

View publications on Google Scholar

Grants

Using Machine Learning to Predict Locations with Crud Buildup
Consortium for Nuclear Power (CNP)(7/01/22 - 6/30/23)
Statistical Approaches to Reduce Uncertainty in PSHA, CNEFS Enhancement Project
Electricite de France (EDF/DER)(1/01/23 - 12/31/23)
Probabilistic and AI/ML Approaches in Structural Engineering, CNEFS Core Project
NCSU Center for Nuclear Energy Facilities and Structures (CNEFS)(1/01/22 - 12/31/23)
COBRA-TF (CTF) Modeling Applicable to High Burnup High Enrichment (HBHE) Fuel
US Dept. of Energy (DOE)(3/22/22 - 8/31/23)
Artificial Intelligence Based Process Control and Optimization for Advanced Manufacturing
US Dept. of Energy (DOE)(11/08/21 - 9/30/23)
Development of PINN for AM optimization
US Dept. of Energy (DOE)(1/06/20 - 9/30/20)