I am currently a Postdoctoral Research Associate in the Computational Mathematics group at Pacific Northwest National Laboratory (PNNL), WA, where I work on the project “High-Dimensional Model Inversion and Uncertainty Quantification for Complex Systems.” My research expertise lies at the intersection of Bayesian inference, structural dynamics, and machine learning, with a strong focus on model updating and uncertainty quantification for large-scale engineering systems.

Prior to joining PNNL, I completed a two-year postdoctoral fellowship at CERL group under the supervision of Prof. Zhen Hu. During this time, I participated in multiple projects involving machine learning, structural health monitoring, and vehicle crashworthiness design, collaborating with industry partners such as Ford Motor Company and the U.S. Army.

I hold a Ph.D. in Civil and Environmental Engineering (Structural Engineering) from the University of Louisville, advised by Prof. Young Hoon Kim. My dissertation focused on integrating data-driven modal analysis with Bayesian inference for hybrid structural health monitoring. I also hold a Master degree in Bridge Engineering from Chongqing Jiaotong University and a Bachelor degree from Xihua University.

If you want to work with me as a collaborator, instructor, or public speaker, please feel free to contact me: patrickjice@gmail.com.

Research Interests

• Strcutural Health Monitoring (SHM)
• Probabilistic Damage Diagnosis, Prognostics, and Stochastic Model Updating
• Bayesian Inference, Likelihood-Free Inference, and Uncertainty Quantification
• Deep Generative Modeling for SHM and Model Updating
• Machine Learning-Enabled High-Dimensional Surrogate Model and Model Inversion Tasks
• Operational Modal Analysis and Uncertainty Quantification

News

• [Sept 2024] Our abstact was accepted by AGU Fall Annual Meeting 2024. I will be presenting my research ‘Solving High-dimensional inverse problems using amortized likelihood-free-inference and Karhunen–Loève expansions’ in December in Washington, D.C.
• [Sept 2024] Our paper ‘Model Uncertainty Quantification of a Degradation Model of Miter Gates Using Normalizing Flow-based Likelihood-free Inference’ was accepted by journal Structural Health Monitoring.
• [Sept 2024] Our paper ‘A Comparative Study of Single-chain and Multi-chain MCMC Algorithms for Bayesian Model Updating-Based Structural Damage Detection’ was accepted by Applied Sciences.
• [Agu 2024] Our paper ‘Fusion of Multiple Data Sources for Vehicle Crashworthiness Prediction Using CycleGAN and Temporal Convolutional Networks’ was accepted by Journal of Mechanical Design.
• [Jun 2024] Our paper ‘Data Augmentation Based on Image Translation for Bayesian Inference-Based Damage Diagnostics of Miter Gates’ was accepted by the ASCE-ASME Journal of Risk and Uncertainty in Engineering Systems, Part B: Mechanical Engineering.
• [Jun 2024] Our paper ‘Bayesian Model Updating of Multiscale Simulations Informing Corrosion Prognostics Using Conditional Invertible Neural Networks’ was accepted by the ASCE-ASME Journal of Risk and Uncertainty in Engineering Systems, Part B: Mechanical Engineering.