Friday, May 5
10:00-10:30 a.m.

“Data-driven Computational Modeling of Complex Spatiotemporal Systems for Energy-related Systems”

Abstract

First-principle modeling and simulation of complex systems based on partial differential equations (PDEs) and numerical discretization have been developed for decades and achieved great success. Nonetheless, traditional numerical solvers face significant challenges in many practical scenarios, e.g., inverse problems, uncertainty quantification, design, and optimizations. Moreover, for complex systems, the governing equations might not be fully known due to a lack of complete understanding of the underlying physics, for which a first-principled numerical solver cannot be built. Recent advances in data science. and machine learning, combined with the ever-increasing availability of high-fidelity simulation and measurement data, open up new opportunities for developing data-enabled computational mechanics models. Although the state-of-the-art machine/deep learning techniques hold great promise, there are still many challenges - e.g., requirement of “big data”, the challenge in generalizability/extrapolibity, lack of interpretability/explainability, etc. On the other hand, there is often a richness of prior knowledge of the systems, including physical laws and phenomenological principles, which can be leveraged in this regard. Thus, there is an urgent need for fundamentally new and transformative machine learning techniques, closely grounded in physics, to address the aforementioned challenges in computational mechanics problems. This talk will briefly discuss our recent developments of scientific machine learning for computational physics, focusing on the integration of PDE operators into neural architecture to fuse prior knowledge of physics, multi-resolution data, numerical techniques, and neural network through differentiable programming.

Biography

Prof. Jian-Xun Wang joined the College of Engineering at the University of Notre Dame as an assistant professor in the Department of Aerospace and Mechanical Engineering in 2018. He received his bachelor degree in Naval Architecture and Ocean Engineering from the Harbin Institute of Technology in 2011 and completed his master’s program in Mechanical Engineering in 2013 from the same university. He joined the graduate program in the Department of Aerospace and Ocean Engineering at Virginia Tech in 2013 and received a master degree in Ocean Engineering and a Ph.D. degree in Aerospace Engineering in 2016 and 2017, respectively. Subsequently, he conducted postdoctoral research at the University of California, Berkeley. 

Prof. Wang has a multidisciplinary research background, cutting cross scientific machine learning, data assimilation, Bayesian inference, uncertainty quantification, and computational mechanics. In particular, his research focus is at the interface of physics-informed deep learning, data-driven modeling, scientific computing, and physics-based computational mechanics. He has (co-) led research projects sponsored by multiple agencies, including NSF, ONR, AFSOR, DARPA, CICP, etc. Dr. Wang received the 2021 NSF CAREER Award, 2023 ONR YIP Award, and the 2022 Top 10 Outstanding Chinese American Youth Award. Dr. Wang also serves on the editorial board of Nature Scientific Report, and he is a member-at-large of the US. Association of Computational Mechanics (USACM) Technical Thrust Area on Uncertainty Quantification and Technical Thrust Area on Data-Driven Modeling.

Relevant Energy Publications

1. Wang, Jian-Xun, Jin-Long Wu, and Heng Xiao. "Physics-informed machine learning approach for reconstructing Reynolds stress modeling discrepancies based on DNS data." Physical Review Fluids 2, no. 3 (2017): 034603.
2. Gao, Han, and Jian-Xun Wang. "A Bi-fidelity ensemble kalman method for PDE-constrained inverse problems in computational mechanics." Computational Mechanics 67, no. 4 (2021): 1115-1131.
3. Gao, Han, Luning Sun, and Jian-Xun Wang. "Super-resolution and denoising of fluid flow using physics-informed convolutional neural networks without high-resolution labels." Physics of Fluids 33, no. 7 (2021): 073603.
4. Liu, Xin-Yang, and Jian-Xun Wang. "Physics-informed Dyna-style model-based deep reinforcement learning for dynamic control." Proceedings of the Royal Society A 477, no. 2255 (2021): 20210618.
5. Xiao, Heng, J-L. Wu, J-X. Wang, Rui Sun, and C. J. Roy. "Quantifying and reducing model-form uncertainties in Reynolds-averaged Navier–Stokes simulations: A data-driven, physics-informed Bayesian approach." Journal of Computational Physics 324 (2016): 115-136.

Department Website
Group Website