Academics

Learning Nonlocal Constitutive Models with Neural Operators

Time:2022-12-22 Thu 10:00-11:30

Venue:Venue: 1129B Zoom: 537 192 5549(PW: BIMSA)

Organizer:Fansheng Xiong, Wuyue Yang, Wen-An Yong, Yi Zhu

Speaker:Jiequn Han Center for Computational Mathematics, Flatiron Institute, Simons Foundation

Abstract

Constitutive models are widely used for modeling complex systems in science and engineering, when first-principle-based, well-resolved simulations are prohibitively expensive. For example, in fluid dynamics, constitutive models are required to describe nonlocal, unresolved physics such as turbulence and laminar-turbulent transition. However, traditional constitutive models based on PDEs often lack robustness and are too rigid to accommodate diverse calibration datasets. We propose a frame-independent, nonlocal constitutive model based on a vector-cloud neural network that represents the physics of PDEs and meanwhile can be learned with data. The proposed model can be interpreted as a neural operator, which by design, respects all the invariance properties desired by constitutive models, faithfully reflects the region of influence in physics, and is applicable to different spatial resolutions. We demonstrate its performance on modeling the Reynolds stress for Reynolds-averaged Navier--Stokes (RANS) equations in two situations: (1) emulating the Reynolds stress transport model through synthetic data and (2) calibrating the Reynolds stress through data from direct numerical simulations. Our results show that the proposed neural operator is a promising alternative to traditional nonlocal constitutive models and paves the way for developing robust and nonlocal, non-equilibrium closure models for the RANS equations.


Speaker Intro

Jiequn Han is a Research Fellow in the Center for Computational Mathematics, Flatiron Institute, Simons Foundation. His research draws inspiration from various disciplines of science and is devoted to solving high-dimensional problems arising from scientific computing. His current research interests mainly focus on solving high-dimensional partial differential equations and machine learning based-multiscale modeling. He holds a Ph.D. in Applied Mathematics from Princeton University, a B.S. in Computational Mathematics and a B.A. in Economics from Peking University.

DATEDecember 22, 2022
SHARE
Related News
    • 0

      Learning constitutive models with neural networks

      AbstractIn this talk, I will introduce some work of learning constitutive equations in fluid mechanics and geophysics based on machine learningSpeaker Intro熊繁升,现任北京雁栖湖应用数学研究院助理研究员,曾任北京应用物理与计算数学研究所所聘博士后。先后毕业于中国地质大学(北京)、清华大学,美国耶鲁大学联合培养博士。研究兴趣主要集中于基于机器学习算法(DNN、PINN、DeepONet等)求解微分方程模型正/反问题...

    • 1

      [BIMSA-Tsinghua Seminar on Machine Learning and Differential Equations] From Neural PDEs to Neural Operators: Blending data and physics for fast predictions

      Abstract:We will review physics-informed neural network and summarize available extensions for applications in computational mechanics and beyond. We will also introduce new NNs that learn functionals and nonlinear operators from functions and corresponding responses for system identification. The universal approximation theorem of operators is suggestive of the potential of NNs in learning fro...