nPINNs: Nonlocal physics-informed neural networks for a parametrized nonlocal universal Laplacian operator. Algorithms and applications

JOURNAL OF COMPUTATIONAL PHYSICS

卷:422

Article

Pang, G.¹  D'Elia, M.²  Parks, M.³  Karniadakis, G. E.¹ 

[1] Brown Univ, Div Appl Math, Providence, RI 02912 USA

[2] Sandia Natl Labs, Computat Sci & Anal, Livermore, CA 94550 USA

[3] Sandia Natl Labs, Ctr Comp Res, Albuquerque, NM 87185 USA

关键词: Nonlocal models;    Deep learning;    Fractional Laplacian;    Physics-informed neural networks;    Turbulence modeling;   

DOI  :  10.1016/j.jcp.2020.109760

来源: Elsevier

【 摘 要 】

Physics-informed neural networks (PINNs) are effective in solving inverse problems based on differential and integro-differential equations with sparse, noisy, unstructured, and multi-fidelity data. PINNs incorporate all available information, including governing equations (reflecting physical laws), initial-boundary conditions, and observations of quantities of interest, into a loss function to be minimized, thus recasting the original problem into an optimization problem. In this paper, we extend PINNs to parameter and function inference for integral equations such as nonlocal Poisson and nonlocal turbulence models, and we refer to them as nonlocal PINNs (nPINNs). The contribution of the paper is three-fold. First, we propose a unified nonlocal Laplace operator, which converges to the classical Laplacian as one of the operator parameters, the nonlocal interaction radius goes to zero, and to the fractional Laplacian as delta goes to infinity. This universal operator forms a super-set of classical Laplacian and fractional Laplacian operators and, thus, has the potential to fit a broad spectrum of data sets. We provide theoretical convergence rates with respect to delta and verify them via numerical experiments. Second, we use nPINNs to estimate the two parameters, delta and alpha, characterizing the kernel of the unified operator. The strong non-convexity of the loss function yielding multiple (good) local minima reveals the occurrence of the operator mimicking phenomenon, that is, different pairs of estimated parameters could produce multiple solutions of comparable accuracy. Third, we propose another nonlocal operator with spatially variable order alpha(y), which is more suitable for modeling wall-bounded turbulence, e.g. turbulent Couette flow. Our results show that nPINNs can jointly infer this function as well as delta. More importantly, these parameters exhibit a universal behavior with respect to the Reynolds number, a finding that contributes to our understanding of nonlocal interactions in wall-bounded turbulence. (C) 2020 Elsevier Inc. All rights reserved.

【 授权许可】

Free