We present a neural network-based method for solving linear and nonlinear partial differential equations, by combining the ideas of extreme learning machines (ELM), domain decomposition and local neural networks. The field solution on each sub-domain is represented by a local feed-forward neural network, and $C^k$ continuity is imposed on the sub-domain boundaries. Each local neural network consists of a small number of hidden layers, while its last hidden layer can be wide. The weight/bias coefficients in all hidden layers of the local neural networks are pre-set to random values and are fixed, and only the weight coefficients in the output layers are training parameters. The overall neural network is trained by a linear or nonlinear least squares computation, not by the back-propagation type algorithms. We introduce a block time-marching scheme together with the presented method for long-time dynamic simulations. The current method exhibits a clear sense of convergence with respect to the degrees of freedom in the neural network. Its numerical errors typically decrease exponentially or nearly exponentially as the number of degrees of freedom increases. Extensive numerical experiments have been performed to demonstrate the computational performance of the presented method. We compare the current method with the deep Galerkin method (DGM) and the physics-informed neural network (PINN) in terms of the accuracy and computational cost. The current method exhibits a clear superiority, with its numerical errors and network training time considerably smaller (typically by orders of magnitude) than those of DGM and PINN. We also compare the current method with the classical finite element method (FEM). The computational performance of the current method is on par with, and oftentimes exceeds, the FEM performance.
Eindhoven University of Technology(埃因霍温理工大学);Université de Toulouse(图卢兹大学);Delft University of Technology(代尔夫特理工大学);INP-ENSEEIHT(图卢兹国立综合理工学院ENSEEIHT);IRIT(计算机、机器人与电信研究所);ANITI(图卢兹人工智能与大数据研究所);CERFACS(欧洲计算流体研究中心);BRLi(生物信息学研究实验室)
A scalable space-time domain decomposition approach for solving large-scale nonlinear regularized inverse ill-posed problems in 4D variational data assimilation
A Proximal Decomposition Method for Solving Convex Variational Inverse Problems
UPMC Université Paris 06(巴黎第六大学);Laboratoire Jacques-Louis Lions – UMR 7598(雅克-路易·利翁斯实验室);Université Paris-Est(巴黎东大学);Institut Gaspard Monge and UMR CNRS 8049(加斯帕尔·蒙日研究所)
Deep Domain Decomposition Method for Solving the Variational Inequality Problems
School of Mathematics and Computing Science, Guilin University of Electronics Technology(桂林电子科技大学数学与计算科学学院);Center for Applied Mathematics of Guangxi (GUET)(广西应用数学中心)
Space-time Domain Decomposition and Mixed Formulation for solving reduced fracture models
INRIA Paris-Rocquencourt(法国国家信息与自动化研究所巴黎-罗盖特分校);Ho Chi Minh City University of Pedagogy(胡志明市师范大学);Université Paris 13, UMR 7539, LAGA(巴黎第十三大学,UMR 7539,LAGA实验室)
Neural Multiscale Decomposition for Solving The Nonlinear Klein-Gordon Equation with Time Oscillation
National Center for Applied Mathematics(应用数学国家研究中心);Tianjin University(天津大学);School of Mechanical and Aerospace Engineering, Jilin University(吉林大学机械与航空航天工程学院);Jilin University(吉林大学)
Stochastic domain decomposition for the solution of the two-dimensional magnetotelluric problem
Department of Mathematics and Statistics, Memorial University of Newfoundland(纪念大学数学与统计系);Department of Earth Sciences, Memorial University of Newfoundland(纪念大学地球科学系)