With the recent study of deep learning in scientific computation, the Physics-Informed Neural Networks (PINNs) method has drawn widespread attention for solving Partial Differential Equations (PDEs). Compared to traditional methods, PINNs can efficiently handle high-dimensional problems, but the accuracy is relatively low, especially for highly irregular problems. Inspired by the idea of adaptive finite element methods and incremental learning, we propose GAS, a Gaussian mixture distribution-based adaptive sampling method for PINNs. During the training procedure, GAS uses the current residual information to generate a Gaussian mixture distribution for the sampling of additional points, which are then trained together with historical data to speed up the convergence of the loss and achieve higher accuracy. Several numerical simulations on 2D and 10D problems show that GAS is a promising method that achieves state-of-the-art accuracy among deep solvers, while being comparable with traditional numerical solvers.
PINN Balls: Scaling Second-Order Methods for PINNs with Domain Decomposition and Adaptive Sampling
BMW AG, Digital Campus Munich(宝马集团慕尼黑数字园区);University of Göttingen(哥廷根大学);Basque Center for Applied Mathematics(巴斯克应用数学中心);Campus Institute Data Science(数据科学校园研究所);University of the Basque Country(巴斯克大学);Intelligent Systems Group(智能系统研究组);IKERBASQUE, Basque Foundation for Science(巴斯克科学基金会);Swansea University(斯旺西大学)
Partition of Unity Physics-Informed Neural Networks (POU-PINNs): An Unsupervised Framework for Physics-Informed Domain Decomposition and Mixtures of Experts
The University of Texas at El Paso(德克萨斯大学埃尔帕索分校);University of California, Santa Cruz(加州大学圣克鲁兹分校);Clarkson University(克拉克森大学);Texas A&M University in Kingsville(德克萨斯农工大学金斯维尔分校)
Energy Dissipation Rate Guided Adaptive Sampling for Physics-Informed Neural Networks: Resolving Surface-Bulk Dynamics in Allen-Cahn Systems
Department of Mathematics, The Pennsylvania State University(数学系,宾夕法尼亚州立大学);Department of Mathematics, The Hong Kong University of Science and Technology(数学系,香港科学与技术大学);Department of Mathematics, University of South Carolina(数学系,南卡罗来纳大学)
Efficient Global-Local Fusion Sampling for Physics-Informed Neural Networks
School of Mathematical Sciences, Soochow University(苏州大学数学科学学院);Zu Chongzhi Center , Duke Kunshan University(杜克昆山学院钟楚中心);University of Science and Technology of China(中国科学技术大学);Key Laboratory of the Ministry of Education for Mathematical Foundations and Applications of Digital Technology(教育部数学基础与应用数字技术重点实验室)
Evaluation of Sampling Strategies and Physics-Informed Kolmogorov--Arnold Networks in Unbounded Domains
Mathematical Applications in Science and Engineering, School of Applied Sciences and Engineering, Universidad EAFIT, Medellín, Colombia(科学与工程数学应用,应用科学与工程学院,埃法伊特大学,梅德林,哥伦比亚);Nature and City, School of Applied Sciences and Engineering, Universidad EAFIT, Medellín, Colombia(自然与城市,应用科学与工程学院,埃法伊特大学,梅德林,哥伦比亚)
School of Mathematical Sciences, Shanghai Jiao Tong University, Shanghai 200240, China(上海交通大学数学科学学院);Department of Mathematics, University of Massachusetts Dartmouth, North Dartmouth, MA 02747(大学马萨诸塞州达特茅斯分校数学系);Department of Chemical and Biomolecular Engineering, University of Pennsylvania, Philadelphia, PA 19104, United States of America(宾夕法尼亚大学化学与生物分子工程系)
Architecture--Optimization Co-Design for Physics-Informed Neural Networks via Layer-wise Coordinate Adaptation and Gradient Conflict Resolution
College of Applied Mathematics(应用数学学院);Chengdu University of Information Technology(成都信息科技大學);College of Mathematics(数学学院);Sichuan University(四川大学);School of Sciences(科学学院)
Learning characteristic parameters and dynamics of centrifugal pumps under multiphase flow using physics-informed neural networks
Faculdade de Engenharia Mecânica (FEM), Universidade Estadual de Campinas (UNICAMP)(坎皮纳斯州立大学机械工程学院);Centro de Estudos de Energia e Petróleo (CEPETRO), Universidade Estadual de Campinas (UNICAMP)(坎皮纳斯州立大学能源与石油研究中心);Division of Applied Mathematics, Brown University(布朗大学应用数学系);School of Engineering, Brown University(布朗大学工程学院)
An Imbalanced Learning-based Sampling Method for Physics-informed Neural Networks
The Fields Institute for Research in Mathematical Sciences(数学科学菲尔兹研究所);Pennsylvania State University(宾夕法尼亚州立大学);Data Science Research Center, Duke Kunshan University(昆山杜克大学数据科学研究中心);Zu Chongzhi Center for Mathematics and Computational Sciences, Duke Kunshan University(昆山杜克大学祖冲之数学与计算科学中心)
Characterization of partial wetting by CMAS droplets using multiphase many-body dissipative particle dynamics and data-driven discovery based on PINNs
The University of Western Ontario(西安大略大学);Cold Spring Harbor Laboratory(冷泉港实验室);Brown University(布朗大学);University of Maryland(马里兰大学);Clemson University(克莱姆森大学);US Army Research Laboratory(美国陆军研究实验室)
LNN-PINN: A Unified Physics-Only Training Framework with Liquid Residual Blocks
Nanophotonics and Biophotonics Key Laboratory of Jilin Province, School of Physics, Changchun University of Science and Technology(吉林省纳米光子与生物光子重点实验室,物理学院,长春理工大学);Faculty of Chinese Medicine, Macau University of Science and Technology(澳门科技大学中医药学院)
Dynamical Measure Transport and Neural PDE Solvers for Sampling
California Institute of Technology(加州理工学院);Zuse Institute Berlin(柏林祖斯研究所);dida Datenschmiede GmbH(迪达数据 Schmiede 有限公司);Simula Research Laboratory(西穆拉研究实验室);University Hospital Freiburg(弗赖堡大学医院);RWTH Aachen(亚琛工业大学);NVIDIA(英伟达)
Integral regularization PINNs for evolution equations
Faculty of Science and Technology(科学与技术学院);Beijing Normal-Hong Kong Baptist University(北京师范大学-香港 Baptist大学);School of Mathematics and Statistics(数学与统计学学院);Guangzhou Nanfang College(广州南芳学院);Zhuhai SimArk Technology Co., LTD(珠海SimArk科技有限公司);Department of Mathematics and Center for Computation and Technology(数学系与计算技术中心);Louisiana State University(路易斯安那州立大学)
Physics-informed Neural Networks-based Model Predictive Control for Multi-link Manipulators
University of Stuttgart(斯图加特大学);Stuttgart Center for Simulation Science (SimTech)(斯图加特模拟科学中心);Institute of Engineering and Computational Mechanics(工程与计算力学研究所)
High precision PINNs in unbounded domains: application to singularity formulation in PDEs
California Institute of Technology(加州理工学院);Massachusetts Institute of Technology(麻省理工学院);The NSF Institute for Artificial Intelligence and Fundamental Interactions(NSF人工智能与基础相互作用研究所)
Stochastic Dimension Implicit Functional Projections for Global Integral Conservation in High-Dimensional PINNs
National Center for Applied Mathematics, Tianjin University, China(应用数学国家中心,天津大学,中国);School of Mechanical and Aerospace Engineering, Jilin University, China(机械与 aerospace 工程学院,吉林大学,中国)