Finite Basis Physics-Informed Neural Networks (FBPINNs): a scalable domain decomposition approach for solving differential equations

Abstract

Recently, physics-informed neural networks (PINNs) have offered a powerful new paradigm for solving problems relating to differential equations. Compared to classical numerical methods PINNs have several advantages, for example their ability to provide mesh-free solutions of differential equations and their ability to carry out forward and inverse modelling within the same optimisation problem. Whilst promising, a key limitation to date is that PINNs have struggled to accurately and efficiently solve problems with large domains and/or multi-scale solutions, which is crucial for their real-world application. Multiple significant and related factors contribute to this issue, including the increasing complexity of the underlying PINN optimisation problem as the problem size grows and the spectral bias of neural networks. In this work we propose a new, scalable approach for solving large problems relating to differential equations called Finite Basis PINNs (FBPINNs). FBPINNs are inspired by classical finite element methods, where the solution of the differential equation is expressed as the sum of a finite set of basis functions with compact support. In FBPINNs neural networks are used to learn these basis functions, which are defined over small, overlapping subdomains. FBINNs are designed to address the spectral bias of neural networks by using separate input normalisation over each subdomain, and reduce the complexity of the underlying optimisation problem by using many smaller neural networks in a parallel divide-and-conquer approach. Our numerical experiments show that FBPINNs are effective in solving both small and larger, multi-scale problems, outperforming standard PINNs in both accuracy and computational resources required, potentially paving the way to the application of PINNs on large, real-world problems.

27 pages, 13 figures

References in corpus (7)

• Fourier Features Let Networks Learn High Frequency Functions in Low Dimensional Domains
• Physics-Constrained Deep Learning for High-dimensional Surrogate Modeling and Uncertainty Quantification without Labeled Data
• Flow over an espresso cup: Inferring 3D velocity and pressure fields from tomographic background oriented schlieren videos via physics-informed neural networks
• Variational Physics-Informed Neural Networks For Solving Partial Differential Equations
• Understanding and mitigating gradient pathologies in physics-informed neural networks
• Solving the wave equation with physics-informed deep learning
• PyDEns: a Python Framework for Solving Differential Equations with Neural Networks

Cited by in corpus (32)

• Transfer learning based physics-informed neural networks for solving inverse problems in engineering structures under different loading scenarios
• Augmented Physics-Informed Neural Networks (APINNs): A gating network-based soft domain decomposition methodology
• Multilevel domain decomposition-based architectures for physics-informed neural networks
• A practical PINN framework for multi-scale problems with multi-magnitude loss terms
• Integrated Finite Element Neural Network (I-FENN) for non-local continuum damage mechanics
• Adaptive Training of Grid-Dependent Physics-Informed Kolmogorov-Arnold Networks
• Finite element interpolated neural networks for solving forward and inverse problems
• Rapid Seismic Waveform Modeling and Inversion with Neural Operators
• GaborPINN: Efficient physics informed neural networks using multiplicative filtered networks
• ViscoelasticNet: A physics informed neural network framework for stress discovery and model selection
• Learning Specialized Activation Functions for Physics-informed Neural Networks
• Physics-Informed Neural Networks for Parametric Compressible Euler Equations
• Enhancing training of physics-informed neural networks using domain-decomposition based preconditioning strategies
• Adapting Physics-Informed Neural Networks to Improve ODE Optimization in Mosquito Population Dynamics
• LordNet: An Efficient Neural Network for Learning to Solve Parametric Partial Differential Equations without Simulated Data
• A Practitioner's Guide to Kolmogorov-Arnold Networks
• Machine Learning in Acoustics: A Review and Open-Source Repository
• An overlapping domain decomposition method for the solution of parametric elliptic problems via proper generalized decomposition
• Geometry-aware framework for deep energy method: an application to structural mechanics with hyperelastic materials
• Meshfree Variational Physics Informed Neural Networks (MF-VPINN): an adaptive training strategy
• Physics-Informed Neural Networks for Transonic Flows around an Airfoil
• Neural Fields in Visual Computing and Beyond
• An operator preconditioning perspective on training in physics-informed machine learning
• Seismic wave propagation and inversion with Neural Operators
• A Nonoverlapping Domain Decomposition Method for Extreme Learning Machines: Elliptic Problems
• Gradient Flow Based Phase-Field Modeling Using Separable Neural Networks
• An approximate Riemann solver approach in Physics-Informed Neural Networks for hyperbolic conservation laws
• Accelerated Gradient-based Design Optimization Via Differentiable Physics-Informed Neural Operator: A Composites Autoclave Processing Case Study
• A Neumann-Neumann Acceleration with Coarse Space for Domain Decomposition of Extreme Learning Machines
• PGD-based local surrogate models via overlapping domain decomposition: a computational comparison
• Transforming physics-informed machine learning to convex optimization
• A physics-informed neural network approach to the point defect model for electrochemical oxide film growth