Meta-PDE: Learning to Solve PDEs Quickly Without a Mesh

11/03/2022
by   Tian Qin, et al.
0

Partial differential equations (PDEs) are often computationally challenging to solve, and in many settings many related PDEs must be be solved either at every timestep or for a variety of candidate boundary conditions, parameters, or geometric domains. We present a meta-learning based method which learns to rapidly solve problems from a distribution of related PDEs. We use meta-learning (MAML and LEAP) to identify initializations for a neural network representation of the PDE solution such that a residual of the PDE can be quickly minimized on a novel task. We apply our meta-solving approach to a nonlinear Poisson's equation, 1D Burgers' equation, and hyperelasticity equations with varying parameters, geometries, and boundary conditions. The resulting Meta-PDE method finds qualitatively accurate solutions to most problems within a few gradient steps; for the nonlinear Poisson and hyper-elasticity equation this results in an intermediate accuracy approximation up to an order of magnitude faster than a baseline finite element analysis (FEA) solver with equivalent accuracy. In comparison to other learned solvers and surrogate models, this meta-learning approach can be trained without supervision from expensive ground-truth data, does not require a mesh, and can even be used when the geometry and topology varies between tasks.

READ FULL TEXT

page 6

page 7

page 8

page 13

research
02/16/2023

Meta-Auto-Decoder: A Meta-Learning Based Reduced Order Model for Solving Parametric Partial Differential Equations

Many important problems in science and engineering require solving the s...
research
10/27/2020

Meta-MgNet: Meta Multigrid Networks for Solving Parameterized Partial Differential Equations

This paper studies numerical solutions for parameterized partial differe...
research
10/23/2022

Meta Learning of Interface Conditions for Multi-Domain Physics-Informed Neural Networks

Physics-informed neural networks (PINNs) are emerging as popular mesh-fr...
research
10/21/2019

Learning and Meta-Learning of Stochastic Advection-Diffusion-Reaction Systems from Sparse Measurements

Physics-informed neural networks (PINNs) were recently proposed in [1] a...
research
06/07/2022

Deep Convolutional Ritz Method: Parametric PDE surrogates without labeled data

Parametric surrogate models for partial differential equations (PDEs) ar...
research
11/07/2022

Neural PDE Solvers for Irregular Domains

Neural network-based approaches for solving partial differential equatio...
research
05/13/2020

Learning Composable Energy Surrogates for PDE Order Reduction

Meta-materials are an important emerging class of engineered materials i...

Please sign up or login with your details

Forgot password? Click here to reset