DeepAI AI Chat
Log In Sign Up

Semi-Implicit Neural Solver for Time-dependent Partial Differential Equations

by   Suprosanna, et al.
Universität Zürich
Cole Normale Suprieure
Technische Universität München
Harvard University

Fast and accurate solutions of time-dependent partial differential equations (PDEs) are of pivotal interest to many research fields, including physics, engineering, and biology. Generally, implicit/semi-implicit schemes are preferred over explicit ones to improve stability and correctness. However, existing semi-implicit methods are usually iterative and employ a general-purpose solver, which may be sub-optimal for a specific class of PDEs. In this paper, we propose a neural solver to learn an optimal iterative scheme in a data-driven fashion for any class of PDEs. Specifically, we modify a single iteration of a semi-implicit solver using a deep neural network. We provide theoretical guarantees for the correctness and convergence of neural solvers analogous to conventional iterative solvers. In addition to the commonly used Dirichlet boundary condition, we adopt a diffuse domain approach to incorporate a diverse type of boundary conditions, e.g., Neumann. We show that the proposed neural solver can go beyond linear PDEs and applies to a class of non-linear PDEs, where the non-linear component is non-stiff. We demonstrate the efficacy of our method on 2D and 3D scenarios. To this end, we show how our model generalizes to parameter settings, which are different from training; and achieves faster convergence than semi-implicit schemes.


page 9

page 12


Implicit Neural Solver for Time-dependent Linear PDEs with Convergence Guarantee

Fast and accurate solution of time-dependent partial differential equati...

Learning Neural PDE Solvers with Convergence Guarantees

Partial differential equations (PDEs) are widely used across the physica...

High order semi-implicit multistep methods for time dependent partial differential equations

We consider the construction of semi-implicit linear multistep methods w...

Stability of implicit neural networks for long-term forecasting in dynamical systems

Forecasting physical signals in long time range is among the most challe...

A new reduced order model of linear parabolic PDEs

How to build an accurate reduced order model (ROM) for multidimensional ...

Multigrid Solver With Super-Resolved Interpolation

The multigrid algorithm is an efficient numerical method for solving a v...