We're sorry but this page doesn't work properly without JavaScript enabled. Please enable it to continue.
Feedback

A hybrid physics-informed neural network based multiscale solver as a partial differential equation constrained optimization problem

Formal Metadata

Title
A hybrid physics-informed neural network based multiscale solver as a partial differential equation constrained optimization problem
Title of Series
Number of Parts
17
Author
License
CC Attribution 3.0 Germany:
You are free to use, adapt and copy, distribute and transmit the work or content in adapted or unchanged form for any legal purpose as long as the work is attributed to the author in the manner specified by the author or licensor.
Identifiers
Publisher
Release Date
Language

Content Metadata

Subject Area
Genre
Abstract
In this talk, we present physics-informed neural networks (PINNs) constrained by partial differential equations (PDEs) and their application in approximating multiscale PDEs. From a continuous perspective, our formulation corresponds to a non-standard PDE-constrained optimization problem with a PINN-type objective. From a discrete standpoint, the formulation represents a hybrid numerical solver that utilizes both neural networks and finite elements. In our setting, the neural network approximates a fine-scale problem, and a coarse-scale problem constrains the learning process. We show that incorporating coarse-scale information into the neural network training process through our modelling framework significantly enhances the overall learning process and results in improved convergence properties and accuracy of the PINN method. The mathematical framework for such a formulation, and the relevance of the hybrid solver to numerical homogenization are discussed.