Conditionally Parameterized, Discretization-Aware Neural Networks for Mesh-Based Modeling of Physical Systems

09/15/2021
by   Jiayang Xu, et al.
7

Simulations of complex physical systems are typically realized by discretizing partial differential equations (PDEs) on unstructured meshes. While neural networks have recently been explored for surrogate and reduced order modeling of PDE solutions, they often ignore interactions or hierarchical relations between input features, and process them as concatenated mixtures. We generalize the idea of conditional parameterization – using trainable functions of input parameters to generate the weights of a neural network, and extend them in a flexible way to encode critical information. Inspired by discretized numerical methods, choices of the parameters include physical quantities and mesh topology features. The functional relation between the modeled features and the parameters is built into the network architecture. The method is implemented on different networks and applied to frontier scientific machine learning tasks including the discovery of unmodeled physics, super-resolution of coarse fields, and the simulation of unsteady flows with chemical reactions. The results show that the conditionally-parameterized networks provide superior performance compared to their traditional counterparts. The CP-GNet - an architecture that can be trained on very few data snapshots - is proposed as the first deep learning model capable of standalone prediction of reacting flows on irregular meshes.

READ FULL TEXT

page 9

page 14

page 15

page 16

page 17

page 18

page 19

research
01/21/2020

Learning to Control PDEs with Differentiable Physics

Predicting outcomes and planning interactions with the physical world ar...
research
10/07/2020

Learning Mesh-Based Simulation with Graph Networks

Mesh-based simulations are central to modeling complex physical systems ...
research
06/16/2020

Multipole Graph Neural Operator for Parametric Partial Differential Equations

One of the main challenges in using deep learning-based methods for simu...
research
12/06/2022

RBF-MGN:Solving spatiotemporal PDEs with Physics-informed Graph Neural Network

Physics-informed neural networks (PINNs) have lately received significan...
research
09/14/2021

Non-linear Independent Dual System (NIDS) for Discretization-independent Surrogate Modeling over Complex Geometries

Numerical solutions of partial differential equations (PDEs) require exp...
research
06/11/2020

Enabling Nonlinear Manifold Projection Reduced-Order Models by Extending Convolutional Neural Networks to Unstructured Data

We propose a nonlinear manifold learning technique based on deep autoenc...

Please sign up or login with your details

Forgot password? Click here to reset