A domain decomposition-based autoregressive deep learning model for unsteady and nonlinear partial differential equations

TL;DR

This paper introduces a domain decomposition-based deep learning framework, transient-CoMLSim, for modeling unsteady, nonlinear PDEs, combining autoencoders and autoregressive models to improve scalability, accuracy, and stability in large-scale simulations.

Contribution

The novel framework employs domain decomposition with CNN autoencoders and autoregressive modeling, enabling scalable, accurate, and stable predictions for complex PDEs beyond existing methods.

Findings

Outperforms FNO and U-Net in accuracy and stability.

Effective in extrapolating to unseen timesteps.

Scales well to larger, out-of-distribution domains.

Abstract

In this paper, we propose a domain-decomposition-based deep learning (DL) framework, named transient-CoMLSim, for accurately modeling unsteady and nonlinear partial differential equations (PDEs). The framework consists of two key components: (a) a convolutional neural network (CNN)-based autoencoder architecture and (b) an autoregressive model composed of fully connected layers. Unlike existing state-of-the-art methods that operate on the entire computational domain, our CNN-based autoencoder computes a lower-dimensional basis for solution and condition fields represented on subdomains. Timestepping is performed entirely in the latent space, generating embeddings of the solution variables from the time history of embeddings of solution and condition variables. This approach not only reduces computational complexity but also enhances scalability, making it well-suited for large-scale simulations. Furthermore, to improve the stability of our rollouts, we employ a curriculum learning (CL) approach during the training of the autoregressive model. The domain-decomposition strategy enables scaling to out-of-distribution domain sizes while maintaining the accuracy of predictions -- a feature not easily integrated into popular DL-based approaches for physics simulations. We benchmark our model against two widely-used DL architectures, Fourier Neural Operator (FNO) and U-Net, and demonstrate that our framework outperforms them in terms of accuracy, extrapolation to unseen timesteps, and stability for a wide range of use cases.