PhyCRNet: Physics-informed Convolutional-Recurrent Network for Solving Spatiotemporal PDEs

Abstract

Partial differential equations (PDEs) play a fundamental role in modeling and simulating problems across a wide range of disciplines. Recent advances in deep learning have shown the great potential of physics-informed neural networks (PINNs) to solve PDEs as a basis for data-driven modeling and inverse analysis. However, the majority of existing PINN methods, based on fully-connected NNs, pose intrinsic limitations to low-dimensional spatiotemporal parameterizations. Moreover, since the initial/boundary conditions (I/BCs) are softly imposed via penalty, the solution quality heavily relies on hyperparameter tuning. To this end, we propose the novel physics-informed convolutional-recurrent learning architectures (PhyCRNet and PhyCRNet-s) for solving PDEs without any labeled data. Specifically, an encoder-decoder convolutional long short-term memory network is proposed for low-dimensional spatial feature extraction and temporal evolution learning. The loss function is defined as the aggregated discretized PDE residuals, while the I/BCs are hard-encoded in the network to ensure forcible satisfaction (e.g., periodic boundary padding). The networks are further enhanced by autoregressive and residual connections that explicitly simulate time marching. The performance of our proposed methods has been assessed by solving three nonlinear PDEs (e.g., 2D Burgers' equations, the $\lambda$-$\omega$ and FitzHugh Nagumo reaction-diffusion equations), and compared against the start-of-the-art baseline algorithms. The numerical results demonstrate the superiority of our proposed methodology in the context of solution accuracy, extrapolability and generalizability.

22 pages

References in corpus (6)

• Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift
• Sequence to Sequence Learning with Neural Networks
• Semi-Supervised Classification with Graph Convolutional Networks
• Physics-Constrained Deep Learning for High-dimensional Surrogate Modeling and Uncertainty Quantification without Labeled Data
• Prediction of Aerodynamic Flow Fields Using Convolutional Neural Networks
• Hard Encoding of Physics for Learning Spatiotemporal Dynamics

Cited by in corpus (22)

• CAN-PINN: A Fast Physics-Informed Neural Network Based on Coupled-Automatic-Numerical Differentiation Method
• Deep Learning in Deterministic Computational Mechanics
• Physics-informed PointNet: A deep learning solver for steady-state incompressible flows and thermal fields on multiple sets of irregular geometries
• KAN-ODEs: Kolmogorov-Arnold Network Ordinary Differential Equations for Learning Dynamical Systems and Hidden Physics
• Multi-resolution partial differential equations preserved learning framework for spatiotemporal dynamics
• Accelerating hydrodynamic simulations of urban drainage systems with physics-guided machine learning
• An unsupervised latent/output physics-informed convolutional-LSTM network for solving partial differential equations using peridynamic differential operator
• RBF-MGN:Solving spatiotemporal PDEs with Physics-informed Graph Neural Network
• Physics-informed MeshGraphNets (PI-MGNs): Neural finite element solvers for non-stationary and nonlinear simulations on arbitrary meshes
• A Spectral-based Physics-informed Finite Operator Learning for Prediction of Mechanical Behavior of Microstructures
• Time series forecasting of multiphase microstructure evolution using deep learning
• Adapting Physics-Informed Neural Networks to Improve ODE Optimization in Mosquito Population Dynamics
• On the locality of local neural operator in learning fluid dynamics
• Geometry-aware framework for deep energy method: an application to structural mechanics with hyperelastic materials
• LSA-PINN: Linear Boundary Connectivity Loss for Solving PDEs on Complex Geometry
• Godunov Loss Functions for Modelling of Hyperbolic Conservation Laws
• Learnable-Differentiable Finite Volume Solver for Accelerated Simulation of Flows
• Spectral Informed Neural Network: An Efficient and Low-Memory PINN
• Multi-resolution Physics-Aware Recurrent Convolutional Neural Network for Complex Flows
• Physics-informed Shadowgraph Network: An End-to-end Density Field Reconstruction Method
• A physics-aware deep learning model for shear band formation around collapsing pores in shocked reactive materials
• SlotPi: Physics-informed Object-centric Reasoning Models