Mosaic Flows: A Transferable Deep Learning Framework for Solving PDEs on Unseen Domains

Abstract

Physics-informed neural networks (PINNs) are increasingly employed to replace/augment traditional numerical methods in solving partial differential equations (PDEs). While state-of-the-art PINNs have many attractive features, they approximate a specific realization of a PDE system and hence are problem-specific. That is, the model needs to be re-trained each time the boundary conditions (BCs) and domain shape/size change. This limitation prohibits the application of PINNs to realistic or large-scale engineering problems especially since the costs and efforts associated with their training are considerable. We introduce a transferable framework for solving boundary value problems (BVPs) via deep neural networks which can be trained once and used forever for various unseen domains and BCs. We first introduce genomic flow network(GFNet), a neural network that can infer the solution of a BVP across arbitrary BCson a small square domain called genome. Then, we proposed mosaic flow(MF) predictor, a novel iterative algorithm that assembles the GFNet's inferences for BVPs on large domains with unseen sizes/shapes and BCs while preserving the spatial regularity of the solution. We demonstrate that our framework can estimate the solution of Laplace and Navier-Stokes equations in domains of unseen shapes and BCs that are, respectively, 1200 and 12 times larger than the training domains. Since our framework eliminates the need to re-train models for unseen domains and BCs, it demonstrates up to 3 orders-of-magnitude speedups compared to the state-of-the-art.

arXiv comment23 pages, 10 figures

References in corpus (32)

• Very Deep Convolutional Networks for Large-Scale Image Recognition
• LSTM: A Search Space Odyssey
• Deep Residual Learning for Image Recognition
• DeepONet: Learning nonlinear operators for identifying differential equations based on the universal approximation theorem of operators
• NSFnets (Navier-Stokes Flow nets): Physics-informed neural networks for the incompressible Navier-Stokes equations
• Adaptive activation functions accelerate convergence in deep and physics-informed neural networks
• Deep learning to represent sub-grid processes in climate models
• Fourier Neural Operator for Parametric Partial Differential Equations
• fPINNs: Fractional Physics-Informed Neural Networks
• Surrogate Modeling for Fluid Flows Based on Physics-Constrained Deep Learning Without Simulation Data
• hp-VPINNs: Variational Physics-Informed Neural Networks With Domain Decomposition
• Bayesian Deep Convolutional Encoder-Decoder Networks for Surrogate Modeling and Uncertainty Quantification
• A unified deep artificial neural network approach to partial differential equations in complex geometries
• PPINN: Parareal Physics-Informed Neural Network for time-dependent PDEs
• Prediction of Aerodynamic Flow Fields Using Convolutional Neural Networks
• GPyTorch: Blackbox Matrix-Matrix Gaussian Process Inference with GPU Acceleration
• Deep Generative Modeling for Mechanistic-based Learning and Design of Metamaterial Systems
• Deep convolutional encoder-decoder networks for uncertainty quantification of dynamic multiphase flow in heterogeneous media
• Modeling the Dynamics of PDE Systems with Physics-Constrained Deep Auto-Regressive Networks
• Accelerating Eulerian Fluid Simulation With Convolutional Networks
• Variational Physics-Informed Neural Networks For Solving Partial Differential Equations
• Understanding and mitigating gradient pathologies in physics-informed neural networks
• Data-Driven Deep Learning of Partial Differential Equations in Modal Space
• Neural Operator: Graph Kernel Network for Partial Differential Equations
• Quantifying model form uncertainty in Reynolds-averaged turbulence models with Bayesian deep neural networks
• When and why PINNs fail to train: A neural tangent kernel perspective
• Data-driven learning of robust nonlocal physics from high-fidelity synthetic data
• METASET: Exploring Shape and Property Spaces for Data-Driven Metamaterials Design
• Latent Map Gaussian Processes for Mixed Variable Metamodeling
• Adaptive Neural Network-Based Approximation to Accelerate Eulerian Fluid Simulation
• Exact imposition of boundary conditions with distance functions in physics-informed deep neural networks
• Convergence rate of DeepONets for learning operators arising from advection-diffusion equations

Cited by in corpus (7)

• Deep transfer operator learning for partial differential equations under conditional shift
• In-Context Operator Learning with Data Prompts for Differential Equation Problems
• Physics-Informed Neural Networks for Parametric Compressible Euler Equations
• Local neural operator for solving transient partial differential equations on varied domains
• Multi-Fidelity Machine Learning Applied to Steady Fluid Flows
• One-Shot Transfer Learning of Physics-Informed Neural Networks
• Accelerated Gradient-based Design Optimization Via Differentiable Physics-Informed Neural Operator: A Composites Autoclave Processing Case Study