Learning Incompressible Fluid Dynamics from Scratch -- Towards Fast, Differentiable Fluid Models that Generalize

Abstract

Fast and stable fluid simulations are an essential prerequisite for applications ranging from computer-generated imagery to computer-aided design in research and development. However, solving the partial differential equations of incompressible fluids is a challenging task and traditional numerical approximation schemes come at high computational costs. Recent deep learning based approaches promise vast speed-ups but do not generalize to new fluid domains, require fluid simulation data for training, or rely on complex pipelines that outsource major parts of the fluid simulation to traditional methods. In this work, we propose a novel physics-constrained training approach that generalizes to new fluid domains, requires no fluid simulation data, and allows convolutional neural networks to map a fluid state from time-point t to a subsequent state at time t + dt in a single forward pass. This simplifies the pipeline to train and evaluate neural fluid models. After training, the framework yields models that are capable of fast fluid simulations and can handle various fluid phenomena including the Magnus effect and Karman vortex streets. We present an interactive real-time demo to show the speed and generalization capabilities of our trained models. Moreover, the trained neural networks are efficient differentiable fluid solvers as they offer a differentiable update step to advance the fluid simulation in time. We exploit this fact in a proof-of-concept optimal control experiment. Our models significantly outperform a recent differentiable fluid solver in terms of computational speed and accuracy.

arXiv commentto be published at International Conference on Learning Representations (ICLR) 2021

References in corpus (16)

• DGM: A deep learning algorithm for solving partial differential equations
• Physics-Constrained Deep Learning for High-dimensional Surrogate Modeling and Uncertainty Quantification without Labeled Data
• Bayesian Deep Convolutional Encoder-Decoder Networks for Surrogate Modeling and Uncertainty Quantification
• Deep Learning Methods for Reynolds-Averaged Navier-Stokes Simulations of Airfoil Flows
• Deep UQ: Learning deep neural network surrogate models for high dimensional uncertainty quantification
• Modeling the Dynamics of PDE Systems with Physics-Constrained Deep Auto-Regressive Networks
• Accelerating Eulerian Fluid Simulation With Convolutional Networks
• Learning Particle Dynamics for Manipulating Rigid Bodies, Deformable Objects, and Fluids
• Flexible Neural Representation for Physics Prediction
• A proof that artificial neural networks overcome the curse of dimensionality in the numerical approximation of Black-Scholes partial differential equations
• Quantifying model form uncertainty in Reynolds-averaged turbulence models with Bayesian deep neural networks
• Solver-in-the-Loop: Learning from Differentiable Physics to Interact with Iterative PDE-Solvers
• Deep unsupervised learning of turbulence for inflow generation at various Reynolds numbers
• Hidden Fluid Mechanics: A Navier-Stokes Informed Deep Learning Framework for Assimilating Flow Visualization Data
• Embedding Hard Physical Constraints in Neural Network Coarse-Graining of 3D Turbulence
• Predictive Collective Variable Discovery with Deep Bayesian Models

Cited by in corpus (3)

• Teaching the Incompressible Navier-Stokes Equations to Fast Neural Surrogate Models in 3D
• Finite Volume Graph Network(FVGN): Predicting unsteady incompressible fluid dynamics with finite volume informed neural network
• Finite-difference-informed graph network for solving steady-state incompressible flows on block-structured grids