Machine learning accelerated computational fluid dynamics
- URL: http://arxiv.org/abs/2102.01010v1
- Date: Thu, 28 Jan 2021 19:10:00 GMT
- Title: Machine learning accelerated computational fluid dynamics
- Authors: Dmitrii Kochkov, Jamie A. Smith, Ayya Alieva, Qing Wang, Michael P.
Brenner, Stephan Hoyer
- Abstract summary: We use end-to-end deep learning to improve approximations inside computational fluid dynamics for modeling two-dimensional turbulent flows.
For both direct numerical simulation of turbulence and large eddy simulation, our results are as accurate as baseline solvers with 8-10x finer resolution in each spatial dimension.
Our approach exemplifies how scientific computing can leverage machine learning and hardware accelerators to improve simulations without sacrificing accuracy or generalization.
- Score: 9.077691121640333
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: Numerical simulation of fluids plays an essential role in modeling many
physical phenomena, such as weather, climate, aerodynamics and plasma physics.
Fluids are well described by the Navier-Stokes equations, but solving these
equations at scale remains daunting, limited by the computational cost of
resolving the smallest spatiotemporal features. This leads to unfavorable
trade-offs between accuracy and tractability. Here we use end-to-end deep
learning to improve approximations inside computational fluid dynamics for
modeling two-dimensional turbulent flows. For both direct numerical simulation
of turbulence and large eddy simulation, our results are as accurate as
baseline solvers with 8-10x finer resolution in each spatial dimension,
resulting in 40-80x fold computational speedups. Our method remains stable
during long simulations, and generalizes to forcing functions and Reynolds
numbers outside of the flows where it is trained, in contrast to black box
machine learning approaches. Our approach exemplifies how scientific computing
can leverage machine learning and hardware accelerators to improve simulations
without sacrificing accuracy or generalization.
Related papers
- Gaussian Splatting to Real World Flight Navigation Transfer with Liquid Networks [93.38375271826202]
We present a method to improve generalization and robustness to distribution shifts in sim-to-real visual quadrotor navigation tasks.
We first build a simulator by integrating Gaussian splatting with quadrotor flight dynamics, and then, train robust navigation policies using Liquid neural networks.
In this way, we obtain a full-stack imitation learning protocol that combines advances in 3D Gaussian splatting radiance field rendering, programming of expert demonstration training data, and the task understanding capabilities of Liquid networks.
arXiv Detail & Related papers (2024-06-21T13:48:37Z) - Physics-enhanced Neural Operator for Simulating Turbulent Transport [9.923888452768919]
This paper presents a physics-enhanced neural operator (PENO) that incorporates physical knowledge of partial differential equations (PDEs) to accurately model flow dynamics.
The proposed method is evaluated through its performance on two distinct sets of 3D turbulent flow data.
arXiv Detail & Related papers (2024-05-31T20:05:17Z) - Differentiable Turbulence II [0.0]
We develop a framework for integrating deep learning models into a generic finite element numerical scheme for solving the Navier-Stokes equations.
We show that the learned closure can achieve accuracy comparable to traditional large eddy simulation on a finer grid that amounts to an equivalent speedup of 10x.
arXiv Detail & Related papers (2023-07-25T14:27:49Z) - Machine learning of hidden variables in multiscale fluid simulation [77.34726150561087]
Solving fluid dynamics equations often requires the use of closure relations that account for missing microphysics.
In our study, a partial differential equation simulator that is end-to-end differentiable is used to train judiciously placed neural networks.
We show that this method enables an equation based approach to reproduce non-linear, large Knudsen number plasma physics.
arXiv Detail & Related papers (2023-06-19T06:02:53Z) - FluidLab: A Differentiable Environment for Benchmarking Complex Fluid
Manipulation [80.63838153351804]
We introduce FluidLab, a simulation environment with a diverse set of manipulation tasks involving complex fluid dynamics.
At the heart of our platform is a fully differentiable physics simulator, providing GPU-accelerated simulations and gradient calculations.
We propose several domain-specific optimization schemes coupled with differentiable physics.
arXiv Detail & Related papers (2023-03-04T07:24:22Z) - Continual learning autoencoder training for a particle-in-cell
simulation via streaming [52.77024349608834]
upcoming exascale era will provide a new generation of physics simulations with high resolution.
These simulations will have a high resolution, which will impact the training of machine learning models since storing a high amount of simulation data on disk is nearly impossible.
This work presents an approach that trains a neural network concurrently to a running simulation without data on a disk.
arXiv Detail & Related papers (2022-11-09T09:55:14Z) - Learning Large-scale Subsurface Simulations with a Hybrid Graph Network
Simulator [57.57321628587564]
We introduce Hybrid Graph Network Simulator (HGNS) for learning reservoir simulations of 3D subsurface fluid flows.
HGNS consists of a subsurface graph neural network (SGNN) to model the evolution of fluid flows, and a 3D-U-Net to model the evolution of pressure.
Using an industry-standard subsurface flow dataset (SPE-10) with 1.1 million cells, we demonstrate that HGNS is able to reduce the inference time up to 18 times compared to standard subsurface simulators.
arXiv Detail & Related papers (2022-06-15T17:29:57Z) - Fast Aquatic Swimmer Optimization with Differentiable Projective
Dynamics and Neural Network Hydrodynamic Models [23.480913364381664]
Aquatic locomotion is a classic fluid-structure interaction (FSI) problem of interest to biologists and engineers.
We present a novel, fully differentiable hybrid approach to FSI that combines a 2D numerical simulation for the deformable solid structure of the swimmer.
We demonstrate the computational efficiency and differentiability of our hybrid simulator on a 2D carangiform swimmer.
arXiv Detail & Related papers (2022-03-30T15:21:44Z) - Machine learning for rapid discovery of laminar flow channel wall
modifications that enhance heat transfer [56.34005280792013]
We present a combination of accurate numerical simulations of arbitrary, flat, and non-flat channels and machine learning models predicting drag coefficient and Stanton number.
We show that convolutional neural networks (CNN) can accurately predict the target properties at a fraction of the time of numerical simulations.
arXiv Detail & Related papers (2021-01-19T16:14:02Z) - Teaching the Incompressible Navier-Stokes Equations to Fast Neural
Surrogate Models in 3D [4.981834139548193]
In this work, we present significant extensions to a recently proposed deep learning framework, which addresses the aforementioned challenges in 2D.
We go from 2D to 3D and propose an efficient architecture to cope with the high demands of 3D grids in terms of memory and computational complexity.
Our method indicates strong improvements in terms of accuracy, speed and generalization capabilities over current 3D NN-based fluid models.
arXiv Detail & Related papers (2020-12-22T09:21:40Z) - Learning Incompressible Fluid Dynamics from Scratch -- Towards Fast,
Differentiable Fluid Models that Generalize [7.707887663337803]
Recent deep learning based approaches promise vast speed-ups but do not generalize to new fluid domains.
We propose a novel physics-constrained training approach that generalizes to new fluid domains.
We present an interactive real-time demo to show the speed and generalization capabilities of our trained models.
arXiv Detail & Related papers (2020-06-15T20:59:28Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.