Accelerating Eulerian Fluid Simulation With Convolutional Networks
[edit]
Proceedings of the 34th International Conference on Machine Learning, PMLR 70:34243433, 2017.
Abstract
Efficient simulation of the NavierStokes equations for fluid flow is a long standing problem in applied mathematics, for which stateoftheart methods require large compute resources. In this work, we propose a datadriven approach that leverages the approximation power of deeplearning with the precision of standard solvers to obtain fast and highly realistic simulations. Our method solves the incompressible Euler equations using the standard operator splitting method, in which a large sparse linear system with many free parameters must be solved. We use a Convolutional Network with a highly tailored architecture, trained using a novel unsupervised learning framework to solve the linear system. We present realtime 2D and 3D simulations that outperform recently proposed datadriven methods; the obtained results are realistic and show good generalization properties.
Related Material


