Back to Search Start Over

MeshfreeFlowNet: A Physics-Constrained Deep Continuous Space-Time Super-Resolution Framework

Authors :
Jiang, Chiyu Max
Esmaeilzadeh, Soheil
Azizzadenesheli, Kamyar
Kashinath, Karthik
Mustafa, Mustafa
Tchelepi, Hamdi A.
Marcus, Philip
Prabhat
Anandkumar, Anima
Publication Year :
2020

Abstract

We propose MeshfreeFlowNet, a novel deep learning-based super-resolution framework to generate continuous (grid-free) spatio-temporal solutions from the low-resolution inputs. While being computationally efficient, MeshfreeFlowNet accurately recovers the fine-scale quantities of interest. MeshfreeFlowNet allows for: (i) the output to be sampled at all spatio-temporal resolutions, (ii) a set of Partial Differential Equation (PDE) constraints to be imposed, and (iii) training on fixed-size inputs on arbitrarily sized spatio-temporal domains owing to its fully convolutional encoder. We empirically study the performance of MeshfreeFlowNet on the task of super-resolution of turbulent flows in the Rayleigh-Benard convection problem. Across a diverse set of evaluation metrics, we show that MeshfreeFlowNet significantly outperforms existing baselines. Furthermore, we provide a large scale implementation of MeshfreeFlowNet and show that it efficiently scales across large clusters, achieving 96.80% scaling efficiency on up to 128 GPUs and a training time of less than 4 minutes.<br />Comment: Supplementary Video: https://youtu.be/mjqwPch9gDo. Accepted to SC20

Details

Database :
arXiv
Publication Type :
Report
Accession number :
edsarx.2005.01463
Document Type :
Working Paper