CaltechAUTHORS
  A Caltech Library Service

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

Jiang, Chiyu Max and Esmaeilzadeh, Soheil and Azizzadenesheli, Kamyar and Kashinath, Karthik and Mustafa, Mustafa and Tchelepi, Hamdi A. and Marcus, Philip and Prabhat, Mr. and Anandkumar, Anima (2020) MESHFREEFLOWNET: A Physics-Constrained Deep Continuous Space-Time Super-Resolution Framework. In: SC20: International Conference for High Performance Computing, Networking, Storage and Analysis. IEEE , Piscataway, NJ, pp. 1-15. ISBN 978-1-7281-9998-6. https://resolver.caltech.edu/CaltechAUTHORS:20200526-153937049

[img]
Preview
PDF (21 Aug 2020) - Submitted Version
See Usage Policy.

7Mb

Use this Persistent URL to link to this item: https://resolver.caltech.edu/CaltechAUTHORS:20200526-153937049

Abstract

We propose MESHFREEFLOWNET, a novel deep learning-based super-resolution framework to generate continuous (grid-free) spatio-temporal solutions from the lowresolution 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-Bénard 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. We provide an opensource implementation of our method that supports arbitrary combinations of PDE constraints.


Item Type:Book Section
Related URLs:
URLURL TypeDescription
https://doi.org/10.1109/SC41405.2020.00013DOIArticle
https://arxiv.org/abs/2005.01463arXivDiscussion Paper
https://github.com/maxjiang93/space_time_pdeRelated ItemCode
https://youtu.be/mjqwPch9gDoRelated ItemSupplementary Video
ORCID:
AuthorORCID
Jiang, Chiyu Max0000-0002-7815-8735
Esmaeilzadeh, Soheil0000-0001-6122-9122
Azizzadenesheli, Kamyar0000-0001-8507-1868
Kashinath, Karthik0000-0002-9311-5215
Tchelepi, Hamdi A.0000-0002-3084-6635
Marcus, Philip0000-0001-5247-0643
Prabhat, Mr.0000-0003-3281-5186
Alternate Title:MeshfreeFlowNet: A Physics-Constrained Deep Continuous Space-Time Super-Resolution Framework
Additional Information:© 2020 IEEE. This research used resources of the National Energy Research Scientific Computing Center (NERSC), a DOE Office of Science User Facility supported by the Office of Science of the U.S. Department of Energy under Contract No. DE-AC02-05CH11231. The research was performed at the Lawrence Berkeley National Laboratory for the U.S. Department of Energy under Contract No. DE340AC02-5CH11231. K. Kashinath is supported by the Intel Big Data Center at NERSC. K. Azizzadenesheli gratefully acknowledges the financial support of Raytheon and Amazon Web Services. A. Anandkumar is supported in part by Bren endowed chair, DARPA PAIHR00111890035 and LwLL grants, Raytheon, Microsoft, Google, and Adobe faculty fellowships. We also acknowledge the Industrial Consortium on Reservoir Simulation Research at Stanford University (SUPRI-B).
Funders:
Funding AgencyGrant Number
Department of Energy (DOE)DE-AC02-05CH11231
Department of Energy (DOE)DE-340AC02-05CH11231
Lawrence Berkeley National LaboratoryUNSPECIFIED
Department of Energy (DOE)DE-340AC02-5CH11231
Raytheon CompanyUNSPECIFIED
Amazon Web ServicesUNSPECIFIED
Bren Professor of Computing and Mathematical SciencesUNSPECIFIED
Defense Advanced Research Projects Agency (DARPA)PAIHR00111890035
Learning with Less Labels (LwLL)UNSPECIFIED
MicrosoftUNSPECIFIED
GoogleUNSPECIFIED
AdobeUNSPECIFIED
Stanford UniversityUNSPECIFIED
Subject Keywords:Super-Resolution, PDEs, Physics-Constrained, Deep Neural Networks
Record Number:CaltechAUTHORS:20200526-153937049
Persistent URL:https://resolver.caltech.edu/CaltechAUTHORS:20200526-153937049
Official Citation:C. “. Jiang et al., "MESHFREEFLOWNET: A Physics-Constrained Deep Continuous Space-Time Super-Resolution Framework," SC20: International Conference for High Performance Computing, Networking, Storage and Analysis, Atlanta, GA, USA, 2020, pp. 1-15, doi: 10.1109/SC41405.2020.00013.
Usage Policy:No commercial reproduction, distribution, display or performance rights in this work are provided.
ID Code:103478
Collection:CaltechAUTHORS
Deposited By: Tony Diaz
Deposited On:26 May 2020 22:49
Last Modified:02 Mar 2021 18:58

Repository Staff Only: item control page