Entropy-driven Optimal Sub-sampling of Fluid Dynamics for Developing Machine-learned Surrogates

Wesley Brewer; Daniel Martinez; Muralikrishnan Gopalakrishnan Meena; Aditya Kashi; Katarzyna Borowiec; Siyan Liu; Christopher Pilmaier; Greg Burgreen; Shanti Bhushan

doi:10.1145/3624062.3626084

Entropy-driven Optimal Sub-sampling of Fluid Dynamics for Developing Machine-learned Surrogates

Wesley Brewer, Daniel Martinez, Muralikrishnan Gopalakrishnan Meena, Aditya Kashi, Katarzyna Borowiec, Siyan Liu, Christopher Pilmaier, Greg Burgreen, Shanti Bhushan

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

Abstract

Optimal sub-sampling of large datasets from fluid dynamics simulations is essential for training reduced-order machine learned models. A method using Shannon entropy was developed to weight flow features according to their level of information content, such that the most informative features can be extracted and used for training a surrogate model. The method is demonstrated in the canonical flow over a cylinder problem simulated with OpenFOAM. Both time-independent predictions and temporal forecasting were investigated as well as two types of prediction targets: local per-grid-point predictions and global per-time-step predictions. When tested on training a surrogate model, results indicate that our entropy-based sampling method typically outperforms random sampling and yields more reproducible results in less iterations. Finally, the method was used to train a surrogate model for modeling turbulence in magnetohydrodynamic flows, which revealed various challenges and opportunities for future research.

Original language	English
Title of host publication	Proceedings of 2023 SC Workshops of the International Conference on High Performance Computing, Network, Storage, and Analysis, SC Workshops 2023
Publisher	Association for Computing Machinery
Pages	73-80
Number of pages	8
ISBN (Electronic)	9798400707858
DOIs	https://doi.org/10.1145/3624062.3626084
State	Published - Nov 12 2023
Event	2023 International Conference on High Performance Computing, Network, Storage, and Analysis, SC Workshops 2023 - Denver, United States Duration: Nov 12 2023 → Nov 17 2023

Publication series

Name	ACM International Conference Proceeding Series

Conference

Conference	2023 International Conference on High Performance Computing, Network, Storage, and Analysis, SC Workshops 2023
Country/Territory	United States
City	Denver
Period	11/12/23 → 11/17/23

Funding

This research was sponsored by and used resources of the Oak Ridge Leadership Computing Facility (OLCF), which is a DOE Office of Science User Facility at the Oak Ridge National Laboratory (ORNL) supported by the U.S. Department of Energy under Contract No. DE-AC05-00OR22725. Moreover, we would like to express our appreciation to a number of colleagues who provided useful advice during the course of this work, including Joshua Brown, Jong Choi, and Mariia Karabin of ORNL, as well as OpenAI’s GPT-4. Notice: This manuscript has been authored by UT-Battelle, LLC, under contract DE-AC05-00OR22725 with the US Department of Energy (DOE). The US government retains and the publisher, by accepting the article for publication, acknowledges that the US government retains a nonexclusive, paid-up, irrevocable, worldwide license to publish or reproduce the published form of this manuscript, or allow others to do so, for US government purposes. DOE will provide public access to these results of federally sponsored research in accordance with the DOE Public Access Plan (https://www.energy.gov/doe-public-access-plan).

Funders	Funder number
U.S. Department of Energy	DE-AC05-00OR22725
U.S. Department of Energy
Office of Science
Oak Ridge National Laboratory

Keywords

clustering
maximum entropy
reduced-order
sampling
surrogate

Access to Document

10.1145/3624062.3626084

Cite this

Brewer, W., Martinez, D., Gopalakrishnan Meena, M., Kashi, A., Borowiec, K., Liu, S., Pilmaier, C., Burgreen, G., & Bhushan, S. (2023). Entropy-driven Optimal Sub-sampling of Fluid Dynamics for Developing Machine-learned Surrogates. In Proceedings of 2023 SC Workshops of the International Conference on High Performance Computing, Network, Storage, and Analysis, SC Workshops 2023 (pp. 73-80). (ACM International Conference Proceeding Series). Association for Computing Machinery. https://doi.org/10.1145/3624062.3626084

Brewer, Wesley ; Martinez, Daniel ; Gopalakrishnan Meena, Muralikrishnan et al. / Entropy-driven Optimal Sub-sampling of Fluid Dynamics for Developing Machine-learned Surrogates. Proceedings of 2023 SC Workshops of the International Conference on High Performance Computing, Network, Storage, and Analysis, SC Workshops 2023. Association for Computing Machinery, 2023. pp. 73-80 (ACM International Conference Proceeding Series).

@inproceedings{9c6bac942cc946f1878373e564432178,

title = "Entropy-driven Optimal Sub-sampling of Fluid Dynamics for Developing Machine-learned Surrogates",

abstract = "Optimal sub-sampling of large datasets from fluid dynamics simulations is essential for training reduced-order machine learned models. A method using Shannon entropy was developed to weight flow features according to their level of information content, such that the most informative features can be extracted and used for training a surrogate model. The method is demonstrated in the canonical flow over a cylinder problem simulated with OpenFOAM. Both time-independent predictions and temporal forecasting were investigated as well as two types of prediction targets: local per-grid-point predictions and global per-time-step predictions. When tested on training a surrogate model, results indicate that our entropy-based sampling method typically outperforms random sampling and yields more reproducible results in less iterations. Finally, the method was used to train a surrogate model for modeling turbulence in magnetohydrodynamic flows, which revealed various challenges and opportunities for future research.",

keywords = "clustering, maximum entropy, reduced-order, sampling, surrogate",

author = "Wesley Brewer and Daniel Martinez and {Gopalakrishnan Meena}, Muralikrishnan and Aditya Kashi and Katarzyna Borowiec and Siyan Liu and Christopher Pilmaier and Greg Burgreen and Shanti Bhushan",

note = "Publisher Copyright: {\textcopyright} 2023 ACM.; 2023 International Conference on High Performance Computing, Network, Storage, and Analysis, SC Workshops 2023 ; Conference date: 12-11-2023 Through 17-11-2023",

year = "2023",

month = nov,

day = "12",

doi = "10.1145/3624062.3626084",

language = "English",

series = "ACM International Conference Proceeding Series",

publisher = "Association for Computing Machinery",

pages = "73--80",

booktitle = "Proceedings of 2023 SC Workshops of the International Conference on High Performance Computing, Network, Storage, and Analysis, SC Workshops 2023",

}

Brewer, W, Martinez, D, Gopalakrishnan Meena, M , Kashi, A , Borowiec, K , Liu, S, Pilmaier, C, Burgreen, G & Bhushan, S 2023, Entropy-driven Optimal Sub-sampling of Fluid Dynamics for Developing Machine-learned Surrogates. in Proceedings of 2023 SC Workshops of the International Conference on High Performance Computing, Network, Storage, and Analysis, SC Workshops 2023. ACM International Conference Proceeding Series, Association for Computing Machinery, pp. 73-80, 2023 International Conference on High Performance Computing, Network, Storage, and Analysis, SC Workshops 2023, Denver, United States, 11/12/23. https://doi.org/10.1145/3624062.3626084

Entropy-driven Optimal Sub-sampling of Fluid Dynamics for Developing Machine-learned Surrogates. / Brewer, Wesley; Martinez, Daniel; Gopalakrishnan Meena, Muralikrishnan et al.
Proceedings of 2023 SC Workshops of the International Conference on High Performance Computing, Network, Storage, and Analysis, SC Workshops 2023. Association for Computing Machinery, 2023. p. 73-80 (ACM International Conference Proceeding Series).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - Entropy-driven Optimal Sub-sampling of Fluid Dynamics for Developing Machine-learned Surrogates

AU - Brewer, Wesley

AU - Martinez, Daniel

AU - Gopalakrishnan Meena, Muralikrishnan

AU - Kashi, Aditya

AU - Borowiec, Katarzyna

AU - Liu, Siyan

AU - Pilmaier, Christopher

AU - Burgreen, Greg

AU - Bhushan, Shanti

PY - 2023/11/12

Y1 - 2023/11/12

N2 - Optimal sub-sampling of large datasets from fluid dynamics simulations is essential for training reduced-order machine learned models. A method using Shannon entropy was developed to weight flow features according to their level of information content, such that the most informative features can be extracted and used for training a surrogate model. The method is demonstrated in the canonical flow over a cylinder problem simulated with OpenFOAM. Both time-independent predictions and temporal forecasting were investigated as well as two types of prediction targets: local per-grid-point predictions and global per-time-step predictions. When tested on training a surrogate model, results indicate that our entropy-based sampling method typically outperforms random sampling and yields more reproducible results in less iterations. Finally, the method was used to train a surrogate model for modeling turbulence in magnetohydrodynamic flows, which revealed various challenges and opportunities for future research.

AB - Optimal sub-sampling of large datasets from fluid dynamics simulations is essential for training reduced-order machine learned models. A method using Shannon entropy was developed to weight flow features according to their level of information content, such that the most informative features can be extracted and used for training a surrogate model. The method is demonstrated in the canonical flow over a cylinder problem simulated with OpenFOAM. Both time-independent predictions and temporal forecasting were investigated as well as two types of prediction targets: local per-grid-point predictions and global per-time-step predictions. When tested on training a surrogate model, results indicate that our entropy-based sampling method typically outperforms random sampling and yields more reproducible results in less iterations. Finally, the method was used to train a surrogate model for modeling turbulence in magnetohydrodynamic flows, which revealed various challenges and opportunities for future research.

KW - clustering

KW - maximum entropy

KW - reduced-order

KW - sampling

KW - surrogate

UR - http://www.scopus.com/inward/record.url?scp=85178160342&partnerID=8YFLogxK

U2 - 10.1145/3624062.3626084

DO - 10.1145/3624062.3626084

M3 - Conference contribution

AN - SCOPUS:85178160342

T3 - ACM International Conference Proceeding Series

SP - 73

EP - 80

BT - Proceedings of 2023 SC Workshops of the International Conference on High Performance Computing, Network, Storage, and Analysis, SC Workshops 2023

PB - Association for Computing Machinery

T2 - 2023 International Conference on High Performance Computing, Network, Storage, and Analysis, SC Workshops 2023

Y2 - 12 November 2023 through 17 November 2023

ER -

Brewer W, Martinez D, Gopalakrishnan Meena M , Kashi A , Borowiec K , Liu S et al. Entropy-driven Optimal Sub-sampling of Fluid Dynamics for Developing Machine-learned Surrogates. In Proceedings of 2023 SC Workshops of the International Conference on High Performance Computing, Network, Storage, and Analysis, SC Workshops 2023. Association for Computing Machinery. 2023. p. 73-80. (ACM International Conference Proceeding Series). doi: 10.1145/3624062.3626084

Entropy-driven Optimal Sub-sampling of Fluid Dynamics for Developing Machine-learned Surrogates

Abstract

Publication series

Conference

Funding

Keywords

Access to Document

Other files and links

Fingerprint

Cite this