Process Guided Deep Learning for Modeling Physical Systems: An Application in Lake Temperature Modeling

Xiaowei Jia; Jared Willard; Anuj Karpatne; Jordan S. Read; Jacob A. Zwart; Michael Steinbach; Vipin Kumar

doi:10.1109/IGARSS39084.2020.9323723

Process Guided Deep Learning for Modeling Physical Systems: An Application in Lake Temperature Modeling

Xiaowei Jia, Jared Willard, Anuj Karpatne, Jordan S. Read, Jacob A. Zwart, Michael Steinbach, Vipin Kumar

Computer Science and Engineering

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

1 Scopus citations

Abstract

In this paper, we introduce a new paradigm that combines scientific knowledge within process-based models and machine learning models to advance scientific discovery in many physical systems. We will describe how to incorporate physical knowledge in real-world dynamical systems as additional constraints for training machine learning models and how to leverage the hidden knowledge encoded by existing process-based models. We evaluate this approach on modeling lake water temperature and demonstrate its superior performance using limited training data and the improved generalizability to different scenarios.

Original language	English (US)
Title of host publication	2020 IEEE International Geoscience and Remote Sensing Symposium, IGARSS 2020 - Proceedings
Publisher	Institute of Electrical and Electronics Engineers Inc.
Pages	3494-3496
Number of pages	3
ISBN (Electronic)	9781728163741
DOIs	https://doi.org/10.1109/IGARSS39084.2020.9323723
State	Published - Sep 26 2020
Event	2020 IEEE International Geoscience and Remote Sensing Symposium, IGARSS 2020 - Virtual, Waikoloa, United States Duration: Sep 26 2020 → Oct 2 2020

Publication series

Name	International Geoscience and Remote Sensing Symposium (IGARSS)

Conference

Conference	2020 IEEE International Geoscience and Remote Sensing Symposium, IGARSS 2020
Country/Territory	United States
City	Virtual, Waikoloa
Period	9/26/20 → 10/2/20

Bibliographical note

Publisher Copyright:
© 2020 IEEE.

Copyright:
Copyright 2021 Elsevier B.V., All rights reserved.

Keywords

Deep Learning
Lake Temperature Modeling
Physical Systems

Publisher link

10.1109/IGARSS39084.2020.9323723

Find It

Find It at U of M Libraries

Cite this

Jia, X., Willard, J., Karpatne, A., Read, J. S., Zwart, J. A., Steinbach, M., & Kumar, V. (2020). Process Guided Deep Learning for Modeling Physical Systems: An Application in Lake Temperature Modeling. In 2020 IEEE International Geoscience and Remote Sensing Symposium, IGARSS 2020 - Proceedings (pp. 3494-3496). [9323723] (International Geoscience and Remote Sensing Symposium (IGARSS)). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/IGARSS39084.2020.9323723

Process Guided Deep Learning for Modeling Physical Systems: An Application in Lake Temperature Modeling. / Jia, Xiaowei; Willard, Jared; Karpatne, Anuj et al.
2020 IEEE International Geoscience and Remote Sensing Symposium, IGARSS 2020 - Proceedings. Institute of Electrical and Electronics Engineers Inc., 2020. p. 3494-3496 9323723 (International Geoscience and Remote Sensing Symposium (IGARSS)).

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

Jia, X, Willard, J, Karpatne, A, Read, JS, Zwart, JA, Steinbach, M & Kumar, V 2020, Process Guided Deep Learning for Modeling Physical Systems: An Application in Lake Temperature Modeling. in 2020 IEEE International Geoscience and Remote Sensing Symposium, IGARSS 2020 - Proceedings., 9323723, International Geoscience and Remote Sensing Symposium (IGARSS), Institute of Electrical and Electronics Engineers Inc., pp. 3494-3496, 2020 IEEE International Geoscience and Remote Sensing Symposium, IGARSS 2020, Virtual, Waikoloa, United States, 9/26/20. https://doi.org/10.1109/IGARSS39084.2020.9323723

Jia X, Willard J, Karpatne A, Read JS, Zwart JA, Steinbach M et al. Process Guided Deep Learning for Modeling Physical Systems: An Application in Lake Temperature Modeling. In 2020 IEEE International Geoscience and Remote Sensing Symposium, IGARSS 2020 - Proceedings. Institute of Electrical and Electronics Engineers Inc. 2020. p. 3494-3496. 9323723. (International Geoscience and Remote Sensing Symposium (IGARSS)). doi: 10.1109/IGARSS39084.2020.9323723

Jia, Xiaowei ; Willard, Jared ; Karpatne, Anuj et al. / Process Guided Deep Learning for Modeling Physical Systems : An Application in Lake Temperature Modeling. 2020 IEEE International Geoscience and Remote Sensing Symposium, IGARSS 2020 - Proceedings. Institute of Electrical and Electronics Engineers Inc., 2020. pp. 3494-3496 (International Geoscience and Remote Sensing Symposium (IGARSS)).

@inproceedings{009f55f5efa74f26b078add7bf76aa86,

title = "Process Guided Deep Learning for Modeling Physical Systems: An Application in Lake Temperature Modeling",

abstract = "In this paper, we introduce a new paradigm that combines scientific knowledge within process-based models and machine learning models to advance scientific discovery in many physical systems. We will describe how to incorporate physical knowledge in real-world dynamical systems as additional constraints for training machine learning models and how to leverage the hidden knowledge encoded by existing process-based models. We evaluate this approach on modeling lake water temperature and demonstrate its superior performance using limited training data and the improved generalizability to different scenarios.",

keywords = "Deep Learning, Lake Temperature Modeling, Physical Systems",

author = "Xiaowei Jia and Jared Willard and Anuj Karpatne and Read, {Jordan S.} and Zwart, {Jacob A.} and Michael Steinbach and Vipin Kumar",

note = "Publisher Copyright: {\textcopyright} 2020 IEEE. Copyright: Copyright 2021 Elsevier B.V., All rights reserved.; 2020 IEEE International Geoscience and Remote Sensing Symposium, IGARSS 2020 ; Conference date: 26-09-2020 Through 02-10-2020",

year = "2020",

month = sep,

day = "26",

doi = "10.1109/IGARSS39084.2020.9323723",

language = "English (US)",

series = "International Geoscience and Remote Sensing Symposium (IGARSS)",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

pages = "3494--3496",

booktitle = "2020 IEEE International Geoscience and Remote Sensing Symposium, IGARSS 2020 - Proceedings",

}

TY - GEN

T1 - Process Guided Deep Learning for Modeling Physical Systems

T2 - 2020 IEEE International Geoscience and Remote Sensing Symposium, IGARSS 2020

AU - Jia, Xiaowei

AU - Willard, Jared

AU - Karpatne, Anuj

AU - Read, Jordan S.

AU - Zwart, Jacob A.

AU - Steinbach, Michael

AU - Kumar, Vipin

PY - 2020/9/26

Y1 - 2020/9/26

N2 - In this paper, we introduce a new paradigm that combines scientific knowledge within process-based models and machine learning models to advance scientific discovery in many physical systems. We will describe how to incorporate physical knowledge in real-world dynamical systems as additional constraints for training machine learning models and how to leverage the hidden knowledge encoded by existing process-based models. We evaluate this approach on modeling lake water temperature and demonstrate its superior performance using limited training data and the improved generalizability to different scenarios.

AB - In this paper, we introduce a new paradigm that combines scientific knowledge within process-based models and machine learning models to advance scientific discovery in many physical systems. We will describe how to incorporate physical knowledge in real-world dynamical systems as additional constraints for training machine learning models and how to leverage the hidden knowledge encoded by existing process-based models. We evaluate this approach on modeling lake water temperature and demonstrate its superior performance using limited training data and the improved generalizability to different scenarios.

KW - Deep Learning

KW - Lake Temperature Modeling

KW - Physical Systems

UR - http://www.scopus.com/inward/record.url?scp=85101969023&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85101969023&partnerID=8YFLogxK

U2 - 10.1109/IGARSS39084.2020.9323723

DO - 10.1109/IGARSS39084.2020.9323723

M3 - Conference contribution

AN - SCOPUS:85101969023

T3 - International Geoscience and Remote Sensing Symposium (IGARSS)

SP - 3494

EP - 3496

BT - 2020 IEEE International Geoscience and Remote Sensing Symposium, IGARSS 2020 - Proceedings

PB - Institute of Electrical and Electronics Engineers Inc.

Y2 - 26 September 2020 through 2 October 2020

ER -

Process Guided Deep Learning for Modeling Physical Systems: An Application in Lake Temperature Modeling

Abstract

Publication series

Conference

Bibliographical note

Keywords

Publisher link

Find It

Other files and links

Fingerprint

Cite this