skip to main content
DOE PAGES title logo U.S. Department of Energy
Office of Scientific and Technical Information

Title: HESS Opinions: Incubating deep-learning-powered hydrologic science advances as a community

Abstract

Recently, deep learning (DL) has emerged as a revolutionary and versatile tool transforming industry applications and generating new and improved capabilities for scientific discovery and model building. The adoption of DL in hydrology has so far been gradual, but the field is now ripe for breakthroughs. This paper suggests that DL-based methods can open up a complementary avenue toward knowledge discovery in hydrologic sciences. In the new avenue, machine-learning algorithms present competing hypotheses that are consistent with data. Interrogative methods are then invoked to interpret DL models for scientists to further evaluate. However, hydrology presents many challenges for DL methods, such as data limitations, heterogeneity and co-evolution, and the general inexperience of the hydrologic field with DL. The roadmap toward DL-powered scientific advances will require the coordinated effort from a large community involving scientists and citizens.Integrating process-based models with DL models will help alleviate data limitations. The sharing of data and baseline models will improve the efficiency of the community as a whole. Open competitions could serve as the organizing events to greatly propel growth and nurture data science education in hydrology, which demands a grassroots collaboration. The area of hydrologic DL presents numerous research opportunities that could, in turn,stimulatemore » advances in machine learning as well.« less

Authors:
 [1];  [2]; ORCiD logo [3];  [4]; ORCiD logo [5];  [6];  [7];  [8];  [1]; ORCiD logo [9];  [1];  [9];  [10];  [1]
  1. Pennsylvania State Univ., University Park, PA (United States)
  2. Belgian Nuclear Research Centre, Mol (Belgium)
  3. Univ. of Saskatchewan, Saskatoon, SK (Canada)
  4. Lawrence Berkeley National Lab. (LBNL), Berkeley, CA (United States)
  5. Consortium of Univ. for the Advancement of Hydrologic Science, Inc. (CUAHSI), Cambridge, MA (United States)
  6. National Taiwan Univ., Taipei (Taiwan)
  7. NASA Ames Research Center (ARC), Moffett Field, Mountain View, CA (United States)
  8. Univ. of California, Irvine, CA (United States)
  9. Univ. of Texas, Arlington, TX (United States)
  10. Sichuan Univ., Sichuan (China)
Publication Date:
Research Org.:
Lawrence Berkeley National Lab. (LBNL), Berkeley, CA (United States)
Sponsoring Org.:
USDOE Office of Science (SC); National Science Foundation (NSF)
OSTI Identifier:
1542338
Grant/Contract Number:  
AC02-05CH11231; SC0016605; EAR-1832294; EAR-1338606; 2018SZ0343; CCF-1317560
Resource Type:
Accepted Manuscript
Journal Name:
Hydrology and Earth System Sciences (Online)
Additional Journal Information:
Journal Name: Hydrology and Earth System Sciences (Online); Journal Volume: 22; Journal Issue: 11; Journal ID: ISSN 1607-7938
Publisher:
European Geosciences Union (EGU)
Country of Publication:
United States
Language:
English
Subject:
58 GEOSCIENCES

Citation Formats

Shen, Chaopeng, Laloy, Eric, Elshorbagy, Amin, Albert, Adrian, Bales, Jerad, Chang, Fi-John, Ganguly, Sangram, Hsu, Kuo-Lin, Kifer, Daniel, Fang, Zheng, Fang, Kuai, Li, Dongfeng, Li, Xiaodong, and Tsai, Wen-Ping. HESS Opinions: Incubating deep-learning-powered hydrologic science advances as a community. United States: N. p., 2018. Web. doi:10.5194/hess-22-5639-2018.
Shen, Chaopeng, Laloy, Eric, Elshorbagy, Amin, Albert, Adrian, Bales, Jerad, Chang, Fi-John, Ganguly, Sangram, Hsu, Kuo-Lin, Kifer, Daniel, Fang, Zheng, Fang, Kuai, Li, Dongfeng, Li, Xiaodong, & Tsai, Wen-Ping. HESS Opinions: Incubating deep-learning-powered hydrologic science advances as a community. United States. doi:10.5194/hess-22-5639-2018.
Shen, Chaopeng, Laloy, Eric, Elshorbagy, Amin, Albert, Adrian, Bales, Jerad, Chang, Fi-John, Ganguly, Sangram, Hsu, Kuo-Lin, Kifer, Daniel, Fang, Zheng, Fang, Kuai, Li, Dongfeng, Li, Xiaodong, and Tsai, Wen-Ping. Thu . "HESS Opinions: Incubating deep-learning-powered hydrologic science advances as a community". United States. doi:10.5194/hess-22-5639-2018. https://www.osti.gov/servlets/purl/1542338.
@article{osti_1542338,
title = {HESS Opinions: Incubating deep-learning-powered hydrologic science advances as a community},
author = {Shen, Chaopeng and Laloy, Eric and Elshorbagy, Amin and Albert, Adrian and Bales, Jerad and Chang, Fi-John and Ganguly, Sangram and Hsu, Kuo-Lin and Kifer, Daniel and Fang, Zheng and Fang, Kuai and Li, Dongfeng and Li, Xiaodong and Tsai, Wen-Ping},
abstractNote = {Recently, deep learning (DL) has emerged as a revolutionary and versatile tool transforming industry applications and generating new and improved capabilities for scientific discovery and model building. The adoption of DL in hydrology has so far been gradual, but the field is now ripe for breakthroughs. This paper suggests that DL-based methods can open up a complementary avenue toward knowledge discovery in hydrologic sciences. In the new avenue, machine-learning algorithms present competing hypotheses that are consistent with data. Interrogative methods are then invoked to interpret DL models for scientists to further evaluate. However, hydrology presents many challenges for DL methods, such as data limitations, heterogeneity and co-evolution, and the general inexperience of the hydrologic field with DL. The roadmap toward DL-powered scientific advances will require the coordinated effort from a large community involving scientists and citizens.Integrating process-based models with DL models will help alleviate data limitations. The sharing of data and baseline models will improve the efficiency of the community as a whole. Open competitions could serve as the organizing events to greatly propel growth and nurture data science education in hydrology, which demands a grassroots collaboration. The area of hydrologic DL presents numerous research opportunities that could, in turn,stimulate advances in machine learning as well.},
doi = {10.5194/hess-22-5639-2018},
journal = {Hydrology and Earth System Sciences (Online)},
number = 11,
volume = 22,
place = {United States},
year = {2018},
month = {11}
}

Journal Article:
Free Publicly Available Full Text
Publisher's Version of Record

Citation Metrics:
Cited by: 7 works
Citation information provided by
Web of Science

Save / Share: