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, stimulate advances in machine learning as well.
| Original language | English (US) |
|---|---|
| Pages (from-to) | 5639-5656 |
| Number of pages | 18 |
| Journal | Hydrology and Earth System Sciences |
| Volume | 22 |
| Issue number | 11 |
| DOIs | |
| State | Published - Nov 1 2018 |
Fingerprint
All Science Journal Classification (ASJC) codes
- Water Science and Technology
- Earth and Planetary Sciences (miscellaneous)
Cite this
}
HESS Opinions : Incubating deep-learning-powered hydrologic science advances as a community. / 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.
In: Hydrology and Earth System Sciences, Vol. 22, No. 11, 01.11.2018, p. 5639-5656.Research output: Contribution to journal › Article
TY - JOUR
T1 - HESS Opinions
T2 - Incubating deep-learning-powered hydrologic science advances as a community
AU - Shen, Chaopeng
AU - Laloy, Eric
AU - Elshorbagy, Amin
AU - Albert, Adrian
AU - Bales, Jerad
AU - Chang, Fi John
AU - Ganguly, Sangram
AU - Hsu, Kuo Lin
AU - Kifer, Daniel
AU - Fang, Zheng
AU - Fang, Kuai
AU - Li, Dongfeng
AU - Li, Xiaodong
AU - Tsai, Wen Ping
PY - 2018/11/1
Y1 - 2018/11/1
N2 - 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.
AB - 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.
UR - http://www.scopus.com/inward/record.url?scp=85056087005&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85056087005&partnerID=8YFLogxK
U2 - 10.5194/hess-22-5639-2018
DO - 10.5194/hess-22-5639-2018
M3 - Article
AN - SCOPUS:85056087005
VL - 22
SP - 5639
EP - 5656
JO - Hydrology and Earth System Sciences
JF - Hydrology and Earth System Sciences
SN - 1027-5606
IS - 11
ER -