Deep dive into hydrologic simulations at global scale: harnessing the power of deep learning and physics-informed differentiable models (<i>δ</i>HBV-globe1.0-hydroDL)

Feng, Dapeng; Beck, Hylke; de Bruijn, Jens; Sahu, Reetik Kumar; Satoh, Yusuke; Wada, Yoshihide; Liu, Jiangtao; Pan, Ming; Lawson, Kathryn; Shen, Chaopeng

doi:https://doi.org/10.5194/gmd-17-7181-2024

Articles | Volume 17, issue 18

Article
Assets
Peer review
Metrics
Related articles

Articles | Volume 17, issue 18

https://doi.org/10.5194/gmd-17-7181-2024

Articles | Volume 17, issue 18

Article
Assets
Peer review
Metrics
Related articles

Model evaluation paper

26 Sep 2024

Model evaluation paper |

| 26 Sep 2024

Deep dive into hydrologic simulations at global scale: harnessing the power of deep learning and physics-informed differentiable models (δHBV-globe1.0-hydroDL)

Dapeng Feng, Hylke Beck, Jens de Bruijn, Reetik Kumar Sahu, Yusuke Satoh, Yoshihide Wada, Jiangtao Liu, Ming Pan, Kathryn Lawson, and Chaopeng Shen

Dapeng Feng

CORRESPONDING AUTHOR

dpfeng@stanford.edu

Civil and Environmental Engineering, Pennsylvania State University, University Park, PA, USA

Earth System Science, Stanford University, Stanford, CA, USA

Water Security Research Group, International Institute for Applied Systems Analysis (IIASA), Laxenburg, Austria

Hylke Beck

https://orcid.org/0000-0003-2553-9566

Climate and Livability Initiative, Physical Science and Engineering Division, King Abdullah University of Science and Technology, Thuwal, Saudi Arabia

Jens de Bruijn

Water Security Research Group, International Institute for Applied Systems Analysis (IIASA), Laxenburg, Austria

Institute for Environmental Studies (IVM), Vrije Universiteit Amsterdam, Amsterdam, the Netherlands

Reetik Kumar Sahu

https://orcid.org/0000-0003-0681-0509

Water Security Research Group, International Institute for Applied Systems Analysis (IIASA), Laxenburg, Austria

Yusuke Satoh

Moon Soul Graduate School of Future Strategy, Korea Advanced Institute of Science and Technology, Daejeon, Republic of Korea

Yoshihide Wada

Biological and Environmental Science and Engineering Division, King Abdullah University of Science and Technology, Thuwal, Saudi Arabia

Jiangtao Liu

https://orcid.org/0000-0002-9219-8354

Civil and Environmental Engineering, Pennsylvania State University, University Park, PA, USA

Ming Pan

https://orcid.org/0000-0003-3350-8719

Center for Western Weather and Water Extremes, Scripps Institution of Oceanography, University of California San Diego, La Jolla, CA, USA

Kathryn Lawson

https://orcid.org/0000-0003-0075-7911

Civil and Environmental Engineering, Pennsylvania State University, University Park, PA, USA

Chaopeng Shen

CORRESPONDING AUTHOR

cshen@engr.psu.edu

https://orcid.org/0000-0002-0685-1901

Civil and Environmental Engineering, Pennsylvania State University, University Park, PA, USA

Viewed

Show all Final revised paper only Preprint only

Total article views: 2,964 (including HTML, PDF, and XML)

HTML	PDF	XML	Total	BibTeX	EndNote
2,141	701	122	2,964	56	56

HTML: 2,141
PDF: 701
XML: 122
Total: 2,964
BibTeX: 56
EndNote: 56

Views and downloads (calculated since 05 Oct 2023)

Cumulative views and downloads (calculated since 05 Oct 2023)

Total article views: 1,227 (including HTML, PDF, and XML)

HTML	PDF	XML	Total	BibTeX	EndNote
1,017	137	73	1,227	14	15

HTML: 1,017
PDF: 137
XML: 73
Total: 1,227
BibTeX: 14
EndNote: 15

Views and downloads (calculated since 26 Sep 2024)

Month	HTML	PDF	XML	Total
Sep 2024	144	23	2	169
Oct 2024	280	46	35	361
Nov 2024	137	25	33	195
Dec 2024	139	9	1	149
Jan 2025	123	13	1	137
Feb 2025	92	12	1	105
Mar 2025	102	9	0	111

Cumulative views and downloads (calculated since 26 Sep 2024)

Month	HTML	PDF	XML	Total
Sep 2024	144	23	2	169
Oct 2024	280	46	35	361
Nov 2024	137	25	33	195
Dec 2024	139	9	1	149
Jan 2025	123	13	1	137
Feb 2025	92	12	1	105
Mar 2025	102	9	0	111

Total article views: 1,737 (including HTML, PDF, and XML)

HTML	PDF	XML	Total	BibTeX	EndNote
1,124	564	49	1,737	42	41

HTML: 1,124
PDF: 564
XML: 49
Total: 1,737
BibTeX: 42
EndNote: 41

Views and downloads (calculated since 05 Oct 2023)

Month	HTML	PDF	XML	Total
Sep 2024	144	23	2	169
Oct 2024	280	46	35	361
Nov 2024	137	25	33	195
Dec 2024	139	9	1	149
Jan 2025	123	13	1	137
Feb 2025	92	12	1	105
Mar 2025	102	9	0	111

Cumulative views and downloads (calculated since 05 Oct 2023)

Month	HTML	PDF	XML	Total
Sep 2024	144	23	2	169
Oct 2024	280	46	35	361
Nov 2024	137	25	33	195
Dec 2024	139	9	1	149
Jan 2025	123	13	1	137
Feb 2025	92	12	1	105
Mar 2025	102	9	0	111

Viewed (geographical distribution)

Show all Final revised paper only Preprint only

Total article views: 2,964 (including HTML, PDF, and XML) Thereof 2,886 with geography defined and 78 with unknown origin.

Total article views: 1,227 (including HTML, PDF, and XML) Thereof 1,178 with geography defined and 49 with unknown origin.

Total article views: 1,737 (including HTML, PDF, and XML) Thereof 1,708 with geography defined and 29 with unknown origin.

Country	#	Views	%
United States of America	1	1071	36
China	2	530	17
Germany	3	179	6
France	4	106	3
Netherlands	5	74	2

Country	#	Views	%
United States of America	1	356	29
China	2	266	21
France	3	54	4
Germany	4	53	4
India	5	42	3

Country	#	Views	%
United States of America	1	715	41
China	2	264	15
Germany	3	126	7
France	4	52	2
Netherlands	5	51	2


Total:	0
HTML:	0
PDF:	0
XML:	0

1
1071

1071


Total:	0
HTML:	0
PDF:	0
XML:	0

356


Total:	0
HTML:	0
PDF:	0
XML:	0

715

Cited

Show all Final revised paper only Preprint only

7 citations as recorded by crossref.

Protocols for Water and Environmental Modeling Using Machine Learning in California M. He et al. 10.3390/hydrology12030059
Fine-tuning long short-term memory models for seamless transition in hydrological modelling: From pre-training to post-application X. Chen et al. 10.1016/j.envsoft.2025.106350
Coupling SWAT+ with LSTM for enhanced and interpretable streamflow estimation in arid and semi-arid watersheds, a case study of the Tagus Headwaters River Basin, Spain S. Asadi et al. 10.1016/j.envsoft.2025.106360
Probing the limit of hydrologic predictability with the Transformer network J. Liu et al. 10.1016/j.jhydrol.2024.131389
Identifying Structural Priors in a Hybrid Differentiable Model for Stream Water Temperature Modeling F. Rahmani et al. 10.1029/2023WR034420
On the need for physical constraints in deep learning rainfall–runoff projections under climate change: a sensitivity analysis to warming and shifts in potential evapotranspiration S. Wi & S. Steinschneider 10.5194/hess-28-479-2024
A comprehensive study of deep learning for soil moisture prediction Y. Wang et al. 10.5194/hess-28-917-2024

3 citations as recorded by crossref.

Protocols for Water and Environmental Modeling Using Machine Learning in California M. He et al. 10.3390/hydrology12030059
Fine-tuning long short-term memory models for seamless transition in hydrological modelling: From pre-training to post-application X. Chen et al. 10.1016/j.envsoft.2025.106350
Coupling SWAT+ with LSTM for enhanced and interpretable streamflow estimation in arid and semi-arid watersheds, a case study of the Tagus Headwaters River Basin, Spain S. Asadi et al. 10.1016/j.envsoft.2025.106360

4 citations as recorded by crossref.

Probing the limit of hydrologic predictability with the Transformer network J. Liu et al. 10.1016/j.jhydrol.2024.131389
Identifying Structural Priors in a Hybrid Differentiable Model for Stream Water Temperature Modeling F. Rahmani et al. 10.1029/2023WR034420
On the need for physical constraints in deep learning rainfall–runoff projections under climate change: a sensitivity analysis to warming and shifts in potential evapotranspiration S. Wi & S. Steinschneider 10.5194/hess-28-479-2024
A comprehensive study of deep learning for soil moisture prediction Y. Wang et al. 10.5194/hess-28-917-2024

Latest update: 01 Apr 2025

Download

Article (4810 KB)
Full-text XML

BibTeX
EndNote

Short summary

Accurate hydrologic modeling is vital to characterizing water cycle responses to climate change. For the first time at this scale, we use differentiable physics-informed machine learning hydrologic models to simulate rainfall–runoff processes for 3753 basins around the world and compare them with purely data-driven and traditional modeling approaches. This sets a benchmark for hydrologic estimates around the world and builds foundations for improving global hydrologic simulations.

Accurate hydrologic modeling is vital to characterizing water cycle responses to climate change....