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

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

© Author(s) 2024. This work is distributed under
the Creative Commons Attribution 4.0 License.

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

© Author(s) 2024. This work is distributed under
the Creative Commons Attribution 4.0 License.

Articles | Volume 17, issue 18

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

Data sets

MSWEP GloH2O https://www.gloh2o.org/mswep/

MSWX GloH2O https://www.gloh2o.org/mswx/

European Water Archive (EWA) of EURO-FRIEND-Water GRDC https://grdc.bafg.de/GRDC/EN/04_spcldtbss/42_EWA/ewa.html

Rivers and Catchments of Europe - Catchment Characterisation Model (CCM) A. de Jager and J. Vogt http://data.europa.eu/89h/8c681046-726b-413d-aff8-b1afebd73c0a

MODIS/Terra Net Evapotranspiration Gap-Filled 8-Day L4 Global 500m SIN Grid V061 S. Running et al. https://doi.org/10.5067/MODIS/MOD16A2GF.061

USGS Water Data for the Nation U.S. Geological Survey https://doi.org/10.5066/F7P55KJN

River Discharge Data GRDC https://grdc.bafg.de/GRDC/EN/Home/homepage_node.html

HidroWeb Portal Brazilian Agência Nacional de Águas https://www.snirh.gov.br/hidroweb/apresentacao

National Water Data Archive: HYDAT WSC https://www.canada.ca/en/environment-climate-change/services/water-overview/quantity/monitoring/survey/data-products-services/national-archive-hydat.html

Water Data Online: Water Information Australia BoM http://www.bom.gov.au/waterdata/

Flow Data Chilean CR2 https://www.cr2.cl/datos-de-caudales/

Model code and software

Differentiable hydrologic models: differentiable parameter learning (dPL)+evolved HBV model Dapeng Feng et al. https://doi.org/10.5281/zenodo.7091334

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.