Preprints
https://doi.org/10.5194/gmd-2023-190
https://doi.org/10.5194/gmd-2023-190
Submitted as: model evaluation paper
 | 
05 Oct 2023
Submitted as: model evaluation paper |  | 05 Oct 2023
Status: this preprint is currently under review for the journal GMD.

Deep Dive into Global Hydrologic Simulations: 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

Abstract. Accurate hydrological modeling is vital to characterizing how the terrestrial water cycle responds to climate change. Pure deep learning (DL) models have shown to outperform process-based ones while remaining difficult to interpret. More recently, differentiable, physics-informed machine learning models with a physical backbone can systematically integrate physical equations and DL, predicting untrained variables and processes with high performance. However, it was unclear if such models are competitive for global-scale applications with a simple backbone. Therefore, we use – for the first time at this scale – differentiable hydrologic models (fullname δHBV-globe1.0-hydroDL and shorthanded δHBV) to simulate the rainfall-runoff processes for 3753 basins around the world. Moreover, we compare the δHBV models to a purely data-driven long short-term memory (LSTM) model to examine their strengths and limitations. Both LSTM and the δHBV models provide competent daily hydrologic simulation capabilities in global basins, with median Kling-Gupta efficiency values close to or higher than 0.7 (and 0.78 with LSTM for a subset of 1675 basins with long-term records), significantly outperforming traditional models. Moreover, regionalized differentiable models demonstrated stronger spatial generalization ability (median KGE 0.64) than a traditional parameter regionalization approach (median KGE 0.46) and even LSTM for ungauged region tests in Europe and South America. Nevertheless, relative to LSTM, the differentiable model was hampered by structural deficiencies for cold or polar regions, and highly arid regions, and basins with significant human impacts. This study also sets the benchmark for hydrologic estimates around the world and builds foundations for improving global hydrologic simulations.

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

Status: final response (author comments only)

Comment types: AC – author | RC – referee | CC – community | EC – editor | CEC – chief editor | : Report abuse
  • RC1: 'Comment on gmd-2023-190', Anonymous Referee #1, 06 Nov 2023
    • AC2: 'Reply on RC1', Chaopeng Shen, 17 Jan 2024
  • CEC1: 'Comment on gmd-2023-190', Juan Antonio Añel, 19 Nov 2023
    • AC1: 'Reply on CEC1', Chaopeng Shen, 08 Jan 2024
  • RC2: 'Comment on gmd-2023-190', Anonymous Referee #2, 10 Jan 2024
    • AC3: 'Reply on RC2', Chaopeng Shen, 17 Jan 2024
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, Hylke Beck, Jens de Bruijn, Reetik Kumar Sahu, Yusuke Satoh, Yoshihide Wada, Jiangtao Liu, Ming Pan, Kathryn Lawson, and Chaopeng Shen

Viewed

Total article views: 937 (including HTML, PDF, and XML)
HTML PDF XML Total BibTeX EndNote
617 295 25 937 17 15
  • HTML: 617
  • PDF: 295
  • XML: 25
  • Total: 937
  • BibTeX: 17
  • EndNote: 15
Views and downloads (calculated since 05 Oct 2023)
Cumulative views and downloads (calculated since 05 Oct 2023)

Viewed (geographical distribution)

Total article views: 897 (including HTML, PDF, and XML) Thereof 897 with geography defined and 0 with unknown origin.
Country # Views %
  • 1
1
 
 
 
 

Cited

Latest update: 24 Feb 2024
Download
Short summary
Accurate hydrological 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 approaches. This sets a benchmark for hydrologic estimates around the world and builds foundations for improving global hydrologic simulations.