Articles | Volume 27, issue 12
https://doi.org/10.5194/hess-27-2357-2023
https://doi.org/10.5194/hess-27-2357-2023
Research article
 | 
30 Jun 2023
Research article |  | 30 Jun 2023

The suitability of differentiable, physics-informed machine learning hydrologic models for ungauged regions and climate change impact assessment

Dapeng Feng, Hylke Beck, Kathryn Lawson, and Chaopeng Shen

Related authors

When ancient numerical demons meet physics-informed machine learning: adjoint-based gradients for implicit differentiable modeling
Yalan Song, Wouter J. M. Knoben, Martyn P. Clark, Dapeng Feng, Kathryn E. Lawson, and Chaopeng Shen
Hydrol. Earth Syst. Sci. Discuss., https://doi.org/10.5194/hess-2023-258,https://doi.org/10.5194/hess-2023-258, 2023
Preprint under review for HESS
Short summary
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
Geosci. Model Dev. Discuss., https://doi.org/10.5194/gmd-2023-190,https://doi.org/10.5194/gmd-2023-190, 2023
Preprint under review for GMD
Short summary
On the time scale of meteorological, soil moisture, and snow drought indices to assess streamflow drought over catchments with different hydrological regime: a case study using a hundred Chilean catchments
Oscar M. Baez-Villanueva, Mauricio Zambrano-Bigiarini, Diego G. Miralles, Hylke E. Beck, Jonatan F. Siegmund, Camila Alvarez-Garreton, Koen Verbist, René Garreaud, Juan Pablo Boisier, and Mauricio Galleguillos
EGUsphere, https://doi.org/10.5194/egusphere-2023-1911,https://doi.org/10.5194/egusphere-2023-1911, 2023
Short summary
Technical note: Surface fields for global environmental modelling
Margarita Choulga, Francesca Moschini, Cinzia Mazzetti, Stefania Grimaldi, Juliana Disperati, Hylke Beck, Peter Salamon, and Christel Prudhomme
EGUsphere, https://doi.org/10.5194/egusphere-2023-1306,https://doi.org/10.5194/egusphere-2023-1306, 2023
Short summary
Metamorphic Testing of Machine Learning and Conceptual Hydrologic Models
Peter Reichert, Kai Ma, Marvin Höge, Fabrizio Fenicia, Marco Baity-Jesi, Dapeng Feng, and Chaopeng Shen
Hydrol. Earth Syst. Sci. Discuss., https://doi.org/10.5194/hess-2023-168,https://doi.org/10.5194/hess-2023-168, 2023
Preprint under review for HESS
Short summary

Related subject area

Subject: Catchment hydrology | Techniques and Approaches: Modelling approaches
Modelling flood frequency and magnitude in a glacially conditioned, heterogeneous landscape: testing the importance of land cover and land use
Pamela E. Tetford and Joseph R. Desloges
Hydrol. Earth Syst. Sci., 27, 3977–3998, https://doi.org/10.5194/hess-27-3977-2023,https://doi.org/10.5194/hess-27-3977-2023, 2023
Short summary
Direct integration of reservoirs' operations in a hydrological model for streamflow estimation: coupling a CLSTM model with MOHID-Land
Ana Ramos Oliveira, Tiago Brito Ramos, Lígia Pinto, and Ramiro Neves
Hydrol. Earth Syst. Sci., 27, 3875–3893, https://doi.org/10.5194/hess-27-3875-2023,https://doi.org/10.5194/hess-27-3875-2023, 2023
Short summary
Modelling the regional sensitivity of snowmelt, soil moisture, and streamflow generation to climate over the Canadian Prairies using a basin classification approach
Zhihua He, Kevin Shook, Christopher Spence, John W. Pomeroy, and Colin Whitfield
Hydrol. Earth Syst. Sci., 27, 3525–3546, https://doi.org/10.5194/hess-27-3525-2023,https://doi.org/10.5194/hess-27-3525-2023, 2023
Short summary
To what extent does river routing matter in hydrological modeling?
Nicolás Cortés-Salazar, Nicolás Vásquez, Naoki Mizukami, Pablo A. Mendoza, and Ximena Vargas
Hydrol. Earth Syst. Sci., 27, 3505–3524, https://doi.org/10.5194/hess-27-3505-2023,https://doi.org/10.5194/hess-27-3505-2023, 2023
Short summary
Calibrating macroscale hydrological models in poorly gauged and heavily regulated basins
Dung Trung Vu, Thanh Duc Dang, Francesca Pianosi, and Stefano Galelli
Hydrol. Earth Syst. Sci., 27, 3485–3504, https://doi.org/10.5194/hess-27-3485-2023,https://doi.org/10.5194/hess-27-3485-2023, 2023
Short summary

Cited articles

Addor, N., Newman, A. J., Mizukami, N., and Clark, M. P.: Catchment attributes for large-sample studies, UCAR/NCAR[data set], https://doi.org/10.5065/D6G73C3Q, 2017. 
Aghakouchak, A. and Habib, E.: Application of a Conceptual Hydrologic Model in Teaching Hydrologic Processes, Int. J. Eng. Educ., 26, 963–973, 2010. 
Baker, N., Alexander, F., Bremer, T., Hagberg, A., Kevrekidis, Y., Najm, H., Parashar, M., Patra, A., Sethian, J., Wild, S., Willcox, K., and Lee, S.: Workshop report on basic research needs for scientific machine learning: Core technologies for artificial intelligence, USDOE Office of Science (SC), Washington, D.C., USA, https://doi.org/10.2172/1478744, 2019. 
Baydin, A. G., Pearlmutter, B. A., Radul, A. A., and Siskind, J. M.: Automatic differentiation in machine learning: A survey, J. Mach. Learn. Res., 18, 1–43, 2018. 
Beck, H. E., van Dijk, A. I. J. M., de Roo, A., Miralles, D. G., McVicar, T. R., Schellekens, J., and Bruijnzeel, L. A.: Global-scale regionalization of hydrologic model parameters, Water Resour. Res., 52, 3599–3622, https://doi.org/10.1002/2015WR018247, 2016. 
Download
Short summary
Powerful hybrid models (called δ or delta models) embrace the fundamental learning capability of AI and can also explain the physical processes. Here we test their performance when applied to regions not in the training data. δ models rivaled the accuracy of state-of-the-art AI models under the data-dense scenario and even surpassed them for the data-sparse one. They generalize well due to the physical structure included. δ models could be ideal candidates for global hydrologic assessment.