18 Feb 2022
18 Feb 2022
Status: this preprint is currently under review for the journal HESS.

Leveraging sap flow data in a catchment-scale hybrid model to improve soil moisture and transpiration estimates

Ralf Loritz1, Maoya Bassiouni2,3, Anke Hildebrandt4,5,6, Sibylle K. Hassler1,5, and Erwin Zehe1 Ralf Loritz et al.
  • 1Karlsruhe Institute of Technology (KIT), Institute of Water and River Basin Management - Hydrology, Karlsruhe, Germany
  • 2Department of Crop Production Ecology, Swedish University of Agricultural Sciences, Uppsala, Sweden
  • 3Department of Environmental Science, Policy and Management, University of California, Berkeley, CA, USA
  • 4Helmholtz Centre for Environmental Research – UFZ, Department Computational Hydrosystems, Leipzig, Germany
  • 5Karlsruhe Institute of Technology (KIT), Institute of Meteorology and Climate Research – Atmospheric Trace Gases and Remote Sensing, Karlsruhe, Germany
  • 6Friedrich Schiller University Jena, Institute of Geoscience, Jena, Germany

Abstract. Sap flow encodes information about how plants regulate opening and closing of stomata in response to varying soil water supply and atmospheric water demand. This study leverages this valuable information with data-model integration and deep learning to estimate canopy conductance in a hybrid catchment-scale model for more accurate hydrological simulations. Using data from three consecutive growing seasons, we first highlight that integrating canopy conductance inferred from sap flow data in a hydrological model leads to more realistic soil moisture estimates than using the conventional Jarvis-Stewart equation, particularly during drought conditions. The applicability of this first approach is, however, limited to the period where sap flow data are available. To overcome this limitation, we subsequently train a deep learning network to predict catchment-averaged sap velocities based on standard hourly meteorological data. These simulated velocities are then used to estimate canopy conductance, allowing simulations for periods without sap flow data. We show that the hybrid model, which uses the canopy conductance from the machine learning approach, matches soil moisture and transpiration equally well as model runs using observed sap flow data and has good potential for extrapolation beyond the study site. We conclude that such hybrid approaches open promising perspectives for more parsimonious process parametrizations by improving our ability to incorporate novel or untypical data sets into hydrological models.

Ralf Loritz et al.

Status: final response (author comments only)

Comment types: AC – author | RC – referee | CC – community | EC – editor | CEC – chief editor | : Report abuse
  • RC1: 'Comment on hess-2022-62', Anonymous Referee #1, 05 Apr 2022
  • RC2: 'Comment on hess-2022-62', Anonymous Referee #2, 19 Apr 2022

Ralf Loritz et al.

Ralf Loritz et al.


Total article views: 561 (including HTML, PDF, and XML)
HTML PDF XML Total BibTeX EndNote
429 118 14 561 6 6
  • HTML: 429
  • PDF: 118
  • XML: 14
  • Total: 561
  • BibTeX: 6
  • EndNote: 6
Views and downloads (calculated since 18 Feb 2022)
Cumulative views and downloads (calculated since 18 Feb 2022)

Viewed (geographical distribution)

Total article views: 477 (including HTML, PDF, and XML) Thereof 477 with geography defined and 0 with unknown origin.
Country # Views %
  • 1
Latest update: 26 May 2022
Short summary
In this study, we highlight that integrating sap flow data in a hydrological model can lead to more accurate hydrological simulations. We, furthermore, combine a deep learning network with a hydrological model and show that such hybrid models are a promising way to improve our ability to make hydrological simulations.