Submitted as: model description paper
01 Aug 2023
Submitted as: model description paper |  | 01 Aug 2023
Status: this preprint is currently under review for the journal GMD.

GEMS v1.0: Generalizable empirical model of snow accumulation and melt based on daily snow mass changes in response to climate and topographic drivers

Atabek Umirbekov, Richard Essery, and Daniel Müller

Abstract. Snow modeling is often hampered by the availability of input and calibration data, which can affect the choice of model complexity and its transferability. To address the trade-off between model parsimony and transferability, we present the Generalizable Empirical Model of Snow Accumulation and Melt (GEMS), a machine learning-based model that requires only daily precipitation, temperature or its daily diurnal cycle, and basic topographic features to simulate snow water equivalent. The model embeds a Support Vector Regression pretrained on a large dataset of daily observations from a diverse set of the Snowpack Telemetry Network (SNOTEL) stations in the United States. GEMS does not require any user calibration, except for the option to adjust the temperature threshold for rain-snow partitioning, though the model achieves robust simulation results with the default value. We validated the model with long term daily observations from numerous independent SNOTEL stations not included in the training and with data from reference stations of the Earth System Model-Snow Model Intercomparison Project. We demonstrate how the model advances large scale SWE modelling in regions with complex terrain that lack in-situ snow mass observations for calibration, such as the Pamir and Andes, by assessing the model`s ability to reproduce daily snow cover dynamics. Future model development should consider the effects of vegetation, improve simulation accuracy for shallow snow in warm locations at lower elevations and address wind-induced snow redistribution. Overall, GEMS provides a new approach for snow modeling that can be useful for hydro-climatic research and operational monitoring in regions where in-situ snow observations are scarce.

Atabek Umirbekov 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 gmd-2023-103', Matthieu Lafaysse, 10 Aug 2023
  • RC2: 'Comment on gmd-2023-103', Anonymous Referee #2, 21 Sep 2023

Atabek Umirbekov et al.

Atabek Umirbekov et al.


Total article views: 279 (including HTML, PDF, and XML)
HTML PDF XML Total BibTeX EndNote
214 55 10 279 4 2
  • HTML: 214
  • PDF: 55
  • XML: 10
  • Total: 279
  • BibTeX: 4
  • EndNote: 2
Views and downloads (calculated since 01 Aug 2023)
Cumulative views and downloads (calculated since 01 Aug 2023)

Viewed (geographical distribution)

Total article views: 248 (including HTML, PDF, and XML) Thereof 248 with geography defined and 0 with unknown origin.
Country # Views %
  • 1
Latest update: 03 Oct 2023
Short summary
We present a new snow model which simulates snow mass without the need for extensive calibration. The model is based on a machine learning algorithm that has been trained on diverse set of daily observations of snow accumulation or melt, along with corresponding climate and topography data. We validated the model using in-situ data from numerous new locations. The model provides a promising solution for accurate snow mass estimation across regions where in-situ data is limited.