Upscaling Snow Accumulation and Ablation Using Machine Learning
Open Access
- 3 September 2025
- journal article
- Published by American Geophysical Union (AGU) in Water Resources Research
- Vol. 61 (9)
Abstract
Hydrologic processes in snowmelt dominated systems are traditionally measured and understood at the point scale. However, snowmelt, sublimation, and snowfall rates exhibit significant spatial variability across larger landscapes. These variations are influenced by local atmospheric and terrain characteristics, which control the deviations between small‐scale measurements and areally averaged responses to spatially heterogeneous mass and energy inputs. Appropriate upscaling relations are needed to translate small‐scale descriptions of snow processes into constitutive relationships that are applicable at larger scales. As a proof of concept, this study examines the temporal and spatial variability of sublimation and snowmelt fluxes in a drainage basin in the Canadian Rockies using machine learning methods. Raven, a hydrological model, generates high‐resolution fluxes and state variables used to train a random forest algorithm. The random forest (RF) algorithm is then applied to estimate coarse resolution fluxes. This study involves estimating spatially averaged results from discretized fine‐scaled models without explicit knowledge of detailed local response, both with and without low‐order statistics of state (e.g., the standard deviation of snow water equivalent). A series of experiments are used to verify that the upscaling methodology can successfully represent the impact of heterogeneity within the system. Spatially averaged forcing estimated from the scale‐appropriate machine learning model is then incorporated into a mass balance equation at a coarse resolution to demonstrate the efficacy of this upscaling methodology.Keywords
Funding Information
- Natural Sciences and Engineering Research Council of Canada (950‐231171)
- Alberta Innovates (212201389)
This publication has 60 references indexed in Scilit:
- Can machine learning accelerate process understanding and decision‐relevant predictions of river water quality?Hydrological Processes, 2022
- Artificial neural networks for water quality soft-sensing in wastewater treatment: a reviewArtificial Intelligence Review, 2021
- Adaptability of machine learning methods and hydrological models to discharge simulations in data-sparse glaciated watershedsJournal of Arid Land, 2021
- Gradient-Based Attribution Methods2019
- A unified approach for process‐based hydrologic modeling: 2. Model implementation and case studiesWater Resources Research, 2015
- Modelling atmospheric and hydrologic processes for assessment of meadow restoration impact on flow and sediment in a sparsely gauged California watershedHydrological Processes, 2013
- Incoming longwave radiation to melting snow: observations, sensitivity and estimation in Northern environmentsHydrological Processes, 2006
- Sub-grid parameterization of snow distribution for an energy and mass balance snow cover modelHydrological Processes, 1999
- An evaluation of snow accumulation and ablation processes for land surface modellingHydrological Processes, 1998
- Scale issues in hydrological modelling: A reviewHydrological Processes, 1995