Articles | Volume 19, issue 10
https://doi.org/10.5194/tc-19-4585-2025
https://doi.org/10.5194/tc-19-4585-2025
Research article
 | 
16 Oct 2025
Research article |  | 16 Oct 2025

UAV LiDAR surveys and machine learning improve snow depth and water equivalent estimates in boreal landscapes

Maiju Ylönen, Hannu Marttila, Joschka Geissler, Anton Kuzmin, Pasi Korpelainen, Timo Kumpula, and Pertti Ala-Aho

Data sets

UAV LiDAR snow depth maps, model inputs and outputs for daily snow depth and SWE in Pallas and Sodankylä, Finland (winter 2023–2024) Anton Kuzmin et al. https://doi.org/10.23729/fd-561771be-24b6-354b-bdd7-1b2bb6068308

Model code and software

ClustSnow Joschka Geissler https://doi.org/10.5281/zenodo.14214935

Download
Short summary
We collected snow depth maps four times during the winter from two different sites and used them as input for a model to predict daily snow depth and snow water equivalent (SWE). Our results show similar snow depth patterns at different sites, with snow depths being the highest in forests and forest gaps and the lowest in open areas. The results can extend operational snow course measurements and their temporal and spatial coverage, helping hydrological forecasting and water resource management.
Share