Mapping daily snow depth with machine learning and airborne lidar across two contrasting snowpacks

Pan, Caleb G.; Johnston, Jeremy; Jacobs, Jennifer M.; O'Neel, Shad

doi:10.5194/tc-20-3759-2026

Articles | Volume 20, issue 7

https://doi.org/10.5194/tc-20-3759-2026

© Author(s) 2026. This work is distributed under
the Creative Commons Attribution 4.0 License.

https://doi.org/10.5194/tc-20-3759-2026

© Author(s) 2026. This work is distributed under
the Creative Commons Attribution 4.0 License.

Articles | Volume 20, issue 7

Research article

|

03 Jul 2026

Research article |

| 03 Jul 2026

Mapping daily snow depth with machine learning and airborne lidar across two contrasting snowpacks

Caleb G. Pan, Jeremy Johnston, Jennifer M. Jacobs, and Shad O'Neel

Data sets

SnowEx Mores Creek Summit (MCS) Airborne LiDAR Survey. (SNEX_MCS_Lidar, Version 1) S. Ciafone et al. https://doi.org/10.5067/NE8CLN3ES5XQ

Model code and software

Mapping daily snow depth with machine learning and airborne lidar across two contrasting snowpacks C. Pan et al. https://doi.org/10.5281/zenodo.20814771

Short summary

We developed a simple method to turn a few airborne snow-mapping flights and one daily snow record into continuous maps showing how snow depth changes each day. Tested in Idaho and New Hampshire, the approach works well in both deep and shallow snow regions and helps plan when and how often to fly lidar surveys for the best results.