Automatic snow type classification of snow micropenetrometer profiles with machine learning algorithms

Kaltenborn, Julia; Macfarlane, Amy R.; Clay, Viviane; Schneebeli, Martin

doi:https://doi.org/10.5194/gmd-16-4521-2023

Articles | Volume 16, issue 15

https://doi.org/10.5194/gmd-16-4521-2023

© Author(s) 2023. This work is distributed under
the Creative Commons Attribution 4.0 License.

Special issue:

Benchmark datasets and machine learning algorithms for Earth...

https://doi.org/10.5194/gmd-16-4521-2023

© Author(s) 2023. This work is distributed under
the Creative Commons Attribution 4.0 License.

Articles | Volume 16, issue 15

Development and technical paper

|

10 Aug 2023

Development and technical paper |

| 10 Aug 2023

Automatic snow type classification of snow micropenetrometer profiles with machine learning algorithms

Julia Kaltenborn, Amy R. Macfarlane, Viviane Clay, and Martin Schneebeli

Data sets

Snowpit SnowMicroPen (SMP) force profiles collected during the MOSAiC expedition A. R. Macfarlane, M. Schneebeli, R. Dadic, D. N. Wagner, S. Arndt, D. Clemens-Sewall, S. Hämmerle, H.-R. Hannula, M. Jaggi, N. Kolabutin, D. Krampe, M. Lehning, I. Matero, M. Nicolaus, M. Oggier, R. Pirazzini, C. Polashenski, I. Raphael, J. Regnery, E. Shimanchuck, M. M. Smith, and A. Tavri https://doi.org/10.1594/PANGAEA.935554

Model code and software

liellnima/snowdragon: Snowdragon Release 1.0.0 (v1.0.0) J. Kaltenborn and vclay https://doi.org/10.5281/zenodo.7335813

Pre-trained Models for SMP Classification and Segmentation J. Kaltenborn, J., A. R. Macfarlane, V. Clay, and M. Schneebeli https://doi.org/10.5281/zenodo.7063521

Short summary

Snow layer segmentation and snow grain classification are essential diagnostic tasks for cryospheric applications. A SnowMicroPen (SMP) can be used to that end; however, the manual classification of its profiles becomes infeasible for large datasets. Here, we evaluate how well machine learning models automate this task. Of the 14 models trained on the MOSAiC SMP dataset, the long short-term memory model performed the best. The findings presented here facilitate and accelerate SMP data analysis.