Automatic snow type classification of snow micropenetrometer profiles with machine learning algorithms
Snow-layer segmentation and classification are essential diagnostic tasks for various cryospheric applications. The SnowMicroPen (SMP) measures the snowpack's penetration force at submillimeter intervals in snow depth. The resulting depth–force profile can be parameterized for density and speci...
Published in: | Geoscientific Model Development |
---|---|
Main Authors: | , , , |
Format: | Article in Journal/Newspaper |
Language: | English |
Published: |
Copernicus Publications
2023
|
Subjects: | |
Online Access: | https://doi.org/10.5194/gmd-16-4521-2023 https://doaj.org/article/d9c7562cbc8141f386f541494ec993f8 |
id |
ftdoajarticles:oai:doaj.org/article:d9c7562cbc8141f386f541494ec993f8 |
---|---|
record_format |
openpolar |
spelling |
ftdoajarticles:oai:doaj.org/article:d9c7562cbc8141f386f541494ec993f8 2023-09-05T13:17:38+02:00 Automatic snow type classification of snow micropenetrometer profiles with machine learning algorithms J. Kaltenborn A. R. Macfarlane V. Clay M. Schneebeli 2023-08-01T00:00:00Z https://doi.org/10.5194/gmd-16-4521-2023 https://doaj.org/article/d9c7562cbc8141f386f541494ec993f8 EN eng Copernicus Publications https://gmd.copernicus.org/articles/16/4521/2023/gmd-16-4521-2023.pdf https://doaj.org/toc/1991-959X https://doaj.org/toc/1991-9603 doi:10.5194/gmd-16-4521-2023 1991-959X 1991-9603 https://doaj.org/article/d9c7562cbc8141f386f541494ec993f8 Geoscientific Model Development, Vol 16, Pp 4521-4550 (2023) Geology QE1-996.5 article 2023 ftdoajarticles https://doi.org/10.5194/gmd-16-4521-2023 2023-08-13T00:35:56Z Snow-layer segmentation and classification are essential diagnostic tasks for various cryospheric applications. The SnowMicroPen (SMP) measures the snowpack's penetration force at submillimeter intervals in snow depth. The resulting depth–force profile can be parameterized for density and specific surface area. However, no information on traditional snow types is currently extracted automatically. The labeling of snow types is a time-intensive task that requires practice and becomes infeasible for large datasets. Previous work showed that automated segmentation and classification is, in theory, possible but cannot be applied to data straight from the field or needs additional time-costly information, such as from classified snow pits. We evaluate how well machine learning models can automatically segment and classify SMP profiles to address this gap. We trained 14 models, among them semi-supervised models and artificial neural networks (ANNs), on the MOSAiC SMP dataset, an extensive collection of snow profiles on Arctic sea ice. SMP profiles can be successfully segmented and classified into snow classes based solely on the SMP's signal. The model comparison provided in this study enables SMP users to choose a suitable model for their task and dataset. The findings presented will facilitate and accelerate snow type identification through SMP profiles. Anyone can access the tools and models needed to automate snow type identification via the software repository “snowdragon”. Overall, snowdragon creates a link between traditional snow classification and high-resolution force–depth profiles. Traditional snow profile observations can be compared to SMP profiles with such a tool. Article in Journal/Newspaper Arctic Sea ice Directory of Open Access Journals: DOAJ Articles Arctic Geoscientific Model Development 16 15 4521 4550 |
institution |
Open Polar |
collection |
Directory of Open Access Journals: DOAJ Articles |
op_collection_id |
ftdoajarticles |
language |
English |
topic |
Geology QE1-996.5 |
spellingShingle |
Geology QE1-996.5 J. Kaltenborn A. R. Macfarlane V. Clay M. Schneebeli Automatic snow type classification of snow micropenetrometer profiles with machine learning algorithms |
topic_facet |
Geology QE1-996.5 |
description |
Snow-layer segmentation and classification are essential diagnostic tasks for various cryospheric applications. The SnowMicroPen (SMP) measures the snowpack's penetration force at submillimeter intervals in snow depth. The resulting depth–force profile can be parameterized for density and specific surface area. However, no information on traditional snow types is currently extracted automatically. The labeling of snow types is a time-intensive task that requires practice and becomes infeasible for large datasets. Previous work showed that automated segmentation and classification is, in theory, possible but cannot be applied to data straight from the field or needs additional time-costly information, such as from classified snow pits. We evaluate how well machine learning models can automatically segment and classify SMP profiles to address this gap. We trained 14 models, among them semi-supervised models and artificial neural networks (ANNs), on the MOSAiC SMP dataset, an extensive collection of snow profiles on Arctic sea ice. SMP profiles can be successfully segmented and classified into snow classes based solely on the SMP's signal. The model comparison provided in this study enables SMP users to choose a suitable model for their task and dataset. The findings presented will facilitate and accelerate snow type identification through SMP profiles. Anyone can access the tools and models needed to automate snow type identification via the software repository “snowdragon”. Overall, snowdragon creates a link between traditional snow classification and high-resolution force–depth profiles. Traditional snow profile observations can be compared to SMP profiles with such a tool. |
format |
Article in Journal/Newspaper |
author |
J. Kaltenborn A. R. Macfarlane V. Clay M. Schneebeli |
author_facet |
J. Kaltenborn A. R. Macfarlane V. Clay M. Schneebeli |
author_sort |
J. Kaltenborn |
title |
Automatic snow type classification of snow micropenetrometer profiles with machine learning algorithms |
title_short |
Automatic snow type classification of snow micropenetrometer profiles with machine learning algorithms |
title_full |
Automatic snow type classification of snow micropenetrometer profiles with machine learning algorithms |
title_fullStr |
Automatic snow type classification of snow micropenetrometer profiles with machine learning algorithms |
title_full_unstemmed |
Automatic snow type classification of snow micropenetrometer profiles with machine learning algorithms |
title_sort |
automatic snow type classification of snow micropenetrometer profiles with machine learning algorithms |
publisher |
Copernicus Publications |
publishDate |
2023 |
url |
https://doi.org/10.5194/gmd-16-4521-2023 https://doaj.org/article/d9c7562cbc8141f386f541494ec993f8 |
geographic |
Arctic |
geographic_facet |
Arctic |
genre |
Arctic Sea ice |
genre_facet |
Arctic Sea ice |
op_source |
Geoscientific Model Development, Vol 16, Pp 4521-4550 (2023) |
op_relation |
https://gmd.copernicus.org/articles/16/4521/2023/gmd-16-4521-2023.pdf https://doaj.org/toc/1991-959X https://doaj.org/toc/1991-9603 doi:10.5194/gmd-16-4521-2023 1991-959X 1991-9603 https://doaj.org/article/d9c7562cbc8141f386f541494ec993f8 |
op_doi |
https://doi.org/10.5194/gmd-16-4521-2023 |
container_title |
Geoscientific Model Development |
container_volume |
16 |
container_issue |
15 |
container_start_page |
4521 |
op_container_end_page |
4550 |
_version_ |
1776198735410233344 |