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://noa.gwlb.de/receive/cop_mods_00068108 https://noa.gwlb.de/servlets/MCRFileNodeServlet/cop_derivate_00066542/gmd-16-4521-2023.pdf https://gmd.copernicus.org/articles/16/4521/2023/gmd-16-4521-2023.pdf |
id |
ftnonlinearchiv:oai:noa.gwlb.de:cop_mods_00068108 |
---|---|
record_format |
openpolar |
spelling |
ftnonlinearchiv:oai:noa.gwlb.de:cop_mods_00068108 2023-09-05T13:17:35+02:00 Automatic snow type classification of snow micropenetrometer profiles with machine learning algorithms Kaltenborn, Julia Macfarlane, Amy R. Clay, Viviane Schneebeli, Martin 2023-08 electronic https://doi.org/10.5194/gmd-16-4521-2023 https://noa.gwlb.de/receive/cop_mods_00068108 https://noa.gwlb.de/servlets/MCRFileNodeServlet/cop_derivate_00066542/gmd-16-4521-2023.pdf https://gmd.copernicus.org/articles/16/4521/2023/gmd-16-4521-2023.pdf eng eng Copernicus Publications Geoscientific Model Development -- http://www.bibliothek.uni-regensburg.de/ezeit/?2456725 -- http://www.geosci-model-dev.net/ -- 1991-9603 https://doi.org/10.5194/gmd-16-4521-2023 https://noa.gwlb.de/receive/cop_mods_00068108 https://noa.gwlb.de/servlets/MCRFileNodeServlet/cop_derivate_00066542/gmd-16-4521-2023.pdf https://gmd.copernicus.org/articles/16/4521/2023/gmd-16-4521-2023.pdf https://creativecommons.org/licenses/by/4.0/ uneingeschränkt info:eu-repo/semantics/openAccess article Verlagsveröffentlichung article Text doc-type:article 2023 ftnonlinearchiv https://doi.org/10.5194/gmd-16-4521-2023 2023-08-13T23:19:56Z 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 Niedersächsisches Online-Archiv NOA Arctic Geoscientific Model Development 16 15 4521 4550 |
institution |
Open Polar |
collection |
Niedersächsisches Online-Archiv NOA |
op_collection_id |
ftnonlinearchiv |
language |
English |
topic |
article Verlagsveröffentlichung |
spellingShingle |
article Verlagsveröffentlichung Kaltenborn, Julia Macfarlane, Amy R. Clay, Viviane Schneebeli, Martin Automatic snow type classification of snow micropenetrometer profiles with machine learning algorithms |
topic_facet |
article Verlagsveröffentlichung |
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 |
Kaltenborn, Julia Macfarlane, Amy R. Clay, Viviane Schneebeli, Martin |
author_facet |
Kaltenborn, Julia Macfarlane, Amy R. Clay, Viviane Schneebeli, Martin |
author_sort |
Kaltenborn, Julia |
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://noa.gwlb.de/receive/cop_mods_00068108 https://noa.gwlb.de/servlets/MCRFileNodeServlet/cop_derivate_00066542/gmd-16-4521-2023.pdf https://gmd.copernicus.org/articles/16/4521/2023/gmd-16-4521-2023.pdf |
geographic |
Arctic |
geographic_facet |
Arctic |
genre |
Arctic Sea ice |
genre_facet |
Arctic Sea ice |
op_relation |
Geoscientific Model Development -- http://www.bibliothek.uni-regensburg.de/ezeit/?2456725 -- http://www.geosci-model-dev.net/ -- 1991-9603 https://doi.org/10.5194/gmd-16-4521-2023 https://noa.gwlb.de/receive/cop_mods_00068108 https://noa.gwlb.de/servlets/MCRFileNodeServlet/cop_derivate_00066542/gmd-16-4521-2023.pdf https://gmd.copernicus.org/articles/16/4521/2023/gmd-16-4521-2023.pdf |
op_rights |
https://creativecommons.org/licenses/by/4.0/ uneingeschränkt info:eu-repo/semantics/openAccess |
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_ |
1776198700775768064 |