A Machine learning framework to automate the classification of surge-type glaciers in Svalbard
Surge-type glaciers are present in many cold environments in the world. These glaciers experience a dramatic increase in velocity over short time periods, the surge, followed by an extended period of slow movement, the quiescence. This study aims at understanding why only few glaciers exhibit a tran...
Published in: | Journal of Geophysical Research: Earth Surface |
---|---|
Main Authors: | , , , , |
Format: | Article in Journal/Newspaper |
Language: | English |
Published: |
2022
|
Subjects: | |
Online Access: | http://hdl.handle.net/10852/99961 https://doi.org/10.1029/2022JF006597 |
id |
ftoslouniv:oai:www.duo.uio.no:10852/99961 |
---|---|
record_format |
openpolar |
spelling |
ftoslouniv:oai:www.duo.uio.no:10852/99961 2023-05-15T16:22:07+02:00 A Machine learning framework to automate the classification of surge-type glaciers in Svalbard ENEngelskEnglishA Machine learning framework to automate the classification of surge-type glaciers in Svalbard Bouchayer, Coline Lili Mathy Aiken, J.M. Thøgersen, Kjetil Renard, Francois Schuler, Thomas 2022-09-12T10:29:09Z http://hdl.handle.net/10852/99961 https://doi.org/10.1029/2022JF006597 EN eng NFR/301837 Bouchayer, Coline Lili Mathy Aiken, J.M. Thøgersen, Kjetil Renard, Francois Schuler, Thomas . A Machine learning framework to automate the classification of surge-type glaciers in Svalbard. Journal of Geophysical Research (JGR): Earth Surface. 2022, 127 http://hdl.handle.net/10852/99961 2050659 info:ofi/fmt:kev:mtx:ctx&ctx_ver=Z39.88-2004&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.jtitle=Journal of Geophysical Research (JGR): Earth Surface&rft.volume=127&rft.spage=&rft.date=2022 Journal of Geophysical Research (JGR): Earth Surface 127 7 https://doi.org/10.1029/2022JF006597 Attribution 4.0 International https://creativecommons.org/licenses/by/4.0/ CC-BY 2169-9003 Journal article Tidsskriftartikkel Peer reviewed PublishedVersion 2022 ftoslouniv https://doi.org/10.1029/2022JF006597 2023-02-15T23:36:40Z Surge-type glaciers are present in many cold environments in the world. These glaciers experience a dramatic increase in velocity over short time periods, the surge, followed by an extended period of slow movement, the quiescence. This study aims at understanding why only few glaciers exhibit a transient behavior. We develop a machine learning framework to classify surge-type glaciers, based on their location, exposure, geometry, climatic mass balance and runoff. We apply this approach to the Svalbard archipelago, a region with a relatively homogeneous climate. We compare the performance of logistic regression, random forest, and extreme gradient boosting (XGBoost) machine learning models that we apply to a newly combined database of glaciers in Svalbard. Based on the most accurate model, XGBoost, we compute surge probabilities along glacier centerlines and quantify the relative importance of several controlling features. Results show that the surface and bed slopes, ice thickness, glacier width, climatic mass balance, and runoff along glacier centerlines are the most significant features explaining surge probability for glaciers in Svalbard. A thicker and wider glacier with a low surface slope has a higher probability to be classified as surge-type, which is in good agreement with the existing theories of surging. Finally, we build a probability map of surge-type glaciers in Svalbard. The framework shows robustness on classifying surge-type glaciers that were not previously classified as such in existing inventories but have been observed surging. Our methodology could be extended to classify surge-type glaciers in other areas of the world. Article in Journal/Newspaper glacier Svalbard Universitet i Oslo: Digitale utgivelser ved UiO (DUO) Svalbard Svalbard Archipelago Journal of Geophysical Research: Earth Surface 127 7 |
institution |
Open Polar |
collection |
Universitet i Oslo: Digitale utgivelser ved UiO (DUO) |
op_collection_id |
ftoslouniv |
language |
English |
description |
Surge-type glaciers are present in many cold environments in the world. These glaciers experience a dramatic increase in velocity over short time periods, the surge, followed by an extended period of slow movement, the quiescence. This study aims at understanding why only few glaciers exhibit a transient behavior. We develop a machine learning framework to classify surge-type glaciers, based on their location, exposure, geometry, climatic mass balance and runoff. We apply this approach to the Svalbard archipelago, a region with a relatively homogeneous climate. We compare the performance of logistic regression, random forest, and extreme gradient boosting (XGBoost) machine learning models that we apply to a newly combined database of glaciers in Svalbard. Based on the most accurate model, XGBoost, we compute surge probabilities along glacier centerlines and quantify the relative importance of several controlling features. Results show that the surface and bed slopes, ice thickness, glacier width, climatic mass balance, and runoff along glacier centerlines are the most significant features explaining surge probability for glaciers in Svalbard. A thicker and wider glacier with a low surface slope has a higher probability to be classified as surge-type, which is in good agreement with the existing theories of surging. Finally, we build a probability map of surge-type glaciers in Svalbard. The framework shows robustness on classifying surge-type glaciers that were not previously classified as such in existing inventories but have been observed surging. Our methodology could be extended to classify surge-type glaciers in other areas of the world. |
format |
Article in Journal/Newspaper |
author |
Bouchayer, Coline Lili Mathy Aiken, J.M. Thøgersen, Kjetil Renard, Francois Schuler, Thomas |
spellingShingle |
Bouchayer, Coline Lili Mathy Aiken, J.M. Thøgersen, Kjetil Renard, Francois Schuler, Thomas A Machine learning framework to automate the classification of surge-type glaciers in Svalbard |
author_facet |
Bouchayer, Coline Lili Mathy Aiken, J.M. Thøgersen, Kjetil Renard, Francois Schuler, Thomas |
author_sort |
Bouchayer, Coline Lili Mathy |
title |
A Machine learning framework to automate the classification of surge-type glaciers in Svalbard |
title_short |
A Machine learning framework to automate the classification of surge-type glaciers in Svalbard |
title_full |
A Machine learning framework to automate the classification of surge-type glaciers in Svalbard |
title_fullStr |
A Machine learning framework to automate the classification of surge-type glaciers in Svalbard |
title_full_unstemmed |
A Machine learning framework to automate the classification of surge-type glaciers in Svalbard |
title_sort |
machine learning framework to automate the classification of surge-type glaciers in svalbard |
publishDate |
2022 |
url |
http://hdl.handle.net/10852/99961 https://doi.org/10.1029/2022JF006597 |
geographic |
Svalbard Svalbard Archipelago |
geographic_facet |
Svalbard Svalbard Archipelago |
genre |
glacier Svalbard |
genre_facet |
glacier Svalbard |
op_source |
2169-9003 |
op_relation |
NFR/301837 Bouchayer, Coline Lili Mathy Aiken, J.M. Thøgersen, Kjetil Renard, Francois Schuler, Thomas . A Machine learning framework to automate the classification of surge-type glaciers in Svalbard. Journal of Geophysical Research (JGR): Earth Surface. 2022, 127 http://hdl.handle.net/10852/99961 2050659 info:ofi/fmt:kev:mtx:ctx&ctx_ver=Z39.88-2004&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.jtitle=Journal of Geophysical Research (JGR): Earth Surface&rft.volume=127&rft.spage=&rft.date=2022 Journal of Geophysical Research (JGR): Earth Surface 127 7 https://doi.org/10.1029/2022JF006597 |
op_rights |
Attribution 4.0 International https://creativecommons.org/licenses/by/4.0/ |
op_rightsnorm |
CC-BY |
op_doi |
https://doi.org/10.1029/2022JF006597 |
container_title |
Journal of Geophysical Research: Earth Surface |
container_volume |
127 |
container_issue |
7 |
_version_ |
1766010100165640192 |