Permafrost Distribution in the Southern Carpathians, Romania, Derived From Machine Learning Modeling
ABSTRACT Computer modeling of sporadic and isolated patches of mountain permafrost distribution is difficult to implement without overestimating it. The main challenge is to determine the very areas where the criteria for permafrost maintenance are met. This paper aims to modeling the permafrost dis...
Published in: | Permafrost and Periglacial Processes |
---|---|
Main Authors: | , , , , , , , , , , , , , , , |
Other Authors: | , |
Format: | Article in Journal/Newspaper |
Language: | English |
Published: |
Wiley
2024
|
Subjects: | |
Online Access: | http://dx.doi.org/10.1002/ppp.2232 https://onlinelibrary.wiley.com/doi/pdf/10.1002/ppp.2232 |
id |
crwiley:10.1002/ppp.2232 |
---|---|
record_format |
openpolar |
spelling |
crwiley:10.1002/ppp.2232 2024-09-15T18:29:18+00:00 Permafrost Distribution in the Southern Carpathians, Romania, Derived From Machine Learning Modeling Popescu, Răzvan Filhol, Simon Etzelmüller, Bernd Vasile, Mirela Pleșoianu, Alin Vîrghileanu, Marina Onaca, Alexandru Șandric, Ionuț Săvulescu, Ionuț Cruceru, Nicolae Vespremeanu‐Stroe, Alfred Westermann, Sebastian Sîrbu, Flavius Mihai, Bogdan Nedelea, Alexandru Gascoin, Simon Norway Grants Universitatea din București 2024 http://dx.doi.org/10.1002/ppp.2232 https://onlinelibrary.wiley.com/doi/pdf/10.1002/ppp.2232 en eng Wiley http://creativecommons.org/licenses/by-nc-nd/4.0/ Permafrost and Periglacial Processes volume 35, issue 3, page 243-261 ISSN 1045-6740 1099-1530 journal-article 2024 crwiley https://doi.org/10.1002/ppp.2232 2024-07-25T04:21:31Z ABSTRACT Computer modeling of sporadic and isolated patches of mountain permafrost distribution is difficult to implement without overestimating it. The main challenge is to determine the very areas where the criteria for permafrost maintenance are met. This paper aims to modeling the permafrost distribution in the Southern Carpathians (SC), a typical marginal periglacial mountain range. For this purpose, a collection of 883 bottom temperature of late winter snow cover (BTS) points was used as a proxy for permafrost presence or absence in order to train several machine learning models. The performances of each model were evaluated with AUC with varying between 0.99 for Maxent and 0.74 for K‐nearest neighbors and most models (five) exhibiting values between 0.82 and 0.86. Other tests such as confusion matrices, sensitivity analyses, data shuffling, and data size reduction tests indicated that Maxent, AdaBoost, and support vector machine offered the best results while logistic regression, neural network, and gradient boosting exhibited rather poor permafrost distributions. The final ensemble median model indicated a total permafrost area of 19.2 km 2 occupying 1%–9% of the alpine area of the studied massifs. NDVI proved crucial for permafrost prediction because it allows delimiting the debris surfaces where permafrost is probable. Article in Journal/Newspaper permafrost Permafrost and Periglacial Processes Wiley Online Library Permafrost and Periglacial Processes 35 3 243 261 |
institution |
Open Polar |
collection |
Wiley Online Library |
op_collection_id |
crwiley |
language |
English |
description |
ABSTRACT Computer modeling of sporadic and isolated patches of mountain permafrost distribution is difficult to implement without overestimating it. The main challenge is to determine the very areas where the criteria for permafrost maintenance are met. This paper aims to modeling the permafrost distribution in the Southern Carpathians (SC), a typical marginal periglacial mountain range. For this purpose, a collection of 883 bottom temperature of late winter snow cover (BTS) points was used as a proxy for permafrost presence or absence in order to train several machine learning models. The performances of each model were evaluated with AUC with varying between 0.99 for Maxent and 0.74 for K‐nearest neighbors and most models (five) exhibiting values between 0.82 and 0.86. Other tests such as confusion matrices, sensitivity analyses, data shuffling, and data size reduction tests indicated that Maxent, AdaBoost, and support vector machine offered the best results while logistic regression, neural network, and gradient boosting exhibited rather poor permafrost distributions. The final ensemble median model indicated a total permafrost area of 19.2 km 2 occupying 1%–9% of the alpine area of the studied massifs. NDVI proved crucial for permafrost prediction because it allows delimiting the debris surfaces where permafrost is probable. |
author2 |
Norway Grants Universitatea din București |
format |
Article in Journal/Newspaper |
author |
Popescu, Răzvan Filhol, Simon Etzelmüller, Bernd Vasile, Mirela Pleșoianu, Alin Vîrghileanu, Marina Onaca, Alexandru Șandric, Ionuț Săvulescu, Ionuț Cruceru, Nicolae Vespremeanu‐Stroe, Alfred Westermann, Sebastian Sîrbu, Flavius Mihai, Bogdan Nedelea, Alexandru Gascoin, Simon |
spellingShingle |
Popescu, Răzvan Filhol, Simon Etzelmüller, Bernd Vasile, Mirela Pleșoianu, Alin Vîrghileanu, Marina Onaca, Alexandru Șandric, Ionuț Săvulescu, Ionuț Cruceru, Nicolae Vespremeanu‐Stroe, Alfred Westermann, Sebastian Sîrbu, Flavius Mihai, Bogdan Nedelea, Alexandru Gascoin, Simon Permafrost Distribution in the Southern Carpathians, Romania, Derived From Machine Learning Modeling |
author_facet |
Popescu, Răzvan Filhol, Simon Etzelmüller, Bernd Vasile, Mirela Pleșoianu, Alin Vîrghileanu, Marina Onaca, Alexandru Șandric, Ionuț Săvulescu, Ionuț Cruceru, Nicolae Vespremeanu‐Stroe, Alfred Westermann, Sebastian Sîrbu, Flavius Mihai, Bogdan Nedelea, Alexandru Gascoin, Simon |
author_sort |
Popescu, Răzvan |
title |
Permafrost Distribution in the Southern Carpathians, Romania, Derived From Machine Learning Modeling |
title_short |
Permafrost Distribution in the Southern Carpathians, Romania, Derived From Machine Learning Modeling |
title_full |
Permafrost Distribution in the Southern Carpathians, Romania, Derived From Machine Learning Modeling |
title_fullStr |
Permafrost Distribution in the Southern Carpathians, Romania, Derived From Machine Learning Modeling |
title_full_unstemmed |
Permafrost Distribution in the Southern Carpathians, Romania, Derived From Machine Learning Modeling |
title_sort |
permafrost distribution in the southern carpathians, romania, derived from machine learning modeling |
publisher |
Wiley |
publishDate |
2024 |
url |
http://dx.doi.org/10.1002/ppp.2232 https://onlinelibrary.wiley.com/doi/pdf/10.1002/ppp.2232 |
genre |
permafrost Permafrost and Periglacial Processes |
genre_facet |
permafrost Permafrost and Periglacial Processes |
op_source |
Permafrost and Periglacial Processes volume 35, issue 3, page 243-261 ISSN 1045-6740 1099-1530 |
op_rights |
http://creativecommons.org/licenses/by-nc-nd/4.0/ |
op_doi |
https://doi.org/10.1002/ppp.2232 |
container_title |
Permafrost and Periglacial Processes |
container_volume |
35 |
container_issue |
3 |
container_start_page |
243 |
op_container_end_page |
261 |
_version_ |
1810470722413264896 |