Assessing machine learning models to generate permafrost distribution map in Solukhumbu, Nepal

Permafrost is one of the key components of the cryosphere. Previous studies show that the extent of permafrost has shifted to higher elevations in Nepal. These researches, however, has been hampered by inconsistency in their study period. Proxies like rock glaciers and climatic variables, such as mu...

Full description

Saved in:
Bibliographic Details
Main Authors: Arnab Singh, Dibas Shrestha, Kaman Ghimire, Sangya Mishra, Darwin Rana, Sunil Acharya
Format: Article
Language:English
Published: KeAi Communications Co., Ltd. 2025-05-01
Series:Geodesy and Geodynamics
Subjects:
Online Access:http://www.sciencedirect.com/science/article/pii/S1674984724001010
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849309925931483136
author Arnab Singh
Dibas Shrestha
Kaman Ghimire
Sangya Mishra
Darwin Rana
Sunil Acharya
author_facet Arnab Singh
Dibas Shrestha
Kaman Ghimire
Sangya Mishra
Darwin Rana
Sunil Acharya
author_sort Arnab Singh
collection DOAJ
description Permafrost is one of the key components of the cryosphere. Previous studies show that the extent of permafrost has shifted to higher elevations in Nepal. These researches, however, has been hampered by inconsistency in their study period. Proxies like rock glaciers and climatic variables, such as multi-decadal annual air temperature, are used to link towards the likely occurrence of permafrost. Here, the rock glacier inventory of Solukhumbu was prepared, and classified based on their activity (Intact/Relict) from Google Earth. Talus-based rock glaciers were observed more than glacier-derived ones. These rock glaciers were highly correlated with Mean Annual Air Temperature, followed by potential incoming solar radiation and slope. Three machine learning models (Logistic Regression, Random Forest and Support Vector Machines) were trained to generate permafrost probability distribution maps based on their prediction of the probability of rock glaciers being intact as opposed to relict. Logistic Regression and Support Vector Machines were able to produce a similar spatial distribution of permafrost. However, the Random Forest has low precision of spatial variation. The permafrost distribution map suggests the likely occurrence of permafrost to be above 5000 m, indicating a potential for rock and landslides should it thaw in the future. While higher-resolution input data can improve the results, this approach remains promising for application in permafrost regions where information about the ice content of rock glaciers is very limited.
format Article
id doaj-art-e133168c4e5c47e7a7c2e6467fdf5ec0
institution Kabale University
issn 1674-9847
language English
publishDate 2025-05-01
publisher KeAi Communications Co., Ltd.
record_format Article
series Geodesy and Geodynamics
spelling doaj-art-e133168c4e5c47e7a7c2e6467fdf5ec02025-08-20T03:53:56ZengKeAi Communications Co., Ltd.Geodesy and Geodynamics1674-98472025-05-0116327528710.1016/j.geog.2024.08.003Assessing machine learning models to generate permafrost distribution map in Solukhumbu, NepalArnab Singh0Dibas Shrestha1Kaman Ghimire2Sangya Mishra3Darwin Rana4Sunil Acharya5Central Department of Hydrology and Meteorology, Tribhuvan University, Kathmandu, Nepal; Department of Geography and Environment Studies, Wilfrid Laurier University, Ontario, CanadaCentral Department of Hydrology and Meteorology, Tribhuvan University, Kathmandu, Nepal; Corresponding author.Institute of Tibetan Plateau Research, Chinese Academy of Sciences, Beijing 100101, ChinaCentral Department of Hydrology and Meteorology, Tribhuvan University, Kathmandu, NepalCentral Department of Hydrology and Meteorology, Tribhuvan University, Kathmandu, NepalCentral Department of Hydrology and Meteorology, Tribhuvan University, Kathmandu, Nepal; Kathmandu Centre for Research and Education, Tribhuvan University-Chinese Academy of Sciences, Kathmandu, NepalPermafrost is one of the key components of the cryosphere. Previous studies show that the extent of permafrost has shifted to higher elevations in Nepal. These researches, however, has been hampered by inconsistency in their study period. Proxies like rock glaciers and climatic variables, such as multi-decadal annual air temperature, are used to link towards the likely occurrence of permafrost. Here, the rock glacier inventory of Solukhumbu was prepared, and classified based on their activity (Intact/Relict) from Google Earth. Talus-based rock glaciers were observed more than glacier-derived ones. These rock glaciers were highly correlated with Mean Annual Air Temperature, followed by potential incoming solar radiation and slope. Three machine learning models (Logistic Regression, Random Forest and Support Vector Machines) were trained to generate permafrost probability distribution maps based on their prediction of the probability of rock glaciers being intact as opposed to relict. Logistic Regression and Support Vector Machines were able to produce a similar spatial distribution of permafrost. However, the Random Forest has low precision of spatial variation. The permafrost distribution map suggests the likely occurrence of permafrost to be above 5000 m, indicating a potential for rock and landslides should it thaw in the future. While higher-resolution input data can improve the results, this approach remains promising for application in permafrost regions where information about the ice content of rock glaciers is very limited.http://www.sciencedirect.com/science/article/pii/S1674984724001010Rock glaciersLogistic regressionRandom forestSupport vector machines
spellingShingle Arnab Singh
Dibas Shrestha
Kaman Ghimire
Sangya Mishra
Darwin Rana
Sunil Acharya
Assessing machine learning models to generate permafrost distribution map in Solukhumbu, Nepal
Geodesy and Geodynamics
Rock glaciers
Logistic regression
Random forest
Support vector machines
title Assessing machine learning models to generate permafrost distribution map in Solukhumbu, Nepal
title_full Assessing machine learning models to generate permafrost distribution map in Solukhumbu, Nepal
title_fullStr Assessing machine learning models to generate permafrost distribution map in Solukhumbu, Nepal
title_full_unstemmed Assessing machine learning models to generate permafrost distribution map in Solukhumbu, Nepal
title_short Assessing machine learning models to generate permafrost distribution map in Solukhumbu, Nepal
title_sort assessing machine learning models to generate permafrost distribution map in solukhumbu nepal
topic Rock glaciers
Logistic regression
Random forest
Support vector machines
url http://www.sciencedirect.com/science/article/pii/S1674984724001010
work_keys_str_mv AT arnabsingh assessingmachinelearningmodelstogeneratepermafrostdistributionmapinsolukhumbunepal
AT dibasshrestha assessingmachinelearningmodelstogeneratepermafrostdistributionmapinsolukhumbunepal
AT kamanghimire assessingmachinelearningmodelstogeneratepermafrostdistributionmapinsolukhumbunepal
AT sangyamishra assessingmachinelearningmodelstogeneratepermafrostdistributionmapinsolukhumbunepal
AT darwinrana assessingmachinelearningmodelstogeneratepermafrostdistributionmapinsolukhumbunepal
AT sunilacharya assessingmachinelearningmodelstogeneratepermafrostdistributionmapinsolukhumbunepal