Mapping Mountain Permafrost via GPR-Augmented Machine Learning in the Northeastern Qinghai–Tibet Plateau

Accurate permafrost mapping in mountainous regions is hindered by sparse in situ observations and heterogeneous terrain. This study develops a GPR-augmented machine learning framework to map mountain permafrost in the northeastern Qinghai–Tibet Plateau. A total of 1037 presence–absence samples were...

Full description

Saved in:
Bibliographic Details
Main Authors: Yao Xiao, Guangyue Liu, Guojie Hu, Defu Zou, Ren Li, Erji Du, Tonghua Wu, Xiaodong Wu, Guohui Zhao, Yonghua Zhao, Lin Zhao
Format: Article
Language:English
Published: MDPI AG 2025-06-01
Series:Remote Sensing
Subjects:
Online Access:https://www.mdpi.com/2072-4292/17/12/2015
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849432200707047424
author Yao Xiao
Guangyue Liu
Guojie Hu
Defu Zou
Ren Li
Erji Du
Tonghua Wu
Xiaodong Wu
Guohui Zhao
Yonghua Zhao
Lin Zhao
author_facet Yao Xiao
Guangyue Liu
Guojie Hu
Defu Zou
Ren Li
Erji Du
Tonghua Wu
Xiaodong Wu
Guohui Zhao
Yonghua Zhao
Lin Zhao
author_sort Yao Xiao
collection DOAJ
description Accurate permafrost mapping in mountainous regions is hindered by sparse in situ observations and heterogeneous terrain. This study develops a GPR-augmented machine learning framework to map mountain permafrost in the northeastern Qinghai–Tibet Plateau. A total of 1037 presence–absence samples were compiled from boreholes, soil pits, 128 GPR transects collected in 2009, and 22 additional empirical points above 4700 m, covering diverse topographic and thermal conditions. Thirteen classification algorithms were evaluated using 5-fold cross-validation repeated 40 times, with LightGBM, CatBoost, XGBoost, and RF achieving top performance (F1 > 0.98). Elevation-based spatial comparisons revealed that LightGBM and CatBoost produced more terrain-adaptive predictions at high altitudes and slope transitions. Aspect-controlled permafrost boundaries were captured, with modeled lower elevation limits varying by >200 m across slope directions. SHAP analysis showed that climate and soil variables contributed nearly 80% to model outputs, with LST, FDD, BD, and TDD being dominant. Several predictors exhibited threshold or nonlinear responses, reinforcing their physical relevance. Additional experiments confirmed that integration of GPR and high-elevation constraint samples significantly improved model generalization, especially in underrepresented terrain zones. This study demonstrates that a GPR-augmented machine learning framework can support cost-effective, physically informed mapping of frozen ground in complex alpine environments.
format Article
id doaj-art-6f44842708a14cfbb853d3605817da4e
institution Kabale University
issn 2072-4292
language English
publishDate 2025-06-01
publisher MDPI AG
record_format Article
series Remote Sensing
spelling doaj-art-6f44842708a14cfbb853d3605817da4e2025-08-20T03:27:25ZengMDPI AGRemote Sensing2072-42922025-06-011712201510.3390/rs17122015Mapping Mountain Permafrost via GPR-Augmented Machine Learning in the Northeastern Qinghai–Tibet PlateauYao Xiao0Guangyue Liu1Guojie Hu2Defu Zou3Ren Li4Erji Du5Tonghua Wu6Xiaodong Wu7Guohui Zhao8Yonghua Zhao9Lin Zhao10Cryosphere Research Station on the Qinghai-Tibet Plateau, State Key Laboratory of Cryospheric Science and Frozen Soil Engineering, Northwest Institute of Eco-Environment and Resources, Chinese Academy of Sciences, Lanzhou 730030, ChinaCryosphere Research Station on the Qinghai-Tibet Plateau, State Key Laboratory of Cryospheric Science and Frozen Soil Engineering, Northwest Institute of Eco-Environment and Resources, Chinese Academy of Sciences, Lanzhou 730030, ChinaCryosphere Research Station on the Qinghai-Tibet Plateau, State Key Laboratory of Cryospheric Science and Frozen Soil Engineering, Northwest Institute of Eco-Environment and Resources, Chinese Academy of Sciences, Lanzhou 730030, ChinaCryosphere Research Station on the Qinghai-Tibet Plateau, State Key Laboratory of Cryospheric Science and Frozen Soil Engineering, Northwest Institute of Eco-Environment and Resources, Chinese Academy of Sciences, Lanzhou 730030, ChinaCryosphere Research Station on the Qinghai-Tibet Plateau, State Key Laboratory of Cryospheric Science and Frozen Soil Engineering, Northwest Institute of Eco-Environment and Resources, Chinese Academy of Sciences, Lanzhou 730030, ChinaCryosphere Research Station on the Qinghai-Tibet Plateau, State Key Laboratory of Cryospheric Science and Frozen Soil Engineering, Northwest Institute of Eco-Environment and Resources, Chinese Academy of Sciences, Lanzhou 730030, ChinaCryosphere Research Station on the Qinghai-Tibet Plateau, State Key Laboratory of Cryospheric Science and Frozen Soil Engineering, Northwest Institute of Eco-Environment and Resources, Chinese Academy of Sciences, Lanzhou 730030, ChinaCryosphere Research Station on the Qinghai-Tibet Plateau, State Key Laboratory of Cryospheric Science and Frozen Soil Engineering, Northwest Institute of Eco-Environment and Resources, Chinese Academy of Sciences, Lanzhou 730030, ChinaNorthwest Institute of Eco-Environment and Resources, Chinese Academy of Sciences, Lanzhou 730030, ChinaCryosphere Research Station on the Qinghai-Tibet Plateau, State Key Laboratory of Cryospheric Science and Frozen Soil Engineering, Northwest Institute of Eco-Environment and Resources, Chinese Academy of Sciences, Lanzhou 730030, ChinaSchool of Geographical Sciences, Nanjing University of Information Science & Technology (NUIST), Nanjing 210044, ChinaAccurate permafrost mapping in mountainous regions is hindered by sparse in situ observations and heterogeneous terrain. This study develops a GPR-augmented machine learning framework to map mountain permafrost in the northeastern Qinghai–Tibet Plateau. A total of 1037 presence–absence samples were compiled from boreholes, soil pits, 128 GPR transects collected in 2009, and 22 additional empirical points above 4700 m, covering diverse topographic and thermal conditions. Thirteen classification algorithms were evaluated using 5-fold cross-validation repeated 40 times, with LightGBM, CatBoost, XGBoost, and RF achieving top performance (F1 > 0.98). Elevation-based spatial comparisons revealed that LightGBM and CatBoost produced more terrain-adaptive predictions at high altitudes and slope transitions. Aspect-controlled permafrost boundaries were captured, with modeled lower elevation limits varying by >200 m across slope directions. SHAP analysis showed that climate and soil variables contributed nearly 80% to model outputs, with LST, FDD, BD, and TDD being dominant. Several predictors exhibited threshold or nonlinear responses, reinforcing their physical relevance. Additional experiments confirmed that integration of GPR and high-elevation constraint samples significantly improved model generalization, especially in underrepresented terrain zones. This study demonstrates that a GPR-augmented machine learning framework can support cost-effective, physically informed mapping of frozen ground in complex alpine environments.https://www.mdpi.com/2072-4292/17/12/2015permafrost mappingground-penetrating radar (GPR)SHAP analysismachine learningQinghai–Tibet Plateaualpine permafrost
spellingShingle Yao Xiao
Guangyue Liu
Guojie Hu
Defu Zou
Ren Li
Erji Du
Tonghua Wu
Xiaodong Wu
Guohui Zhao
Yonghua Zhao
Lin Zhao
Mapping Mountain Permafrost via GPR-Augmented Machine Learning in the Northeastern Qinghai–Tibet Plateau
Remote Sensing
permafrost mapping
ground-penetrating radar (GPR)
SHAP analysis
machine learning
Qinghai–Tibet Plateau
alpine permafrost
title Mapping Mountain Permafrost via GPR-Augmented Machine Learning in the Northeastern Qinghai–Tibet Plateau
title_full Mapping Mountain Permafrost via GPR-Augmented Machine Learning in the Northeastern Qinghai–Tibet Plateau
title_fullStr Mapping Mountain Permafrost via GPR-Augmented Machine Learning in the Northeastern Qinghai–Tibet Plateau
title_full_unstemmed Mapping Mountain Permafrost via GPR-Augmented Machine Learning in the Northeastern Qinghai–Tibet Plateau
title_short Mapping Mountain Permafrost via GPR-Augmented Machine Learning in the Northeastern Qinghai–Tibet Plateau
title_sort mapping mountain permafrost via gpr augmented machine learning in the northeastern qinghai tibet plateau
topic permafrost mapping
ground-penetrating radar (GPR)
SHAP analysis
machine learning
Qinghai–Tibet Plateau
alpine permafrost
url https://www.mdpi.com/2072-4292/17/12/2015
work_keys_str_mv AT yaoxiao mappingmountainpermafrostviagpraugmentedmachinelearninginthenortheasternqinghaitibetplateau
AT guangyueliu mappingmountainpermafrostviagpraugmentedmachinelearninginthenortheasternqinghaitibetplateau
AT guojiehu mappingmountainpermafrostviagpraugmentedmachinelearninginthenortheasternqinghaitibetplateau
AT defuzou mappingmountainpermafrostviagpraugmentedmachinelearninginthenortheasternqinghaitibetplateau
AT renli mappingmountainpermafrostviagpraugmentedmachinelearninginthenortheasternqinghaitibetplateau
AT erjidu mappingmountainpermafrostviagpraugmentedmachinelearninginthenortheasternqinghaitibetplateau
AT tonghuawu mappingmountainpermafrostviagpraugmentedmachinelearninginthenortheasternqinghaitibetplateau
AT xiaodongwu mappingmountainpermafrostviagpraugmentedmachinelearninginthenortheasternqinghaitibetplateau
AT guohuizhao mappingmountainpermafrostviagpraugmentedmachinelearninginthenortheasternqinghaitibetplateau
AT yonghuazhao mappingmountainpermafrostviagpraugmentedmachinelearninginthenortheasternqinghaitibetplateau
AT linzhao mappingmountainpermafrostviagpraugmentedmachinelearninginthenortheasternqinghaitibetplateau