Enhanced Detection of Permafrost Deformation with Machine Learning and Interferometric SAR Along the Qinghai–Tibet Engineering Corridor

Interferometric synthetic aperture radar (InSAR) plays a significant role in monitoring permafrost deformation. However, owing to environmental constraints in permafrost regions, some regions exhibit temporal incoherence, which results in deformation with fewer measurement points and difficulties wi...

Full description

Saved in:
Bibliographic Details
Main Authors: Peng Fan, Hong Lin, Zhengjia Zhang, Heming Deng
Format: Article
Language:English
Published: MDPI AG 2025-06-01
Series:Remote Sensing
Subjects:
Online Access:https://www.mdpi.com/2072-4292/17/13/2231
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849704603511160832
author Peng Fan
Hong Lin
Zhengjia Zhang
Heming Deng
author_facet Peng Fan
Hong Lin
Zhengjia Zhang
Heming Deng
author_sort Peng Fan
collection DOAJ
description Interferometric synthetic aperture radar (InSAR) plays a significant role in monitoring permafrost deformation. However, owing to environmental constraints in permafrost regions, some regions exhibit temporal incoherence, which results in deformation with fewer measurement points and difficulties with deformation automatic detection. In this study, a full-coverage deformation rate map of the 10 km buffer of the Qinghai–Tibet Engineering Corridor (QTEC) was generated by combining nine driving factors and the deformation rate of the 5 km buffer along the QTEC based on three machine learning methods. The importance of the factors contributing to ground deformation was explored. The experimental results show that support vector regression (SVR) yielded the best performance (R2 = 0.98, RMSE = 0.76 mm/year, MAE = 0.74 mm/year). The 10 km buffer of deformation data obtained not only preserved the original deformation data well, but it also filled the blank areas in the deformation map. Subsequently, we trained the Faster R-CNN model on the deformation rate map simulated by SVR and used it for the automatic detection of permafrost thaw settlement areas. The results showed that the Faster R-CNN could identify the permafrost thawing slump quickly and accurately. More than 300 deformation areas along the QTEC were detected through our proposed method, with some of these areas located near thaw slump and thermokarst lake regions. This study confirms the significant potential of combining InSAR and deep learning techniques for permafrost degradation monitoring applications.
format Article
id doaj-art-1baf18d690154bd89d14a1c30b3fee48
institution DOAJ
issn 2072-4292
language English
publishDate 2025-06-01
publisher MDPI AG
record_format Article
series Remote Sensing
spelling doaj-art-1baf18d690154bd89d14a1c30b3fee482025-08-20T03:16:42ZengMDPI AGRemote Sensing2072-42922025-06-011713223110.3390/rs17132231Enhanced Detection of Permafrost Deformation with Machine Learning and Interferometric SAR Along the Qinghai–Tibet Engineering CorridorPeng Fan0Hong Lin1Zhengjia Zhang2Heming Deng3School of New Energy and Electrical Engineering, Hubei University, 368 Friendship Avenue, Wuchang District, Wuhan 430062, ChinaSchool of Geography and Information Engineering, China University of Geosciences, 388 Lumo Road, Wuhan 430074, ChinaSchool of Geography and Information Engineering, China University of Geosciences, 388 Lumo Road, Wuhan 430074, ChinaSchool of New Energy and Electrical Engineering, Hubei University, 368 Friendship Avenue, Wuchang District, Wuhan 430062, ChinaInterferometric synthetic aperture radar (InSAR) plays a significant role in monitoring permafrost deformation. However, owing to environmental constraints in permafrost regions, some regions exhibit temporal incoherence, which results in deformation with fewer measurement points and difficulties with deformation automatic detection. In this study, a full-coverage deformation rate map of the 10 km buffer of the Qinghai–Tibet Engineering Corridor (QTEC) was generated by combining nine driving factors and the deformation rate of the 5 km buffer along the QTEC based on three machine learning methods. The importance of the factors contributing to ground deformation was explored. The experimental results show that support vector regression (SVR) yielded the best performance (R2 = 0.98, RMSE = 0.76 mm/year, MAE = 0.74 mm/year). The 10 km buffer of deformation data obtained not only preserved the original deformation data well, but it also filled the blank areas in the deformation map. Subsequently, we trained the Faster R-CNN model on the deformation rate map simulated by SVR and used it for the automatic detection of permafrost thaw settlement areas. The results showed that the Faster R-CNN could identify the permafrost thawing slump quickly and accurately. More than 300 deformation areas along the QTEC were detected through our proposed method, with some of these areas located near thaw slump and thermokarst lake regions. This study confirms the significant potential of combining InSAR and deep learning techniques for permafrost degradation monitoring applications.https://www.mdpi.com/2072-4292/17/13/2231ground deformationpermafrostmachine learningQinghai–Tibet Engineering Corridor
spellingShingle Peng Fan
Hong Lin
Zhengjia Zhang
Heming Deng
Enhanced Detection of Permafrost Deformation with Machine Learning and Interferometric SAR Along the Qinghai–Tibet Engineering Corridor
Remote Sensing
ground deformation
permafrost
machine learning
Qinghai–Tibet Engineering Corridor
title Enhanced Detection of Permafrost Deformation with Machine Learning and Interferometric SAR Along the Qinghai–Tibet Engineering Corridor
title_full Enhanced Detection of Permafrost Deformation with Machine Learning and Interferometric SAR Along the Qinghai–Tibet Engineering Corridor
title_fullStr Enhanced Detection of Permafrost Deformation with Machine Learning and Interferometric SAR Along the Qinghai–Tibet Engineering Corridor
title_full_unstemmed Enhanced Detection of Permafrost Deformation with Machine Learning and Interferometric SAR Along the Qinghai–Tibet Engineering Corridor
title_short Enhanced Detection of Permafrost Deformation with Machine Learning and Interferometric SAR Along the Qinghai–Tibet Engineering Corridor
title_sort enhanced detection of permafrost deformation with machine learning and interferometric sar along the qinghai tibet engineering corridor
topic ground deformation
permafrost
machine learning
Qinghai–Tibet Engineering Corridor
url https://www.mdpi.com/2072-4292/17/13/2231
work_keys_str_mv AT pengfan enhanceddetectionofpermafrostdeformationwithmachinelearningandinterferometricsaralongtheqinghaitibetengineeringcorridor
AT honglin enhanceddetectionofpermafrostdeformationwithmachinelearningandinterferometricsaralongtheqinghaitibetengineeringcorridor
AT zhengjiazhang enhanceddetectionofpermafrostdeformationwithmachinelearningandinterferometricsaralongtheqinghaitibetengineeringcorridor
AT hemingdeng enhanceddetectionofpermafrostdeformationwithmachinelearningandinterferometricsaralongtheqinghaitibetengineeringcorridor