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

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:
permafrost mapping
ground-penetrating radar (GPR)
SHAP analysis
machine learning
Qinghai–Tibet Plateau
alpine permafrost
Online Access:https://www.mdpi.com/2072-4292/17/12/2015
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary: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.
ISSN:2072-4292

Similar Items