A ChiMerge–WOE Ensemble Learning Framework for Landslide Susceptibility Assessment in Jiuzhaigou County, China
Sustainability · 25.06.2026 · 18 (13) · 6488
DOI: 10.3390/su18136488 ↗Kurz gefasst
Fachartikel in der Zeitschrift Sustainability, online erschienen am 25.06.2026. Verfasst von Yujie Liu und 4 weiteren Autor:innen. Die Arbeit nennt 55 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Fundamental Research Funds for the Central Universities, National Natural Science Foundation of China, Hebei Key Laboratory of Resource and Environmental Disaster Mechanism and Risk Monitoring.
Abstract (Originalsprache)
Landslide susceptibility assessment is important for disaster prevention and sustainable land-use planning in mountainous regions. However, conventional discretization methods often overlook threshold effects in conditioning factors, and many machine learning models still have limited interpretability. This study develops an integrated framework that combines ChiMerge discretization, Weight of Evidence (WOE) transformation, and tree-based ensemble learning to map landslide susceptibility in Jiuzhaigou County, Sichuan Province, China. A landslide inventory of 164 points was compiled from field investigations and hazard records, and fourteen topographic, geological, and environmental conditioning factors were derived from multi-source spatial datasets. Continuous factors were discretized using ChiMerge, a supervised chi-square-based discretization method that identifies statistically meaningful thresholds according to the distributions of landslide and non-landslide samples. WOE values were then calculated to quantify the association between each factor class and landslide occurrence. Three WOE-based ensemble models, WOE-CatBoost, WOE-LightGBM, and WOE-RF, were constructed and compared. All models showed high predictive performance (AUC > 0.90), with WOE-CatBoost performing best (AUC = 0.9432). Its high and very high susceptibility zones covered 28.59% of the study area but contained 85.96% of observed landslides. High-risk areas were mainly concentrated in steep valleys, fractured lithological zones, erosion belts, and areas affected by engineering activities, such as road construction, slope cutting, tourism infrastructure development, and settlement expansion. The proposed framework improves prediction accuracy and interpretability and provides spatial support for landslide prevention and sustainable land-use management.
Förderung
- Fundamental Research Funds for the Central Universities
- National Natural Science Foundation of China
- Hebei Key Laboratory of Resource and Environmental Disaster Mechanism and Risk Monitoring
- The Science and Technology Project of the Hebei Education Department of China
Zitieren
APA
Liu, Y., Zhang, L., Zhang, Y., Yao, Y., & Bao, Z. (2026). A ChiMerge–WOE Ensemble Learning Framework for Landslide Susceptibility Assessment in Jiuzhaigou County, China. Sustainability, 18(13), 6488. https://doi.org/10.3390/su18136488
Vancouver
Liu Y, Zhang L, Zhang Y, Yao Y, Bao Z. A ChiMerge–WOE Ensemble Learning Framework for Landslide Susceptibility Assessment in Jiuzhaigou County, China. Sustainability. 2026;18(13):6488. doi:10.3390/su18136488
BibTeX
@article{Liu2026,
author = {Liu, Yujie and Zhang, Lili and Zhang, Yaowen and Yao, Yunsheng and Bao, Zhicheng},
title = {A ChiMerge–WOE Ensemble Learning Framework for Landslide Susceptibility Assessment in Jiuzhaigou County, China},
journal = {Sustainability},
year = {2026},
volume = {18},
number = {13},
pages = {6488},
doi = {10.3390/su18136488}
}
EUVIMED