A Systematic Comparison of Statistical and Machine-Learning Models for Mapping Landslide Susceptibility: Evidence from the 2018 Rainfall-Induced Landslides in Hiroshima
GeoHazards · 18.07.2026 · 7 (3) · 87
DOI: 10.3390/geohazards7030087 ↗Kurz gefasst
Fachartikel in der Zeitschrift GeoHazards, online erschienen am 18.07.2026. Verfasst von Kumari Kanchana Mallika Achchillage und 3 weiteren Autor:innen. Die Arbeit nennt 68 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: JSPS KAKENHI.
Abstract (Originalsprache)
Landslide susceptibility mapping (LSM) is an essential tool for hazard assessment and land-use planning in landslide-prone areas. This study compares three statistical models—Frequency Ratio (FR), Weight of Evidence (WoE), and Logistic Regression (LR)—with six machine-learning algorithms: Support Vector Machine (SVM), Random Forest (RF), Extreme Gradient Boosting (XGBoost), Artificial Neural Network (ANN), k-Nearest Neighbor (KNN), and Decision Tree (DT), for regional landslide susceptibility assessment in Hiroshima Prefecture, Japan. A balanced dataset comprising 1936 landslide and 1936 non-landslide samples was developed from the 2018 rainfall-induced landslide inventory, utilizing seven conditioning factors: slope angle, profile curvature, aspect, elevation, lithology, soil water index, and 24 h cumulative rainfall. Model performance was assessed using the area under the receiver operating characteristic curve (AUC), accuracy, precision, recall, and F1-score. Among the statistical models, WoE exhibited the highest performance, while SVM provided the most balanced results among the machine-learning models. Both modeling approaches consistently identified lithology and slope angle as the primary controls on landslide occurrence. Independent validation demonstrated comparable predictive performance for both models; however, spatial validation showed that WoE assigned 96.72% of observed landslides to the High and Very High susceptibility classes, compared to 72.54% for SVM. These findings underscore the importance of integrating conventional classification metrics with spatial validation to enhance the evaluation and interpretation of landslide susceptibility models for regional hazard assessment.
Förderung
- JSPS KAKENHI
Zitieren
APA
Achchillage, K. K. M., Wakatsuki, T., Oguchi, C. T., & Osada, M. (2026). A Systematic Comparison of Statistical and Machine-Learning Models for Mapping Landslide Susceptibility: Evidence from the 2018 Rainfall-Induced Landslides in Hiroshima. GeoHazards, 7(3), 87. https://doi.org/10.3390/geohazards7030087
Vancouver
Achchillage KKM, Wakatsuki T, Oguchi CT, Osada M. A Systematic Comparison of Statistical and Machine-Learning Models for Mapping Landslide Susceptibility: Evidence from the 2018 Rainfall-Induced Landslides in Hiroshima. GeoHazards. 2026;7(3):87. doi:10.3390/geohazards7030087
BibTeX
@article{Achchillage2026,
author = {Achchillage, Kumari Kanchana Mallika and Wakatsuki, Tsuyoshi and Oguchi, Chiaki T. and Osada, Masahiko},
title = {A Systematic Comparison of Statistical and Machine-Learning Models for Mapping Landslide Susceptibility: Evidence from the 2018 Rainfall-Induced Landslides in Hiroshima},
journal = {GeoHazards},
year = {2026},
volume = {7},
number = {3},
pages = {87},
doi = {10.3390/geohazards7030087}
}
EUVIMED