Skip to content
Open access

An Interpretable Stacking Ensemble Framework for Defining Rainfall–Geoenvironmental Coupling Thresholds of Shallow Landslides

Oct 2026 · Remote Sensing · 0 citations · 38 references

Abstract

Rainfall-induced landslides exhibit marked spatio-temporal heterogeneity and multi-factor coupling. Existing susceptibility methods struggle to balance predictive accuracy with interpretability in nonlinear settings. This study addresses this gap by developing a Stacking ensemble framework integrated with SHAP analysis, using the July 2019 extreme rainfall-triggered landslides in northern Fujian and eastern Jiangxi as a case study. The framework builds an indicator system from multi-source data (topographic, geological, hydrological, and rainfall factors), screens key factors via correlation analysis, and constructs a Stacking model with Random Forest, XGBoost, and LightGBM as base learners and Ridge Regression as the meta-learner. The Stacking model outperforms individual models on the test set (AUC = 0.8935, F1 = 0.800) and captures 90.9% of known landslide points within high and very high susceptibility zones. SHAP-based interpretability identifies rainfall as the dominant control, with soil thickness, slope gradient, and lithology as secondary factors. Each factor exhibits nonlinear marginal effects and condition-dependent behavior, with significant rainfall–terrain and rainfall–geotechnical interactions. The proposed framework not only improves prediction stability but also provides critical interpretability and decision-making support for landslide risk identification under extreme rainfall conditions.

Read PDF

Similar papers

Open access Sep 2026

Integrating Grid-Based Random Forest Predictions with Slope Units for Landslide Susceptibility Mapping

Landslide susceptibility mapping identifies terrain prone to slope failure under comparable environmental and triggering conditions. Grid-based machine-learning outputs can be spatially fragmented and difficult to translate into slope-scale mitigation. We developed a two-stage grid-to-slope-unit framework for rainfall-...

Jin-Xiang Li, Muhammad Zeeshan Ali, Wen-Feng Cui et al. · 0 citations
Open access Sep 2026

A Dynamic Early Warning Model for Rainfall-Induced Landslides Coupling Slope Units and Rainfall Thresholds: A Case Study of Jinyang County, Southwest China

Climate-driven extreme rainfall is increasing landslide risk, whereas conventional regional rainfall thresholds inadequately represent spatial variations in slope preconditioning across complex mountainous terrain. This study develops a dynamic early-warning framework that couples slope unit landslide susceptibility wi...

Feng Zhang, Qi-Li Xie, Yong Zhang et al. · 0 citations
Sep 2026

Integrating CMIP6 climate change projections into machine learning–based flood susceptibility mapping: a comparative analysis for Pontian district, Johor

A climate-informed flood susceptibility model for the Pontian District, Johor is developed by integrating CMIP6 climate projections with machine learning approaches, demonstrating the value of integrating climate projections with explainable machine learning to support climate-resilient flood risk management and land-u...

Mohd Radhie Mohd Salleh, N. Alias, J. Muniandy et al. · 0 citations
Open access Nov 2026

Comparative Evaluation of Statistical and Morphometric Models for Rainfall-Induced Shallow Landslide Susceptibility Mapping: A Case Study Along the Fujian–Guangdong Border

Extreme rainfall can trigger widespread shallow landslides, highlighting the need for reliable susceptibility assessment systems. This study compares an information value–logistic regression (IV-LR) model with a terrain-driven morphometric model in terms of their predictive performance for shallow landslides triggered...

Xi-Han Xing, Xiao-Hong Ma, J. Huang et al. · 0 citations

We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.