Interpretable and Calibrated XGBoost Framework for Risk-Informed Probabilistic Prediction of Slope Stability
Sustainability · 12.11.2025 · 17 (22) · 10122
DOI: 10.3390/su172210122 ↗Kurz gefasst
Fachartikel in der Zeitschrift Sustainability, online erschienen am 12.11.2025. Verfasst von Hani S. Alharbi. Die Arbeit wurde bisher 14-mal zitiert (Crossref) und nennt 65 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).
Abstract (Originalsprache)
This study develops an interpretable and calibrated XGBoost framework for probabilistic slope stability assessment using a 627-case database of circular-mode failures. Six predictors, namely, unit weight (γ), cohesion (c), friction angle (φ), slope angle (β), slope height (H), and pore-pressure ratio (ru), were used to train a gradient-boosted tree model optimized through Bayesian hyperparameter search with five-fold stratified cross-validation. Physically based monotone constraints ensured that failure probability (Pf) decreases as c and φ increase and increases with β, H, and ru. The final model achieved strong performance (AUC = 0.88, Accuracy = 0.80, MCC = 0.61) and reliable calibration, confirmed by a Brier score of 0.14 and ECE/MCE of 0.10/0.19. A 1000-iteration bootstrap quantified both epistemic and aleatoric uncertainties, providing 95% confidence bands for Pf-feature curves. SHAP analysis validated physically consistent influence rankings (φ > H ≈ c > β > γ > ru). Predicted probabilities were classified into Low (Pf < 0.01), Medium (0.01 ≤ Pf ≤ 0.10), and High (Pf > 0.10) risk levels according to geotechnical reliability practices. The proposed framework integrates calibration, uncertainty quantification, and interpretability into a comprehensive, auditable workflow, supporting transparent and risk-informed slope management for infrastructure, mining, and renewable energy projects.
Zitieren
APA
Alharbi, H. S. (2025). Interpretable and Calibrated XGBoost Framework for Risk-Informed Probabilistic Prediction of Slope Stability. Sustainability, 17(22), 10122. https://doi.org/10.3390/su172210122
Vancouver
Alharbi HS. Interpretable and Calibrated XGBoost Framework for Risk-Informed Probabilistic Prediction of Slope Stability. Sustainability. 2025;17(22):10122. doi:10.3390/su172210122
BibTeX
@article{Alharbi2025,
author = {Alharbi, Hani S.},
title = {Interpretable and Calibrated XGBoost Framework for Risk-Informed Probabilistic Prediction of Slope Stability},
journal = {Sustainability},
year = {2025},
volume = {17},
number = {22},
pages = {10122},
doi = {10.3390/su172210122}
}
EUVIMED