TY - JOUR

T1 - Modeling unsaturated hydraulic conductivity of compacted bentonite using a constrained CatBoost with bootstrap analysis

AU - Taherdangkoo, Reza

AU - Nagel, Thomas

AU - Chen, Chaofan

AU - Mollaali, Mostafa

AU - Ghasabeh, Mehran

AU - Cuisinier, Olivier

AU - Abdallah, Adel

AU - Butscher, Christoph

N1 - Publisher Copyright: © 2024 The Author(s)

PY - 2024/8/21

Y1 - 2024/8/21

N2 - Accurately determining the hydraulic conductivity of unsaturated bentonite is important for modeling subsurface thermo-hydro-mechanical and chemical processes. This study introduced a new hybrid model that employs a constrained categorial boosting (CatBoost) algorithm, combined with a genetic algorithm for hyperparameter tuning, to estimate the hydraulic conductivity of unsaturated compacted bentonite The performance of the constrained CatBoost model was benchmarked against a diverse set of data-driven baseline regression models, including lasso, elastic net, polynomial, k-nearest neighbors, decision tree, bagging tree, random forest, and CatBoost. The results indicated that the constrained CatBoost model offers a superior balance between model robustness and predictive accuracy in estimating the hydraulic conductivity of compacted bentonite-based materials during the wetting phase. The model effectively captured the U-shape relationship between hydraulic conductivity and suction, a key characteristic of bentonite behavior. Additionally, bootstrapping analyses confirmed the model's reliability under data variability, further validating its applicability in environmental and geotechnical applications.

AB - Accurately determining the hydraulic conductivity of unsaturated bentonite is important for modeling subsurface thermo-hydro-mechanical and chemical processes. This study introduced a new hybrid model that employs a constrained categorial boosting (CatBoost) algorithm, combined with a genetic algorithm for hyperparameter tuning, to estimate the hydraulic conductivity of unsaturated compacted bentonite The performance of the constrained CatBoost model was benchmarked against a diverse set of data-driven baseline regression models, including lasso, elastic net, polynomial, k-nearest neighbors, decision tree, bagging tree, random forest, and CatBoost. The results indicated that the constrained CatBoost model offers a superior balance between model robustness and predictive accuracy in estimating the hydraulic conductivity of compacted bentonite-based materials during the wetting phase. The model effectively captured the U-shape relationship between hydraulic conductivity and suction, a key characteristic of bentonite behavior. Additionally, bootstrapping analyses confirmed the model's reliability under data variability, further validating its applicability in environmental and geotechnical applications.

KW - Bentonite

KW - Bootstrap resampling

KW - Categorial boosting

KW - Constrained machine learning

KW - Hydraulic conductivity

KW - Sobol indices

UR - http://www.scopus.com/inward/record.url?scp=85201520880&partnerID=8YFLogxK

U2 - 10.1016/j.clay.2024.107530

DO - 10.1016/j.clay.2024.107530

M3 - Article

AN - SCOPUS:85201520880

VL - 260.2024

JO - Applied clay science

JF - Applied clay science

SN - 0169-1317

IS - November

M1 - 107530

ER -