An explainable ensemble machine learning approach for coefficient of compressibility prediction of Chengdu clay
- 1School of Earth Sciences, Guilin University of Technology
- 2School of Business, Guilin University of Technology
Abstract
Accurate prediction of the coefficient of compressibility (av) for regional clays remains a fundamental challenge in geotechnical engineering. Focusing on Chengdu clays, this study proposes a machine learning framework that integrates physically constrained data augmentation, differentiated hyperparameter optimization, and interpretability analysis. Based on 338 experimental datasets, a hybrid optimization strategy (Grid Search + Bayesian Optimization) is employed to ensure fair model comparison. The statistical significance of performance differences is rigorously validated using 30 iterations of Monte Carlo cross-validation combined with paired t-tests. Generalization capability is assessed via spatial grouping cross-validation, accompanied by Bootstrap-based uncertainty quantification. Results demonstrate that LightGBM achieves the highest predictive accuracy (test R2 = 0.8817), significantly outperforming comparison models (p < 0.05). XGBoost exhibits comparable accuracy (R2 = 0.8805), while Random Forest demonstrates superior robustness in spatial cross-validation (R2 = 0.7273). Multi-model analysis consistently identifies water content and liquidity index as the dominant factors governing av, with cumulative contribution exceeding 95%. SHAP analysis confirms both factors exhibit monotonically positive effects with approximate additivity. Tree-based models yield Bootstrap confidence intervals with mean widths ranging from 0.0526 to 0.0653 MPa-1, providing essential risk references for engineering practice. This study not only delivers a reliable predictive tool for av of Chengdu clays but also establishes a reproducible, physically guided, and statistically rigorous paradigm for regional geotechnical machine learning research.
Related
- Hybrid Explainable Deep Ensemble Framework with self-attention mechanism for early prediction of depression severity using PHQ-9 clinical and behavioral data
- Explainable diabetes prediction using a stacked ensemble framework
- Explainable DSC Perfusion Radiomics for Post-Treatment Glioblastoma Assessment Using a Soft-Voting Machine-Learning Ensemble
- A hybrid deep learning and ensemble approach for accurate prediction of hepatocellular carcinoma from sequence variants of hepatitis B virus (HBV) X gene
- Explainable machine learning for preoperative prediction of acute kidney injury after intertrochanteric fracture surgery in older adults
BibTeX
@article{wang2026explainable,
title = {{An explainable ensemble machine learning approach for coefficient of compressibility prediction of Chengdu clay}},
author = {Tongtong Wang and Hanying Bai and Lihong Yang},
journal = {Scientific Reports},
year = {2026},
month = sep,
doi = {10.1038/s41598-026-69689-8},
url = {https://doi.org/10.1038/s41598-026-69689-8},
note = {CC BY},
}
RIS
TY - JOUR
TI - An explainable ensemble machine learning approach for coefficient of compressibility prediction of Chengdu clay
AU - Tongtong Wang
AU - Hanying Bai
AU - Lihong Yang
PY - 2026
DA - 2026/09/01
JO - Scientific Reports
DO - 10.1038/s41598-026-69689-8
UR - https://doi.org/10.1038/s41598-026-69689-8
AB - Accurate prediction of the coefficient of compressibility (av) for regional clays remains a fundamental challenge in geotechnical engineering. Focusing on Chengdu clays, this study proposes a machine learning framework that integrates physically constrained data augmentation, differentiated hyperparameter optimization, and interpretability analysis. Based on 338 experimental datasets, a hybrid optimization strategy (Grid Search + Bayesian Optimization) is employed to ensure fair model comparison. The statistical significance of performance differences is rigorously validated using 30 iterations of Monte Carlo cross-validation combined with paired t-tests. Generalization capability is assessed via spatial grouping cross-validation, accompanied by Bootstrap-based uncertainty quantification. Results demonstrate that LightGBM achieves the highest predictive accuracy (test R2 = 0.8817), significantly outperforming comparison models (p < 0.05). XGBoost exhibits comparable accuracy (R2 = 0.8805), while Random Forest demonstrates superior robustness in spatial cross-validation (R2 = 0.7273). Multi-model analysis consistently identifies water content and liquidity index as the dominant factors governing av, with cumulative contribution exceeding 95%. SHAP analysis confirms both factors exhibit monotonically positive effects with approximate additivity. Tree-based models yield Bootstrap confidence intervals with mean widths ranging from 0.0526 to 0.0653 MPa-1, providing essential risk references for engineering practice. This study not only delivers a reliable predictive tool for av of Chengdu clays but also establishes a reproducible, physically guided, and statistically rigorous paradigm for regional geotechnical machine learning research.
SN - 2045-2322
ER -