Scholarlink

<p>Accurate prediction of soil stress–strain behavior remains a major challenge in geotechnical engineering due to the inherent heterogeneity, nonlinearity, and sparsity of soil datasets. Conventional laboratory and in-situ testing methods are often expensive, time-consuming, and sensitive to sampling disturbances, which limits their efficiency in large-scale engineering applications. To address these challenges, this study proposes an optimized stacking ensemble framework that integrates advanced tree-based learning algorithms with metaheuristic optimization. The selected base learners Light Gradient Boosting (LGB), Extreme Gradient Boosting (XGB), Random Forest (RFR), and Histogram-based Gradient Boosting (HGB) were chosen for their complementary strengths in capturing nonlinear interactions, handling high-dimensional inputs, and maintaining robustness under sparse and heterogeneous data conditions. These models are optimized using the Puma Optimization (PO) algorithm and combined through a stacking strategy to enhance predictive stability and generalization performance. A dataset comprising 1,410 samples was compiled literature data, witch the K-fold cross-validation was employed to evaluate model robustness. The proposed stacking model, particularly the optimized XGB<sub>PO</sub> ensemble, achieved superior predictive accuracy with a coefficient of determination (R<sup>2</sup>) of 0.9914 in the testing phase, outperforming individual and hybrid models. Interpretability and sensitivity analyses further identified dry density (<InlineEquation ID="IEq1"> <EquationSource Format="TEX">\({\gamma }_{d}\)</EquationSource> </InlineEquation>), void ratio (<i>e</i><sub>0</sub>), and degree of saturation (<InlineEquation ID="IEq2"> <EquationSource Format="TEX">\({S}_{r}\)</EquationSource> </InlineEquation>) as the most influential factors governing soil compressibility behavior. The proposed framework provides a scalable, reliable, and computationally efficient alternative to traditional geotechnical testing methods, offering improved predictive accuracy and practical applicability for infrastructure design and decision-making under complex soil conditions.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Construction of multi-parameter intelligent comprehensive estimation algorithms for soil compression modulus

  • 期刊论文

  • 出版模式：

    开放获取

  • 发表日期：

    2026年4月10日

查看全文
  • Reza Sarkhani Benemaran,
  • Erfan Khajavi,
  • Amir Reza Taghavi Khanghah

摘要

Accurate prediction of soil stress–strain behavior remains a major challenge in geotechnical engineering due to the inherent heterogeneity, nonlinearity, and sparsity of soil datasets. Conventional laboratory and in-situ testing methods are often expensive, time-consuming, and sensitive to sampling disturbances, which limits their efficiency in large-scale engineering applications. To address these challenges, this study proposes an optimized stacking ensemble framework that integrates advanced tree-based learning algorithms with metaheuristic optimization. The selected base learners Light Gradient Boosting (LGB), Extreme Gradient Boosting (XGB), Random Forest (RFR), and Histogram-based Gradient Boosting (HGB) were chosen for their complementary strengths in capturing nonlinear interactions, handling high-dimensional inputs, and maintaining robustness under sparse and heterogeneous data conditions. These models are optimized using the Puma Optimization (PO) algorithm and combined through a stacking strategy to enhance predictive stability and generalization performance. A dataset comprising 1,410 samples was compiled literature data, witch the K-fold cross-validation was employed to evaluate model robustness. The proposed stacking model, particularly the optimized XGBPO ensemble, achieved superior predictive accuracy with a coefficient of determination (R2) of 0.9914 in the testing phase, outperforming individual and hybrid models. Interpretability and sensitivity analyses further identified dry density ( \({\gamma }_{d}\) ), void ratio (e0), and degree of saturation ( \({S}_{r}\) ) as the most influential factors governing soil compressibility behavior. The proposed framework provides a scalable, reliable, and computationally efficient alternative to traditional geotechnical testing methods, offering improved predictive accuracy and practical applicability for infrastructure design and decision-making under complex soil conditions.