Scholarlink

<p>Against the backdrop of booming engineering construction in loess areas, achieving rapid and accurate prediction of the loess collapsibility coefficient is of great significance. This study takes the loess in the Longdong area as the research object. Based on analyzing the correlation between the collapsibility coefficient and various soil property indices, a rapid determination standard for the collapsibility of loess in this area is proposed. Prediction models between the loess collapsibility coefficient and void ratio, depth, saturation, and compression coefficient are established using three machine learning algorithms: random forest (RF), extreme gradient boosting (XGBoost), and support vector machine (SVM). The prediction results are subjected to interpretability analysis using the Shapley additive explanations (SHAP) technique. The research results show that loess with a void ratio less than 0.960 and a soil layer depth greater than 16&#xa0;m can be used as the rapid determination standard for non-collapsible loess in this area. The XGBoost model has higher prediction accuracy and applicability, with coefficients of determination (<i>R</i><sup>2</sup>) of 0.910 and 0.900 for the training set and testing set, respectively. The prediction accuracy for identifying whether loess is collapsible or nocollapsible reaches 92.7%. SHAP analysis reveals that the influence trends of various factors on model predictions are consistent with theoretical cognition, and soils with a depth less than 11&#xa0;m and a void ratio greater than 1.02 have a high collapsibility tendency. The results and conclusions of this study can provide a theoretical basis for subsequent engineering construction in the Longdong area.</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

Correlation analysis between the collapsibility of loess and physicomechanical indices in Longdong region and prediction of the collapsibility coefficient based on machine learning

  • 期刊论文

  • 出版模式：

    开放获取

  • 发表日期：

    2026年4月3日

查看全文
  • Deren Liu,
  • Kaiqiang Wang,
  • Yicheng Bian,
  • Xu Wang,
  • Yanjie Zhang

摘要

Against the backdrop of booming engineering construction in loess areas, achieving rapid and accurate prediction of the loess collapsibility coefficient is of great significance. This study takes the loess in the Longdong area as the research object. Based on analyzing the correlation between the collapsibility coefficient and various soil property indices, a rapid determination standard for the collapsibility of loess in this area is proposed. Prediction models between the loess collapsibility coefficient and void ratio, depth, saturation, and compression coefficient are established using three machine learning algorithms: random forest (RF), extreme gradient boosting (XGBoost), and support vector machine (SVM). The prediction results are subjected to interpretability analysis using the Shapley additive explanations (SHAP) technique. The research results show that loess with a void ratio less than 0.960 and a soil layer depth greater than 16 m can be used as the rapid determination standard for non-collapsible loess in this area. The XGBoost model has higher prediction accuracy and applicability, with coefficients of determination (R2) of 0.910 and 0.900 for the training set and testing set, respectively. The prediction accuracy for identifying whether loess is collapsible or nocollapsible reaches 92.7%. SHAP analysis reveals that the influence trends of various factors on model predictions are consistent with theoretical cognition, and soils with a depth less than 11 m and a void ratio greater than 1.02 have a high collapsibility tendency. The results and conclusions of this study can provide a theoretical basis for subsequent engineering construction in the Longdong area.