Scholarlink

<p>This study developed a Python-based framework to predict the ultimate bearing capacity of shallow foundations on cohesionless soil, employing machine learning (<i>ML</i>) and deep learning (<i>DL</i>) techniques. Utilizing a comprehensive dataset of 116 footing experiments, Eleven <i>ML</i> models (Gaussian Process Regression (<i>GPR</i>), Extreme Gradient Boosting (<i>XGBoost</i>), Gradient Boosting Machine (<i>GBM</i>), Random Forest (<i>RF</i>), Categorical Boosting (<i>CatBoost</i>) etc.) and five <i>DL</i> models (Artificial Neural Network (<i>ANN</i>), Deep Neural Network (<i>DNN</i>), etc.) trained and compared against traditional methods. Input parameters included foundation dimensions and soil properties. Results demonstrated that <i>ML</i> and <i>DL</i> models significantly outperformed traditional equations, achieving higher accuracy. Ensemble methods like <i>GPR</i>, <i>XGBoost</i>, <i>GBM</i>, <i>RF</i>, and <i>CatBoost</i> exhibited superior performance, with a Coefficient of Determination (<i>R</i><sup>2</sup>) values above 0.988 and a Mean Absolute Percentage Error (<i>MAPE</i>) below 5.07%. Conversely, traditional methods showed lower accuracy, with <i>R</i><sup>2</sup> values ranging from 0.684 to 0.82 and <i>MAPE</i> exceeding 19.63%. Taylor diagram analysis confirmed the improved performance of <i>ML</i> and <i>DL</i>. Additionally, a SHapley Additive exPlanations (<i>SHAP</i>) analysis highlighted foundation depth and soil friction angle as the most influential parameters, consistent with geotechnical principles.</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

A comparative machine and deep learning approach for predicting ultimate bearing capacity of shallow foundations in cohesionless soil

  • 期刊论文

  • 出版模式：

    开放获取

  • 发表日期：

    2025年11月18日

查看全文
  • Mahmoud El Gendy

摘要

This study developed a Python-based framework to predict the ultimate bearing capacity of shallow foundations on cohesionless soil, employing machine learning (ML) and deep learning (DL) techniques. Utilizing a comprehensive dataset of 116 footing experiments, Eleven ML models (Gaussian Process Regression (GPR), Extreme Gradient Boosting (XGBoost), Gradient Boosting Machine (GBM), Random Forest (RF), Categorical Boosting (CatBoost) etc.) and five DL models (Artificial Neural Network (ANN), Deep Neural Network (DNN), etc.) trained and compared against traditional methods. Input parameters included foundation dimensions and soil properties. Results demonstrated that ML and DL models significantly outperformed traditional equations, achieving higher accuracy. Ensemble methods like GPR, XGBoost, GBM, RF, and CatBoost exhibited superior performance, with a Coefficient of Determination (R2) values above 0.988 and a Mean Absolute Percentage Error (MAPE) below 5.07%. Conversely, traditional methods showed lower accuracy, with R2 values ranging from 0.684 to 0.82 and MAPE exceeding 19.63%. Taylor diagram analysis confirmed the improved performance of ML and DL. Additionally, a SHapley Additive exPlanations (SHAP) analysis highlighted foundation depth and soil friction angle as the most influential parameters, consistent with geotechnical principles.