Scholarlink

The compacting parameters are one of the basic elements used to determine the California bearing ratio value, which is used to determine the subgrade strength of infrastructures. The maximum dry density (MDD) and the optimum moisture content (OMC) are the compaction parameters that are determined from the Atterberg limit tests. For this relationship, around 252 soil samples are used to model the relationship between the compaction parameters and the Atterberg limits on the liquid limit (LL), the plastic limit (PL), and the plasticity index. To do this experiment, the random forest (RF), support vector machine (SVM), and decision tree algorithms are used on 80% of the training data and 20% of the testing data. In this model, different performance measurement techniques were used. The mean absolute error, coefficient of determination, mean squared error, and root mean square errors are used to evaluate the performance of the regression model. According to the performance measure, in OMC and MDD, the value of R2 of the random forest algorithm is 0.55 and 0.54, respectively. This relationship is better than any other model, which is done using support vector machines and decision tree algorithms in the case of the coefficient of determination. The most important characteristics are the plasticity index and the liquid limit in maximum dry density and the optimum moisture content, respectively. The paper’s findings may be useful and applicable in many fields of civil engineering.

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

Prediction of Compaction Parameters Based on the Atterberg Limit by Using a Machine Learning Approach

  • 会议论文

  • 发表日期：

    2025年

查看全文
  • Semachew Molla Kassa,
  • Betelhem Zewdu Wubineh,
  • Africa Mulumar Geremew,
  • Tezera Firew Azmatch,
  • Nandyala Darga Kumar

摘要

The compacting parameters are one of the basic elements used to determine the California bearing ratio value, which is used to determine the subgrade strength of infrastructures. The maximum dry density (MDD) and the optimum moisture content (OMC) are the compaction parameters that are determined from the Atterberg limit tests. For this relationship, around 252 soil samples are used to model the relationship between the compaction parameters and the Atterberg limits on the liquid limit (LL), the plastic limit (PL), and the plasticity index. To do this experiment, the random forest (RF), support vector machine (SVM), and decision tree algorithms are used on 80% of the training data and 20% of the testing data. In this model, different performance measurement techniques were used. The mean absolute error, coefficient of determination, mean squared error, and root mean square errors are used to evaluate the performance of the regression model. According to the performance measure, in OMC and MDD, the value of R2 of the random forest algorithm is 0.55 and 0.54, respectively. This relationship is better than any other model, which is done using support vector machines and decision tree algorithms in the case of the coefficient of determination. The most important characteristics are the plasticity index and the liquid limit in maximum dry density and the optimum moisture content, respectively. The paper’s findings may be useful and applicable in many fields of civil engineering.