Scholarlink

<p>This study presents a comparative analysis of three machine learning algorithms—Random Forest Regression (RFR), Support Vector Machine Regression (SVR), and Kernel Ridge Regression (KRR)—for predicting soil compaction parameters. Models were developed using a comprehensive dataset of 373 soil samples to predict Optimum Moisture Content (OMC) and Maximum Dry Density (MDD) from soil index properties. SVR demonstrated superior performance with testing R<sup>2</sup> values of 0.89 and 0.85 for OMC and MDD predictions, respectively. The models were validated using independent laboratory data, achieving validation R<sup>2</sup> values ranging from 0.79 to 0.94. The findings establish machine learning algorithms, particularly SVR, as reliable alternatives to traditional laboratory testing for predicting soil compaction parameters.</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

Prediction of Soil Compaction Parameters Using Machine Learning Algorithms: A Comparative Analysis

  • 期刊论文

  • 发表日期：

    2025年9月5日

查看全文
  • Pranshu Vardhan,
  • Suneet Kaur,
  • Usha Chouhan,
  • Rakesh Kumar

摘要

This study presents a comparative analysis of three machine learning algorithms—Random Forest Regression (RFR), Support Vector Machine Regression (SVR), and Kernel Ridge Regression (KRR)—for predicting soil compaction parameters. Models were developed using a comprehensive dataset of 373 soil samples to predict Optimum Moisture Content (OMC) and Maximum Dry Density (MDD) from soil index properties. SVR demonstrated superior performance with testing R2 values of 0.89 and 0.85 for OMC and MDD predictions, respectively. The models were validated using independent laboratory data, achieving validation R2 values ranging from 0.79 to 0.94. The findings establish machine learning algorithms, particularly SVR, as reliable alternatives to traditional laboratory testing for predicting soil compaction parameters.