Predicting California Bearing Ratio of Lateritic Soils Using Hybrid Machine Learning Technique

The increase in population has made it possible for better, more cost-effective vehicular services, which warrants good roadways. sub-base that serves as a stress-transmitting media and distributes vehicle weight to resist shear radial deformation is critical component of the pavement structures. Developing novel techniques can assess soil’s geotechnical characteristics performance an urgent need. Laterite soil abundantly available West Godavari area India was employed this research. Roads highways construction takes chunk investigation, particularly, California bearing ratio (CBR) subgrade soils. Therefore, there need intelligent tool predict or analyze CBR value without time-consuming cumbersome laboratory tests. An integrated extreme learning machine-cooperation search optimizer (ELM-CSO) approach used herein values. correlation coefficient utilized cost functions CSO identify optimal activation weights ELM. statistical measures are separately considered, best solutions reported article. Comparisons provided with standard ELM show superiorities proposed Further, impact each input variable studied separately, reduced models limited inadequate data loss prediction accuracy. When 70% training 30% testing applied, ELM-CSO outperforms Pearson (R), determination (R2), root mean square error (RMSE) values 0.98, 0.97, 0.84, respectively. based on findings, newly built be considered alternative method predicting real-time engineering issues, including lateritic properties.