Affiliations 

  • 1 Department of Civil Engineering, Faculty of Engineering, International Islamic University Malaysia, Jalan Gombak, Selangor, 50728, Malaysia. ahmadm@iium.edu.my
  • 2 Department of Mechanical Engineering, Hijjawai Faculty for Engineering, Yarmouk University, Irbid, 21163, Jordan
  • 3 Faculty of Management, AGH University of Science and Technology, 30-067, Krakow, Poland
  • 4 Department of Building and Construction Techniques Engineering, Al-Mustaqbal University College, Hilla, 51001, Iraq
  • 5 Department of Civil Engineering, Faculty of Engineering, International Islamic University Malaysia, Jalan Gombak, Selangor, 50728, Malaysia
  • 6 Peter the Great St. Petersburg Polytechnic University, 195251, St. Petersburg, Russia
  • 7 Faculty of Engineering and Technology, Future University in Egypt, New Cairo, 11835, Egypt
  • 8 Department of Civil Engineering, Al-Baha University, Al-Baha, 65527, P. O. Box 1988, Saudi Arabia
  • 9 Department of Food Nutrition Science, College of Science, Taif University, Taif, 21944, P. O. Box 11099, Saudi Arabia
  • 10 Department of Civil Engineering, CECOS University of IT and Emerging Sciences, Peshawar, 25000, Pakistan
Sci Rep, 2023 Aug 21;13(1):13593.
PMID: 37604957 DOI: 10.1038/s41598-023-40903-1

Abstract

The California bearing ratio (CBR) is one of the basic subgrade strength characterization properties in road pavement design for evaluating the bearing capacity of pavement subgrade materials. In this research, a new model based on the Gaussian process regression (GPR) computing technique was trained and developed to predict CBR value of hydrated lime-activated rice husk ash (HARHA) treated soil. An experimental database containing 121 data points have been used. The dataset contains input parameters namely HARHA-a hybrid geometrical binder, liquid limit, plastic limit, plastic index, optimum moisture content, activity and maximum dry density while the output parameter for the model is CBR. The performance of the GPR model is assessed using statistical parameters, including the coefficient of determination (R2), mean absolute error (MAE), root mean square error (RMSE), Relative Root Mean Square Error (RRMSE), and performance indicator (ρ). The obtained results through GPR model yield higher accuracy as compare to recently establish artificial neural network (ANN) and gene expression programming (GEP) models in the literature. The analysis of the R2 together with MAE, RMSE, RRMSE, and ρ values for the CBR demonstrates that the GPR achieved a better prediction performance in training phase with (R2 = 0.9999, MAE = 0.0920, RMSE = 0.13907, RRMSE = 0.0078 and ρ = 0.00391) succeeded by the ANN model with (R2 = 0.9998, MAE = 0.0962, RMSE = 4.98, RRMSE = 0.20, and ρ = 0.100) and GEP model with (R2 = 0.9972, MAE = 0.5, RMSE = 4.94, RRMSE = 0.202, and ρ = 0.101). Furthermore, the sensitivity analysis result shows that HARHA was the key parameter affecting the CBR.

* Title and MeSH Headings from MEDLINE®/PubMed®, a database of the U.S. National Library of Medicine.

Similar publications