Different AI Predictive Models for Pavement Subgrade Stiffness and Resilient Deformation of Geopolymer Cement-Treated Lateritic Soil with Ordinary Cement Addition

Onyelowe, Kennedy C.; Ebid, Ahmed M.; Ikechukwu, Aneke Frank; Nwobia, Light I.

doi:10.1007/s42947-022-00185-8

Cited by 7 publications

(1 citation statement)

References 25 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…It is evident from the figures that all the developed models exhibit a satisfactory level of accuracy in predicting the UCS values of geopolymer stabilized clayey soil. Based on Table 6 , the GB and AdaBoost models are efficient in predicting UCS values better than MLSR 34 , MGGP 34 , RF 39 , XGB 39 , and ANN 39 techniques. However, the GB model with an R 2 of 0.980 for the testing part was more accurate than the MGGP with an R 2 of 0.922, MLSR with an R 2 of 0.803, RF with an R 2 of 0.9459, XGB with an R 2 of 0.9671, ANN with an R 2 of 0.9676 and AdaBoost with an R 2 of 0.975.…”

Section: Resultsmentioning

confidence: 99%

Boosting-based ensemble machine learning models for predicting unconfined compressive strength of geopolymer stabilized clayey soil

Abdullah,

Ahmad,

Babur

et al. 2024

Sci Rep

View full text Add to dashboard Cite

The present research employs new boosting-based ensemble machine learning models i.e., gradient boosting (GB) and adaptive boosting (AdaBoost) to predict the unconfined compressive strength (UCS) of geopolymer stabilized clayey soil. The GB and AdaBoost models were developed and validated using 270 clayey soil samples stabilized with geopolymer, with ground-granulated blast-furnace slag and fly ash as source materials and sodium hydroxide solution as alkali activator. The database was randomly divided into training (80%) and testing (20%) sets for model development and validation. Several performance metrics, including coefficient of determination (R2), mean absolute error (MAE), root mean square error (RMSE), and mean squared error (MSE), were utilized to assess the accuracy and reliability of the developed models. The statistical results of this research showed that the GB and AdaBoost are reliable models based on the obtained values of R2 (= 0.980, 0.975), MAE (= 0.585, 0.655), RMSE (= 0.969, 1.088), and MSE (= 0.940, 1.185) for the testing dataset, respectively compared to the widely used artificial neural network, random forest, extreme gradient boosting, multivariable regression, and multi-gen genetic programming based models. Furthermore, the sensitivity analysis result shows that ground-granulated blast-furnace slag content was the key parameter affecting the UCS.

show abstract