Estimation of unconfined compressive strength of cement stabilized clay using artificial neural networks (ANN) model

Clay soil is greatly affected by the change in its water content, which negatively affects civil engineering projects, as it damages infrastructure and buildings and places a financial burden to repair these damages. Therefore, stabilization of clay soils is necessary in civil engineering projects, so soil treatment with cement is one of the most efficient and effective chemical stabilization methods due to its economic advantages and ease of use. In order to save the time and effort required for laboratory experiments, in this study, an artificial neural network (ANN) technique was applied using the Levenberg-Marquardt algorithm to develop a model that predicts the unconfined compressive strength of cementitious clay soils. The number of data for this study was (206) collected from (12) previous research studies. The input parameters were chosen as follows: likit limiti(LL)%, plastisite indeksi (PI)%, kil fraksiyonu (CF)%, kum %, silt %, water content (Wc) % , curing time (day) and cement ratio (C)% The unconfined compressive strength (qu) was chosen as an output parameter, then the data was normalized using the min-max method. The predictive model was developed using the artificial neural network tools in MATLAB software. In order to evaluate the performance of the predictive model developed in this study, the statistical analysis of the model was performed using regression (R2), mean square error (MSE), root mean square error (RMSE), and coefficient of efficiency (CE).