Assessment of the various soft computing techniques to predict sodium absorption ratio (SAR)

Abstract

ABSTRACT In this investigation, the performance of the four soft computing techniques, that is M5P model tree, random forest (RF), bagging M5P model tree and group method for data handling (GMDH) were compared to estimate the sodium absorption ratio (SAR). Total data set consists of water quality of three (Alsthar, Biranshahr and Khoramabad in Iran) watershed out of which 70% data used to train the model and 30% data were used to test the model. The models’ accuracy were assessed using three performance evaluation parameters, which were correlation coefficient (C.C.), root mean square error (RMSE) and maximum absolute error (MAE). The obtained results suggest that the bagging M5P model tree regression technique (with C.C. = 0.9993, RMSE = 0.0097 and MAE = 0.006) is more accurate to estimate the SAR as compare to the M5P model tree, RF and GMDH for the given study area. Uncertainty analysis also suggested the same trends with minimum mean prediction error, standard deviation of prediction error and width of uncertainty band. Further, a comparison was also done with the previous study which also shows bagging M5P model tree predicts the SAR accurately.