Ensemble of M5 Model Tree-Based Modelling of Sodium Adsorption Ratio

In this paper, we report the results of four ensemble approaches with the M5 model tree as the base regression model to anticipate Sodium Adsorption Ratio (SAR). The ensemble methods that combine the output of multiple regression models have been found to be more accurate than any of the individual models making up the ensemble. In this work, the additive boosting, bagging, rotation forest, and random sub-space methods were used. A dataset consisting of 488 samples with nine input parameters was obtained from the Barandoozchay River in the West Azerbaijan province, Iran. The three evaluation criteria correlation coefficient, root mean square error, and mean absolute error were used to judge the accuracy of different ensemble models. In addition to the use of an M5 model tree as the learning algorithm to predict the SAR values, a wrapper-based variable selection approach and a genetic algorithm were also used to select useful input variables. The encouraging performance motivates the use of this technique to predict the SAR values.