This study focuses on validity of modeling of trihalomethane formation using artificial neural network with a feed-forward back-propagation neural network approach and graphical user interface function of MATLAB at a water treatment plant. Regularly measured parameters, which are conducted by Uyak et al., 2005, consisting of pH, total organic carbon, temperature and applied chlorine dose were utilized to implement the model for forecasting of trihalomethane formation. Attempting to investigate and compare with the use of traditional multiple linear regressions. The default Levenberg-Marquardt algorithm was used for training the network structures. It is noted that the best validation performance depending on the mean square error was 62.8539 at epoch 49. The simulated result tracked the measured data through a regression plot with a correlation coefficient of 0.95842, 0.94717 and 0.93369 for training, validation and test respectively. With respect to simulated testing the model demonstrates great performance in predicting the trihalomethane formation in chlorinated water. It is concluded that the artificial neural network generally is better than the multiple linear regression for forecasting trihalomethane formation.