improving the performance of ann model, using wavelet transform and pca methodfor modeling and predict biochemical oxygen demand (bod)

in recent decades, the developments of artificial intelligence to predict hydrologic models have been widely used. in this study, the ability of artificial neural network(ann) models for modeling and predict the biological oxygen demand (bod) is located on the karun river in west iran were evaluated. to improve the simulation results, wavelet analysis was used as a hybrid model. bod index monthly time series karun river in mollasani station for 13 years (2002-2014) and the use of auxiliary variables dissolved oxygen (do), river flows and monthly temperature was simulated. thebest of inputs of model by the principal component analysis method (pca) was selected. to evaluate and compare the performance of models, root mean square error(rmse) criteria, coefficient of determination (r2) and akaike's information criterion (aic) were used. the results showed that ann has a margin of error of 0.0412 and the coefficient of determination 0.76 and application of wavelet transform on input data model improves the results to error of 0.0273 and the coefficient of determination 0.89.