Modeling wastewater treatment plant (WWTP) performance using artificial neural networks: Case of Adana (Seyhan)

In this study, performance estimation of biological wastewater treatment plants (WWTP) was made by applying Artificial Neural Network (ANN) techniques. As material, 355-day data from Adana Metropolitan Municipality Seyhan plant for 2021 were used. Of the used, 240 evaluated as training and 115 test data. establishment ANN model, daily chemical oxygen demand (COD), water flow (Qw) suspended solids (SS) parameters at entrance WWTP used input parameters. The (BOD) parameter determined output parameter. feed forward back propagation model (FFBPANN) to estimate BOD amounts WWTP. statistical analysis, correlation (R2) values with found be 0.906 COD, 0.294 Qw 0.605 SS. R2 value 0.891, MAE 10.32% RMSE 722.21 in network structures where best results obtained (in 4-4-1 model). a result it concluded that successful estimating BODs WWTPs obtaining reliable realistic results, effective analyzes simulation their nonlinear behavior could good evaluation tool terms reducing operating costs.