Optimal performance of COD removal during aqueous treatment of alazine and gesaprim commercial herbicides by direct and inverse neural network

► We predict the COD of alazine and gesaprim commercial herbicides by direct and inverse artificial neural network approach. ► We are able to obtain any unknown input variables on line using the artificial neural network inverse approach. ► The artificial neural network approach allows us to simulate the COD removal when the input parameters are known. ► We are able to obtain any unknown input variables using artificial neural network inverse approach. ► The inverse neural network methodology is useful for on-line optimal control in the framework of the advanced oxidation processes.