Artificial neural network modeling of water and wastewater treatment processes

Artificial neural networks (ANNs) are computer based systems that are designed to simulate the learning process of neurons in the human brain. ANNs have been attracting great interest during the last decade as predictive models and pattern recognition. Artificial neural networks possess the ability to "learn" from a set of experimental data (e.g. processing conditions and corresponding responses) without actual knowledge of the physical and chemical laws that govern the system. Therefore, ANNs application in data treatment is high especially where systems present nonlinearities and complex behavior. A growing world population, unrelenting urbanization, increasing scarcity of good quality water resources and rising fertilizer applications are the driving forces behind the accelerating upward trend in the use of new and more efficient methods of water and wastewater treatment. Due to the complexity of reactions in these new processes, the kinetic parameters of the various steps involved are very difficult to determine, leading to uncertainties in the design and scale-up of chemical reactors of industrial interest. Since the treatment efficiency depends on several factors, the modeling of these processes involves many problems. It is evident that these difficulties can not be solved by simple linear multivariate correlation. As a result of good modeling capabilities, artificial neural networks have been used extensively for a number of treatment processes. One of the characteristics of modeling based on ANNs is that it does not require the mathematical description of the phenomena involved in the process. This document briefly describes the application of artificial neural networks for modeling of water and wastewater treatment processes. Examples of early applications of ANNs in modeling and simulation of electrochemical treatment, photocatalytic, advanced treatment, photooxidative and adsorption processes are reviewed.