Prediction of COD and NH4+-N Concentrations in Leachate from Lab-scale Landfill Bioreactors Using Artificial Neural Networks

Abstract

In this study, we present an Artificial Neural Network (ANN) model for predicting COD and NH4+-N concentrations in landfill leachate from lab-scale landfill bioreactors. For this purpose, two different lab-scale systems were modeled. for neural network’s data obtained. In the first system, the leachate from a fresh-waste reactor was drained to a recirculation tank and recycled every two days. In the second, the leachate from a fresh waste landfill reactor was fed through a well-decomposed refuse landfill reactor, while the leachate from a well-decomposed refuse landfill reactor was simultaneously recycled to a fresh waste landfill reactor. The results indicate that leachate NH4+-N and COD concentrations accumulated to a high level in the first system, while. NH4+-N and COD removals were successfully carried out in the second. Also, average removal efficiencies in the second system reached 85% and 34% for COD and NH4+-N, respectively. Finally, the ANN’s results exhibited the success of the model as witnessed by the excellent agreement obtained between measured and predicted values.

Keywords

• Anaerobic Process
• artificial neural network
• Organic Content
• NH4+-N
• Leachate