Neural Prediction of a Hydrocarbon Degradation Process in Biopiles

Abstract

Abstract This paper proposes the use of a Recurrent Neural Network model (RNN) for modeling a hydrocarbon degradation process carried out in a biopile system. The proposed RNN model has seven inputs, five outputs and twelve neurons in the hidden layer, with global and local feedbacks. The learning algorithm is a modified version of the backpropagation through time. The approximation and generalization error is below 2%. The learning was performed in 131 epochs, 56 iterations each one