A neural network based modeling of energy inputs for predicting economic indices in seed and grain corn production

In this study, various Artificial Neural Networks (ANNs) were developed to determine the economics indices for seed and grain corn production in Ardabil province, Iran. For this purpose, the data was collected by a face-to-face interview method from 144 corn farms during 2011 and analyzed. The results indicated that total energy input for seed and grain corn productions was about 45162.77 and 35198.11, respectively. The developed ANN was a multilayer perceptron (MLP) with six neurons in the input layer (human labor, machinery, diesel fuel, chemical fertilizer, Chemicals, Seed), one, two and three hidden layer(s) of various numbers of neurons and four neuron (BCR, P, TR, NR) in the output layer. The results of ANNs analyze showed that the best MLP network models for predicting economic indices in seed and grain corn production had (6-6-10-4) and (6-4-8-4) topologies, respectively. For these topologies, MSE, MAE and R2 calculated. The ANN approach appears to be a suitable method for modeling output energy, fuel consumption, CO2 emission, yield, and energy consumption.