Prediction of economic indices for dry farming chickpea production in Ravansar county of Iran using artificial neural networks

Determination of suitable model for forecasting of economic indices of chickpea production under dry farming system in Ravansar county of Iran using artificial neural network (ANN) is the main aim of this study. For this purpose, the energy consumption for chickpea production under dry farming system are found from ۸۰ questionnaires. The results reveal the average total energy use of chickpea production is ۶۳۹۷.۲۵ MJ ha-۱. In the next step, the economic indices are calculated for chickpea farms. Accordingly, benefit to cost ratio, productivity, and energy intensiveness are calculated as ۱.۸۳, ۱.۳۱ kg $-۱, ۳۱۰.۶۲ $ ha-۱ and ۱۷.۰۹ MJ $-۱, respectively. In this study, a back propagation algorithm is used for training of ANN model and Levenberg-Marquardt is learning algorithm. The best topology has the ۶-۶-۴ structure. Moreover, the R۲ of best structure is found ۰.۹۸۱, ۰.۹۳۴, ۰.۹۹۳, and ۰.۹۴۳ for benefit to cost ratio, productivity, net return and energy intensiveness, respectively.

Keywords:

Agriculture , Artificial neural network , Chickpea , Economical analysis , Prediction