Artificial neural networks approach for energy modeling of chickpea production under dry farming system in Kangavar county of Iran

This study was conducted in order to determine energy consumption and their modeling for chickpea production under dry farming system using artificial neural networks (ANNs) in Kangavar county of Kermanshah province, Iran. The initial data was collected from 25 chickpea producers in thestudied area. The results indicated that total average energy input for chickpea production was 5513.81 MJ ha–1. Also, diesel fuel (with 64%) was the highest energy inputs for chickpea production. The rate of energy use efficiency, energy productivity and net energy was calculated as 1.40, 0.10 kg MJ-1 and 2215.75MJ ha-1, respectively. In this study, Levenberg-Marquardt learning algorithm was used for training ANNs based on data collected from chickpea producers. The ANN model with 6-6-1 structure was the best network for predicting the chickpea yield with highest rate of R2 and lowest rate of MSE and MAPE in allthree cases of training, testing and validating

Artificial neural networks approach for energy modeling of chickpea production under dry farming system in Kangavar county of Iran Keywords:

Artificial neural network , Chickpea , Dry farming , Energy , Modeling