Modeling fuel consumption in wheat production using neural networks

Abstract

An artificial neural network (ANN) approach was used to model the fuel consumption of wheat production. This study was conducted over 18,316 hectares of irrigated and dry land wheat fields in Canterbury in the 2007-2008 harvest year. The data was collected from three different sources: questionnaire, literature review, and field measurements. The developed model is capable of predicting fuel consumption in wheat production under different conditions. It can help farmers find the best practice to reduce their expenditure with minimum income reduction. This study investigates the potential for using neural networks to forecast fuel consumption, as compared to traditional regression models. This study examines more than 15 different technical, social and geographical inputs in wheat production in Canterbury to find the most important factors for model development. Finally, 8 variables: distance from nearest town, size of farm, farmer education, average size of paddocks, farmer experience, farmer age, proportion of wheat area(ha)/total area(ha), total tractor power(hp)/ farm(ha) were selected. The final model can predict fuel consumption to ±5.6 L/ha accuracy in wheat production by using different social, geographical, and technical factors.