Modelling energy use and fuel consumption in wheat production using indirect factors and artificial neural networks

Abstract

This study was conducted over 35,300 hectares of irrigated and dry land wheat fields in Canterbury, New Zealand in the 2007-2008 harvest year. The Artificial Neural Network models (ANNs), after examining more than 140 several direct and indirect parameters, can predict energy use and fuel consumption based on farm conditions, farmers’ social considerations, farm operation, machinery condition and farm inputs, arable farms in Canterbury with an error margin of ±12% (± 2900 MJ/ha) and ±8% (± 5.6 l/ha), respectively.