Prediction of wheat production using artificial neural networks and investigating indirect factors affecting it: Case study in Canterbury province, New Zealand

An artificial neural network (ANN) approach was used to model the wheat production. From an extensive data collection involving 40 farms in Canterbury, New Zealand, the average wheat production was estimated at 9.9 t ha⁻¹. The final ANN model developed was capable of predicting wheat production under different conditions and farming systems using direct and indirect technical factors. After examining more than 140 different factors, 6 factors were selected as influential input into the model. The final ANN model can predict wheat production based on farm conditions (wheat area and irrigation frequency), machinery condition (tractor hp ha⁻¹ and number of passes of sprayer) and farm inputs (N and fungicides consumption) in Canterbury with an error margin of ±9% (±0.89 t ha⁻¹)