Modelling fuel consumption in wheat production using artificial neural networks

Majeed Safa and Sandhya Samarasinghe

Energy, 2013, vol. 49, issue C, 337-343

Abstract: An ANN (artificial neural network) approach was used to model the fuel consumption of wheat production. This study was conducted over 35,300 ha of irrigated and dry land wheat fields in Canterbury in the 2007–2008 harvest year. From an extensive data collection involving 40 farms, the total fuel consumption in wheat production was estimated at 65.3 l/ha. On average, fuel consumption in tillage and harvesting was more than in other operations, at 29.6 l/ha (45%) and 18 l/ha (28%), respectively. The ANN model developed was capable of predicting fuel consumption in wheat production under different conditions using technical and social factors. This will help farmers find the best practice to reduce their expenditure, with minimum income reduction. This study investigated the potential for using ANN to forecast fuel consumption, as compared to traditional regression models. After examining more than 140 different factors, 8 were selected as influential input into the model. The final neural network model can predict fuel consumption based on farm conditions (size of wheat area and number of sheep), farmers' social considerations (level of education), farm operation (number of passes of plough), machinery condition (age of sprayer) and farm inputs (P, herbicide and insecticide consumption) in arable farms in Canterbury with an error margin of ±8% (±5.6 l/ha).

Keywords: Modelling; Neural networks; Fuel consumption; Wheat; Canterbury; New Zealand (search for similar items in EconPapers)
Date: 2013
References: View references in EconPapers View complete reference list from CitEc
Citations: View citations in EconPapers (6)

Downloads: (external link)
http://www.sciencedirect.com/science/article/pii/S0360544212008353
Full text for ScienceDirect subscribers only

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:eee:energy:v:49:y:2013:i:c:p:337-343

DOI: 10.1016/j.energy.2012.10.055

Access Statistics for this article

Energy is currently edited by Henrik Lund and Mark J. Kaiser

More articles in Energy from Elsevier
Bibliographic data for series maintained by Catherine Liu ().