African Journal of
Agricultural Research

  • Abbreviation: Afr. J. Agric. Res.
  • Language: English
  • ISSN: 1991-637X
  • DOI: 10.5897/AJAR
  • Start Year: 2006
  • Published Articles: 6576

Full Length Research Paper

A comparative study between parametric and artificial neural network approaches for economical assessment of potato production

  Morteza Zangeneh*, Mahmoud Omid and Asadollah Akram        
Department of Agricultural Machinery Engineering, Faculty of Agricultural Engineering and Technology, School of Agriculture and Natural Resources, University of Tehran, Karaj, Iran.
Email: [email protected]

  •  Accepted: 19 November 2010
  •  Published: 04 July 2011



This paper compares results of the application of two different approaches- parametric model (PM) and artificial neural network (ANN) for assessing economical productivity (EP), total costs of production (TCP) and benefit to cost ratio (BC) of potato crop. In this comparison, ANN model and Cobb-Douglas function as PM has been used. The ANN 8-6-12-1 topology with R2=0.89 resulted in the best-suited model for estimating EP. Similarly, optimal topologies for TCP and BC were 8-13-15-1 (R2=0.97) and 8-15-13-1 (R2=0.94). The ANN approach allowed to reduce the average estimation error from -184% for PM to less than 7% with a +30% to -95% variability range.


Key words: Economical productivity, benefit to cost ratio, total cost of production, Cobb-Douglas function, estimation error.