A comparative study between parametric and artificial neural networks approaches for economical assessment of potato production in Iran

Abstract

Potatoes are the single most important agricultural commodity in Hamadan province of Iran, where 25,503 ha of this crop were planted in 2008 under irrigated conditions. This paper compares results of the application of two different approaches, parametric model (PM) and artificial neural networks (ANNs), for assessing economical productivity (EP), total costs of production (TCP) and benefit to cost ratio (BC) of potato crop. In this comparison, Cobb-Douglas function for PM and multilayer feedforward for implementing ANN models have been used. The ANN, having 8-6-12-1 topology with R 2 = 0.89, resulted in the best-suited model for estimating EP. Similarly, optimal topologies for TCP and BC were 8-13-15-1 (R 2 = 0.97) and 8-15-13-1 (R 2 = 0.94), respectively. In validating the PM and ANN models, mean absolute percentage error (MAPE) was used as performance indicator. The ANN approach allowed to reduce the MAPE from -184% for PM to less than 7% with a +30% to -95% variability range. Since ANN outperformed PM model, it should be preferred for estimating economical indices.Additional key words: artificial neural networks; benefit to cost ratio; Cobb-Douglas production function; economical productivity; estimation error; Solanum tuberosum; total cost of production. ResumenEstudio comparativo entre enfoques paramétricos y de redes neuronales artificiales para la evaluación económica de la producción de patata en Irán La patata es el producto agrícola más importante en la provincia de Hamadan (Irán), donde se plantaron 25.503 ha de este cultivo en 2008 bajo condiciones de riego. Este trabajo compara los resultados de aplicar dos enfoques diferentes, un modelo paramétrico (PM) y redes neuronales artificiales (ANN), para evaluar la productividad económica (EP), los costos totales de producción (TCP) y el coeficiente beneficio/costo (BC) del cultivo de la patata. En esta comparación se han utilizado la función Cobb-Douglas como PM y el proceso "feedforward" multicapa para implementar modelos de ANN. Las ANN, con una topología 8-6-12-1 con R 2 = 0,89, resultaron ser el modelo más adecuado para estimar la EP. Del mismo modo, las topologías óptimas para TCP y BC fueron 8-13-15-1 (R 2 = 0,97) y 8-15-13-1 (R 2 = 0,94), respectivamente. Para validar los modelos PM y ANN, se utilizó como indicador de desempeño el error porcentual medio absoluto (MAPE). El enfoque de ANN permitió reducir el MAPE desde -184% para PM a menos del 7% con un rango de variabilidad de +30% a-95%. Dado que ANN fue mejor que el modelo PM, debe ser preferido para la estimación de los índices económicos.Palabras clave adicionales: coeficiente beneficio/costo; costo total de producción; error de estimación; función de producción Cobb-Douglas; productividad económica; redes neuronales artificiales; Solanum tuberosum.

Neural network approach for predicting solar still production using agricultural drainage as a feedwater source

“…To assess the accuracy of the prediction models, the coefficient of determination (R 2 ), the root mean square error (RMSE), the mean absolute error (MAE), the coefficient of model efficiency (ME), the overall index of model performance (OI), and the coefficient of residual mass (CRM) were used. The R 2 , RMSE, 6)-(11), respectively [33][34][35]:…”

Joint of Modeling Techniques and Life Cycle Assessment for Prediction of Yield, Economic Profit, and Global Warming Potential for Wheat Farms

“…The basic tools applied in machine learning are called ANNs (Kalogirou and Bojic 2000). As part of the neural their names indicate, they are inducted by the brain systems that seek to the way we humans learn reproduction (Zangeneh et al 2011).…”

Prediction of Almond Nut Yield and Its Greenhouse Gases Emission Using Different Methodologies

“…In a production process, artificial intelligence (AI) is more attractive compared to mathematical models [18]. The advantage of AI over the regular statistical methods has been discussed in several studies, such as Kaul et al [19] for corn and soybean yield estimation, Zangeneh et al [20] for economical evaluation of potato yield, Safa and Samarasinghe [17] for prediction and simulation of consumed energy for wheat production, Rahimi-Ajdadi and Abbaspour-Gilandeh [21] for the prediction of tractor fuel consumption, Esmaeili et al [18] for the prediction of backbreak in open pit blasting, and Amid and Mesri Gundoshmian [22] for broiler production.…”