Forecasting Wheat Production in Iran Using Time Series Technique and Artificial Neural Network

With the increase of the world population, the worries and concerns for food supply increase too. Wheat, as one of the most important agricultural products, which is widely consumed all over the world, has a very important role in people's nutrition, particularly among Iranians, the diet of whom is highly dependent on bread. Product forecasting is critical for any country so that decisions about storage, import or export, etc. can be planned. In this paper, several univariate time series models and the Artificial Neural Network (ANN) model are used to forecast wheat production in Iran. Annual wheat production, total annual precipitation, total applied fertilizer, population, and wheat cultivated area data were used in the period between ۱۹۶۱-۱۹۶۲ to ۲۰۱۸-۲۰۱۹. With the minimum values of ۱.۴۵۸۹۴, ۱.۰۰۳۲۹, ۱.۰۴۴۸, and ۱.۰۹۷۴۲ obtained for RMSE, AIC, HQC, and SIBC criteria, respectively, Autoregressive Integrated Moving Average (ARIMA) (۱,۱,۱) was selected as the best univariate model. In testing the ANN models, total annual precipitation, total applied fertilizer, population, and wheat cultivated, area as input variables, and wheat production, as output variable, were used. Among several NN models, the Multilayer Perceptron Neural Network (MLP-NN) model with five hidden layers had the lowest MSE= ۰.۱۵۳ and was chosen in this study. Comparison between the ANN model and the ARIMA (۱,۱,۱) model showed that RMSE= ۰.۳۹۱, MSE= ۰.۱۵۳, and MAPE= ۰.۴۲۳۱ in the ANN model were much lower than that of the ARIMA (۱,۱,۱) model. The results showed the power of ANN models to predict wheat production using efficient parameters, as compared to the ARIMA model.

کلیدواژه ها:

Agriculture Production ، Autoregressive Integrated Moving Average Model.