Development of Linear, Nonlinear and Hybrid Models for Forecasting Sugarcane Yield
Development of Linear, Nonlinear and Hybrid Models for Forecasting Sugarcane Yield
Qaisar Mehmood1*, Ali Raza2, Asif Ali Abro3, Nargis Shaheen4 and Muhammad Riaz5
ABSTRACT
Sugarcane is important cash crop massive contributing the agricultural economy of the Pakistan, it is necessary for future to forecast the yield of sugarcane crop. The purpose of the study has to propose the optimum forecast models of the time series, artificial neural network and their hybrid models for forecasting the yield of sugarcane. Yearly data for the yield of sugarcane crop from 1947 to 2020 for economic survey of Pakistan was used for forecasting. We compare ARIMA, ETS, TBATS, Artificial Neural Network (ANN), ARIMA-ETS, ARIMA-TBATS, and ARIMA-ANN hybrid models by calculating RMSE and MAE for each model. It was observed that the ARIMA (2, 1, 0) model was optimum because it shows the minimum values for RMSE (2345.059) and MAE (1879.447) for sugarcane yield. Forecast average yield of sugarcane crop will be increase after ten years from 63827kg to 65660.37kg per hectare from 2020 to 2030. This increase amount of yield may increase the amount of sugar to meet the country requirements. More over these forecast estimates for sugarcane yield will be important for the Government in formulating their policies to fulfill the food necessities of the nation, trade, support prices, and planning about the cultivation sector.
To share on other social networks, click on any share button. What are these?
