Time Series Prediction Using Hybrid ARIMA-ANN Models for Sugarcane

Recently Hybrid model approach has led to a tremendous surge in many domains of science and engineering. In this study, we present the advantage of ANN to improve time series forecasting precision. The Autoregressive Integrated Moving Average (ARIMA) and Artificial Neural Network (ANN) models are used to separately recognize the linear and nonlinear components in the data set respectively. In this manner, the proposed approach tactically utilizes the unique strengths ARIMA and ANN to improve the forecasting accuracy. Our hybrid method is tested on two Yamunanagar and Panipat sugarcane time series of Haryana. Results clearly indicate that Hybrid ARIMA-ANN model was better perform than ARIMA models with smaller values of RMSE and MAPE for both districts.