Rice Yields Time Series Forecasting Using ANFIS

This study examines the forecasting performance of Adaptive Neuro Fuzzy Inference System(ANFIS) compared in comparison to statistical autoregressive integrated moving average (ARIMA) and the artificial neural network (ANN) model in forecasting of rice yield production.. To assess the effectiveness of these models, we used 9 years of time series records for rice yield data in Malaysia from 1995 to 2001. The rice yield forecasting models having various input structures are trained and tested to investigate the applicability of ANFIS and ANN methods. The results of ANFIS and ANN models for both training and testing are evaluated and the best fit forecasting model structure and method is determined according to criteria of performance evaluation. The best fit model is also trained and tested by ARIMA method and the performances of all models are compared in order to get more effective evaluation. The results demonstrate that ANFIS model is superior to the ANN and ARIMA forecasting models in term of accuracy and reliability. Thus, and ANFIS can be successfully utilized for rice yield forecasting.