The GMDH model and its application to forecating of rice yields

Abstract

In this paper, the group method of handling (GMDH) model and their application to the forecasting of the rice yields time series are described. The use of such GMDH leads to successful application in broad range of areas. However, in some fields, such as rice yields forecasting, the use GMDH is still scare. At1ificial neural networks (ANN) have been shown to be powerful tools for system modeling. This study addressed the question of whether GMDH could be used to estimate more accurate in modeling and forecasting compared with the ANN model. To assess the effectiveness of these models, we used 9 years of time series records for rice yield data in Malaysia from 1995 to 200 I. The results demonstrate that GMDH model is superior to the ANN for rice yield forecasting.