Application of trigonometric grey prediction approach to forecasting China grain yield

The grain yield time series is a non-steady time series that has the definite dynamic tendency and stronger random fluctuation. Therefore, we first use the grey GM(1, 1) model to obtain the tendency term, and then the generalized trigonometric model is used to catch the periodic phenomenon from the data for improving forecasting accuracy. The grey model with the trigonometric residual modification technique, which is named trigonometric grey prediction model, has combined the advantages of grey model and the trigonometric model, it has overcome the influence by data fluctuation to precision of forecasting. At last, the validity and applicability of the model are demonstrated by a simulation of annual grain yield.