Grey Prediction Model Based On Time Delay Effect And Its Application In Agricultural Drought

Grey prediction model is an important part of grey system theory,and the classical grey prediction model has a good simulation effect on data series with exponential characteristics.However,drought series in real life still show time delay,so it is difficult to find a suitable forecasting model.To solve this problem,this paper will propose new grey forecasting models to solve the problem of forecasting data series with time delay.(1)Modeling method of GM(1,1)model with time delay.In view of the uncertainty and time-delay accumulation of drought series,the grey system theory can be combined with time-delay phenomenon.The traditional GM(1,1)model can not reflect the system delay effect,and most of the previous time delay models are based on the fact that the current value of the system behavior sequence is only affected by the single-stage influence factor of the lag ? period.In view of the long-term effect of time delay,the GM(1,1)model with accumulated effect of time delay is put forward,the modeling process of this model is studied,and the solution method of time delay parameter is given.(2)Modeling method of GM(1,N)model with time delay.If the system behavior sequence is affected by many factors,and different factors have time delay accumulation effect on the system behavior,it will be inaccurate to predict the system behavior sequence simply by using the traditional GM(1,N)model.To solve the prediction problem of this kind system,in order to improve the prediction accuracy of the model,it is proposed to introduce lag parameter and power exponent into the traditional GM(1,N)model.The lag parameter is used to describe the delay accumulation effect of related factors on system behavior,and the power exponent is used to describe the nonlinear effect of related factors on system behavior characteristic sequence after adding delay effect.(3)The proposed model is applied to the simulation and prediction of drought data series in Henan Province.Groundwater resources is an important index to evaluate the current situation of drought,and it is of great significance to predict it,but it also shows uncertainty and time lag,so the time lag GM(1,1)model proposed in this paper is used to simulate and predict it.An effective description and an accurate prediction of the changing trend of grain yield can provide a strong basis for relevant departments to formulate corresponding measures to reduce production.However,grain yield is a complex multivariable system with time delay effect.The delayed GM(1,N)model is used to simulate and predict the grain yield in Henan Province.By comparing the three prediction models with two inspection methods,it can be concluded that the model proposed in this chapter can better simulate the grain yield in Henan Province.