基于R语言自回归积分移动平均模型在长沙市三带喙库蚊密度预测中的应用

Application of R-based autoregressive integrated moving average model in the prediction of Culex tritaeniorhynchus density in Changsha City

目的构建长沙市三带喙库蚊自回归积分移动平均模型(autoregressive integrated moving average,ARIMA)并进行预测。方法应用R语言3.3.2将2007年1月~2015年6月的三带喙库蚊密度数据构建ARIMA模型,比较2015年7~12月预测值与真实值,对2016年三带喙库蚊密度进行预测。结果三带喙库蚊密度监测数据构建ARIMA(1,1,1)×(1,1,0)12模型,赤池信息准则(AIC)值为487.98,经检验残差为白噪声(P>0.05),模型有效。2015年7~12月预测值与实际值基本一致,均方根误差(RMSE)=3.021,平均绝对误差(MAE)=2.132,模型外推良好。结论ARIMA模型在三带喙库蚊密度短期预测方面有一定可行性。

Objective To construct the autoregressive integrated moving average(ARIMA)model of Culex tritaeniorhynchus in Changsha City and to use it for prediction.Methods The ARIMA model was constructed using the R Programming Language 3.3.2 from January 2007 to June 2015 for Culex tritaeniorhynchus density data.The predicted value and the real value from July 2015 to December 2015 were compared to predict the density of Culex tritaeniorhynchus in 2016.Results The ARIMA(1,1,1)×(1,1,0)12 model was constructed for the Culex tritaeniorhynchus density monitoring data.The AIC value was 487.98,and the residual sequence was proved to be white noise(P>0.05).The model was valid.The predicted values from July to December2015 were basically the same as the real values.The Root Mean Square Error(RMSE)=3.021 and the Mean Absolute Error(MAE)=2.132.Good model data fit was demonstrated.Conclusion The ARIMA model has certain feasibility in the short-term prediction of Culex tritaeniorhynchus density.