组合预测法对粮食产量的预测研究  

Combined Forecasting Method for the Prediction of Grain Yield

作　　者：李欣 代雁娜 杨敏 胡佳俊 Li Xin;Dai Yanna;Yang Min;Hu Jiajun(Chengdu College,University of Electronic Science and Technology of China,Sichuan Chengdu611731)

机构地区：[1]电子科技大学成都学院,四川成都611731

出　　处：《南方农机》2023年第6期183-185,共3页

摘　　要：为了对粮食产量进行准确预测,使用组合模型对粮食产量进行预测研究。通过对数据的分析确定了构成组合模型的三个单项模型:灰色预测GM(1,1)模型、多元回归预测模型、时间序列预测模型,并明确了确定组合预测模型权重的方法。使用4种预测模型对2015—2020年的粮食产量进行预测,结果显示组合预测模型的平均相对误差最小。因此,通过对预测模型的检验证实了模型的可行性和准确性,确定了组合模型可以充分地利用各种预测方法所提供的信息提高预测精度,使得预测结果更加准确有效。In order to accurately predict the grain yield, the combined model is used to predict the grain yield. Through the analysis of the data, the three single models that constitute the combined model are determined: the gray prediction GM(1,1)model, the multiple regression prediction model, the time series prediction model, and the method to determine the weight of the combined prediction model is clarified. Four forecasting models were used to forecast the grain output from 2015 to 2020, and the results showed that the average relative error of the combined forecasting model was the smallest. Therefore, the feasibility and accuracy of the prediction model are confirmed through the test of the prediction model, and the combined model can make full use of the information provided by various prediction methods to improve the prediction accuracy, and make the prediction results more accurate and effective.

关 键 词：组合预测模型 粮食产量 GM(1 1)模型 

分 类 号：F224.0[经济管理—国民经济]