基于IOWA算子的空气质量组合预测  

Combined prediction of air quality based on IOWA operator

作　　者：杨璐瑞 张权[1] YANG Lu-rui;ZHANG Quan(College of Science,Qiqihar University,Heilongjiang Qiqihar 161006,China)

机构地区：[1]齐齐哈尔大学理学院,黑龙江齐齐哈尔161006

出　　处：《齐齐哈尔大学学报（自然科学版）》2024年第1期87-94,共8页Journal of Qiqihar University(Natural Science Edition)

基　　金：黑龙江省教育厅项目(135509127)。

摘　　要：对空气质量指数进行预测,反映数据波动的趋势与规律,提出基于诱导有序加权平均(IOWA)算子的Prophet-EEMD-XGBoost模型。首先利用Prophet算法将数据分解为趋势项、季节项、节假日、误差项;然后集合经验模态分解EEMD将原始数据分为9项IMF以及残余分量。最后,利用XGBoost模型对各分量分别进行预测,预测结果利用MAE、MAPE、RMSE、RMSPE进行评价。结果表明,相较于一些单预测模型与其他组合预测模型,基于IOWA算子的Prophet-EEMD-XGBoost组合预测模型有更好的预测效果。The purpose of this paper is to forecast AQI to reflect the trend and the fluctuation of data.So we propose a Prophet-EEMD-XGBoost model based on the induced ordered weighted average operator(IOWA).Firstly,Prophet algorithm was used to decompose the data into trend item,season item,holiday item and error item.Then,ensemble empirical mode decomposition EEMD was used to divide the original data into 9 IMF and residual component.Finally,XGBoost model was used to predict each component.MAE,MAPE,RMSE and RMSPE were used to evaluate the predicted results.The results show that compared with some single prediction models and other combined prediction models,the Prophet-EEMD-XGBoost model based on IOWA operator has better prediction effect.

关 键 词：Prophet算法 极度梯度提升树 诱导有序加权平均算子 

分 类 号：X831[环境科学与工程—环境工程]