基于外界影响及时序因素的PM_(2.5)预测研究  

Prediction of PM_(2.5) Based on External Influences and Time-Series Factors

作　　者：杨艳梅 程宗毛[1] YANG Yanmei;CHENG Zongmao(School of Sciences,Hangzhou Dianzi University,Hangzhou 310037,China)

机构地区：[1]杭州电子科技大学理学院,浙江杭州310037

出　　处：《电子科技》2022年第3期51-57,共7页Electronic Science and Technology

基　　金：国家自然科学基金(61370087,71802065)。

摘　　要：随着雾霾问题逐渐加重,对其主成分之一PM_(2.5)的预测已成为广泛关注的问题。PM_(2.5)日浓度变化受多种因素影响,且具有非线性、时变性的特征,难以被准确预测。针对此问题,文中提出一种基于外界影响及时序因素的PM_(2.5)日浓度预测方法。该方法分离出PM_(2.5)日浓度的外界主要影响因素与时间因素,建立了基于外界主要影响因素的BP神经网络初步预测模型以及基于时间因素的EEMD-LSTM组合残差修正模型。使用杭州市2014年~2019年间的PM_(2.5)日浓度和其他相关因素数据进行仿真实验。结果表明,相比其他模型,文中所提出预测模型的均方根误差为2.74,预测准确率更高。As the haze problem gradually worsens,the prediction of one of its main component PM_(2.5) has become a widespread concern.The daily concentration of PM_(2.5) is affected by many factors,and it has the characteristics of non-linear and time-varying,which is difficult to accurately predict.To solve this problem,a prediction method of PM_(2.5) daily concentration based on external influences and time-series factors is proposed.With this method,the main external factors and time factors of PM_(2.5) daily concentration are separated,and the BP neural network preliminary prediction model based on the main external factors and the combined residual correction model of EEMD-LSTM neural network based on time factor are established.The daily PM_(2.5) concentration and other related factors data of Hangzhou from 2014 to 2019 are used for simulation experiments.The results show that compared with other models,the root mean square error of the prediction model proposed in the study is 2.74,and the prediction accuracy is higher.

关 键 词：雾霾 PM_(2.5) BP EEMD LSTM 时间序列预测 神经网络 时间序列分解 组合预测 

分 类 号：TP39[自动化与计算机技术—计算机应用技术] TN99[自动化与计算机技术—计算机科学与技术]