欢迎访问《环境监测管理与技术》编辑部网站！

文章摘要

基于小波分析优化PM2.5浓度预测模型

Wavelet Analysis for Optimizating PM2.5 Concentration Prediction Models

DOI：

英文关键词: PM2.5 Meteorological elements Multiple linear regression BP neural network Wavelet analysis

基金项目:广西气象科研基金资助项目（桂气科 2019M22）；贵港市科技局基金资助项目（贵科攻 1505004）

作者	单位
许艺馨	广西物流职业技术学院
任杰	南京理工大学环境科学与工程学院
冯磊	广西物流职业技术学院
梁莹露	贵港市气象局
刘怡明	贵港市气象局

摘要点击次数: 621

全文下载次数: 40

中文摘要:

采用多元线性回归方法（MLR）和BP神经网络方法（BPNN），按1 h、3 h、6 h、12 h、24 h、48 h预测时长对贵港市2015—2018年PM2.5浓度建模并检验对比模型准确率。结果表明，基于MLR与BPNN都能对PM2.5浓度作预测，预测效果随着预测时长的增加而下降，MLR、BPNN模型预测结果平均绝对误差（MAE）分别为401 μg/m3～1548 μg/m3、389 μg/m3～1563 μg/m3。采用小波分析方法对污染物数据优化并再次建模，结果表明，小波-多元线性回归（W MLR）模型与小波-神经网络（W BPNN）模型均得到优化，3 h～24 h预测时长优化效果尤为显著，W MLR、W BPNN模型预测结果分别使MAE降低16%～135%、08%～98%，且后者预测效果优于前者。

英文摘要:

Using multiple linear regression method (MLR) and BP neural network method (BPNN), PM2.5 concentration prediction models were built by taking 1 h, 3 h, 6 h, 12 h, 24 h, 48 h as prediction time from 2015 to 2018 in Guigang. The accuracy of the models were tested and compared. The results showed that both MLR and BPNN could be used in PM2.5 concentration prediction. The prediction accuracy declined as the prediction time increased. The mean absolute error(MAE) of the prediction models by MLR and BPNN were 4.01 μg/m3～15.48 μg/m3 and 3.89 μg/m3～15.63 μg/m3, respectively. Using wavelet data analysis method for optimizing the contaminant data and making the model again, both W MLR and W BPNN were optimized. The optimization was significant when the prediction time was from 3 h to 24 h. By W MLR and W BPNN models, the MAE reduced 1.6%～13.5% and 0.8%～9.8%, respectively, and W BPNN model was superior to W MLR model in prediction.

查看全文查看/发表评论下载PDF阅读器

关闭