Using support vector regression to predict PM10 and PM2.5

35th International Symposium on Remote Sensing of Environment

地球科学;生态环境科学

Weizhen, Hou^1 ; Zhengqiang, Li^1 ; Yuhuan, Zhang^1,2 ; Hua, Xu^1,2 ; Ying, Zhang^1,2 ; Kaitao, Li^1,2 ; Donghui, Li^1,2 ; Peng, Wei^1,2 ; Yan, Ma^3

Institute of Remote Sensing and Digital Earth, Chinese Academy of Sciences, Beijing, China^1

University of Chinese Academy of Sciences, Beijing, China^2

School of Earth Sciences and Engineering, Hohai University, Nanjing, China^3

关键词: Aerosol optical depths;    Gaussian kernel functions;    Generalization ability;    Generalization capability;    Grid-search method;    Meteorological parameters;    Successive over relaxation;    Support vector regression (SVR);   

Others  :  https://iopscience.iop.org/article/10.1088/1755-1315/17/1/012268/pdf
DOI  :  10.1088/1755-1315/17/1/012268

学科分类：环境科学（综合）

来源: IOP

【 摘 要 】

Support vector machine (SVM), as a novel and powerful machine learning tool, can be used for the prediction of PM10and PM2.5(particulate matter less or equal than 10 and 2.5 micrometer) in the atmosphere. This paper describes the development of a successive over relaxation support vector regress (SOR-SVR) model for the PM10and PM2.5prediction, based on the daily average aerosol optical depth (AOD) and meteorological parameters (atmospheric pressure, relative humidity, air temperature, wind speed), which were all measured in Beijing during the year of 2010-2012. The Gaussian kernel function, as well as the k-fold crosses validation and grid search method, are used in SVR model to obtain the optimal parameters to get a better generalization capability. The result shows that predicted values by the SOR-SVR model agree well with the actual data and have a good generalization ability to predict PM10and PM2.5. In addition, AOD plays an important role in predicting particulate matter with SVR model, which should be included in the prediction model. If only considering the meteorological parameters and eliminating AOD from the SVR model, the prediction results of predict particulate matter will be not satisfying.