Dynamic model for forecasting concentration of PM2.5 one hour in advance using support vector machine

Zhang Changjiang; Dai Lijie; Ma Leiming

doi:10.3788/IRLA201746.0226002

Volume 46 Issue 2

Mar. 2017

Turn off MathJax

Article Contents

Article Navigation > Infrared and Laser Engineering > 2017 > 46(2): 226002-0226002(8)

Zhang Changjiang, Dai Lijie, Ma Leiming. Dynamic model for forecasting concentration of PM2.5 one hour in advance using support vector machine[J]. Infrared and Laser Engineering, 2017, 46(2): 226002-0226002(8). doi: 10.3788/IRLA201746.0226002

Citation:

Zhang Changjiang, Dai Lijie, Ma Leiming. Dynamic model for forecasting concentration of PM2.5 one hour in advance using support vector machine[J]. Infrared and Laser Engineering, 2017, 46(2): 226002-0226002(8). doi: 10.3788/IRLA201746.0226002

Dynamic model for forecasting concentration of PM2.5 one hour in advance using support vector machine

doi: 10.3788/IRLA201746.0226002

1.
College of Mathematics,Physics and Information Engineering,Zhejiang Normal University,Jinhua 321004,China;
2.
Shanghai Meteorological Bureau,Pudong New Area,Shanghai 200135,China

Received Date: 2016-06-10
Rev Recd Date: 2016-07-20
Publish Date: 2017-02-25

Abstract

Current PM2.5 model forecasting data greatly deviate from the measured concentration. In order to solve this problem, support vector machine (SVM) was applied to set up a dynamic model. The data of PM2.5 model forecasting (WRF-CHEM) concentration and the five main model forecasting meteorological factors were used as training data of SVM. The data were provided by Shanghai Meteorological Bureau in Pudong New Area (from November in 2012 to November in 2013). The dynamic model was used to improve the forecasting accuracy of PM2.5 concentration one hour in advance. SVM model was compared with radical basis function neural network (RBFNN), Multi-variable Linear Regression (MLR) and WRF-CHEM. Experimental results show that the proposed algorithm greatly improves the forecasting accuracy of PM2.5 concentration one hour in advance. SVM model performs better than RBFNN, MLR and WRF-CHEM, and has better forecasting ability for the condition with concentration dramatic changing.
- PM2.5,
- concentration forecast,
- support vector machine,
- dynamic model

References

[1]	Cobourn W G. An enhanced PM2.5 air quality forecast model based on nonlinear regression and back-trajectory concentrations[J]. Atmospheric Environment, 2010, 44(25):3015-3023.
[2]	Liu Huijun. Developing pattern prediction, casual analysis and simulation of PM2.5 pollution in Wuhan City[D]. Changsha:Hunan University, 2014. (in Chinese)刘慧君. 武汉市PM2.5污染的演变预测及成因分析和仿真[D]. 长沙:湖南大学, 2014.
[3]	Baker K R, Foley K M. A nonlinear regression model estimating single source concentrations of primary and secondarily formed PM2.5[J]. Atmospheric Environment, 2011, 45(22):3758-3767.
[4]	Qin Shanshan. Statistical analysis and forecasting of suspended particulate matters, PM10 and PM2.5[D]. Lan zhou:Lanzhou University, 2014. (in Chinese)秦珊珊. 悬浮颗粒物PM10与PM2.5的统计分析与预测[D]. 兰州:兰州大学, 2014.
[5]	Zhang Ping, Zhang Tao, He Liang, et al. Study on prediction and spatial variation of PM2.5 pollution by using improved BP artificial neural network model of computer technology and GIS[J]. Computer Modelling and New Technologies, 2014, 18(12):107-115.
[6]	Li Long, Ma Lei, He Jianfeng, et al. PM2.5 concentration prediction model of least squares support vector machine based on feature vector[J]. Journal of Computer Applications, 2014, (8):2212-2216. (in Chinese)李龙, 马磊, 贺建峰, 等. 基于特征向量的最小二乘支持向量机PM2.5浓度预测模型[J]. 计算机应用, 2014, (8):2212-2216.
[7]	Liu Jie, Yang Peng, Lv Wensheng, et al. Prediction model of PM2. 5 mass concentrations based on fuzzy time series and support vector machine[J]. Journal of University of Science and Technology Beijing, 2014, 36(12):1694-1702. (in Chinese)刘杰, 杨鹏, 吕文生, 等. 模糊时序与支持向量机建模相结合的PM2.5质量浓度预测[J]. 北京科技大学学报, 2014, 36(12):1694-1702.
[8]	Li Jianyang, Yang Zhao, Shi Shenkai. The multivariate gray model approach to predict the concentration of atmospheric fine PM2.5[C]//3rd International Conference on Energy and Environmental Protection, 2014:2362-2365.
[9]	Sun Wei, Zhang Hao, Palazoglu Ahment, et al. Prediction of 24-hour-average PM2.5 concentrations using a hidden Markov model with different emission distributions in Northern California[J]. Science of the Total Environment, 2013, 443:93-103.
[10]	Dong Ming, Yang Dong, Kuang Yan, et al. PM2.5 concentration prediction using hidden semi-Markov model-based times series data mining[J]. Expert Systems With Applications, 2009, 36(5):9046-9055.
[11]	Han Jun, Chang Bo, Lu Shaojun, et al. Image distortion calibration of imaging spectrometer with grating by SVM[J]. Infrared and Laser Engineering, 2014, 43(9):3099-3104. 韩军, 常波, 路邵军, 等. SVM的光栅成像光谱仪图像畸变校准方法[J]. 红外与激光工程, 2014, 43(9):3099-3104.
[12]	Li Jiang, Guo Lihong. Target threat assessment using improved SVM[J]. Optics and Precision Engineering, 2014, 22(5):1354-1362. (in Chinese)李姜, 郭立红. 基于改进支持向量机的目标威胁估计[J]. 光学精密工程, 2014, 22(5):1354-1362.
[13]	Wang Fangbin, Hong Jin, Sun Xiaobing, et al. Prediction of polarization pattern by SVM[J]. Optics and Precision Engineering, 2014, 22(11):2914-2922. (in Chinese)汪方斌, 洪津, 孙晓兵, 等. 基于支持向量机预测偏振模式[J]. 光学精密工程, 2014, 22(11):2914-2922.
[14]	Liang Dong, Yang Qinying, Huang Wenjiang, et al. Estimation of leaf area index based on wavelet transform and support vector machine regression in winter wheat[J]. Infrared and Laser Engineering, 2015, 44(1):335-340. (in Chinese)梁栋, 杨勤英, 黄文江, 等. 基于小波变换与支持向量机回归的冬小麦叶面积指数估算[J]. 红外与激光工程,2015, 44(1):335-340.
[15]	Jin Yan, Chu Zheng, Zhang Jin. Improved weighted support vector regression algorithm for vulnerability assessment of electronic devices illuminated or injected by high power microwave[J]. High Power Laser and Particle Beams, 2014, 26(12):177-182. (in Chinese)金焱, 褚政, 张瑾. 改进加权支持向量机回归方法器件易损性评估[J]. 强激光与粒子束, 2014, 26(12):177-182.

Proportional views

通讯作者: 陈斌, bchen63@163.com

1.
沈阳化工大学材料科学与工程学院沈阳 110142

Get Citation

PDF

XML

Article Metrics

Article views(410) PDF downloads(153) Cited by()

Proportional views

Dynamic model for forecasting concentration of PM2.5 one hour in advance using support vector machine

1. College of Mathematics,Physics and Information Engineering,Zhejiang Normal University,Jinhua 321004,China;

2. Shanghai Meteorological Bureau,Pudong New Area,Shanghai 200135,China

Received Date: 2016-06-10

Rev Recd Date: 2016-07-20

Publish Date: 2017-02-25

Key words:

Abstract: Current PM2.5 model forecasting data greatly deviate from the measured concentration. In order to solve this problem, support vector machine (SVM) was applied to set up a dynamic model. The data of PM2.5 model forecasting (WRF-CHEM) concentration and the five main model forecasting meteorological factors were used as training data of SVM. The data were provided by Shanghai Meteorological Bureau in Pudong New Area (from November in 2012 to November in 2013). The dynamic model was used to improve the forecasting accuracy of PM2.5 concentration one hour in advance. SVM model was compared with radical basis function neural network (RBFNN), Multi-variable Linear Regression (MLR) and WRF-CHEM. Experimental results show that the proposed algorithm greatly improves the forecasting accuracy of PM2.5 concentration one hour in advance. SVM model performs better than RBFNN, MLR and WRF-CHEM, and has better forecasting ability for the condition with concentration dramatic changing.

HTML

Reference (15)

[1]	Cobourn W G. An enhanced PM2.5 air quality forecast model based on nonlinear regression and back-trajectory concentrations[J]. Atmospheric Environment, 2010, 44(25):3015-3023.
[2]	Liu Huijun. Developing pattern prediction, casual analysis and simulation of PM2.5 pollution in Wuhan City[D]. Changsha:Hunan University, 2014. (in Chinese)刘慧君. 武汉市PM2.5污染的演变预测及成因分析和仿真[D]. 长沙:湖南大学, 2014.
[3]	Baker K R, Foley K M. A nonlinear regression model estimating single source concentrations of primary and secondarily formed PM2.5[J]. Atmospheric Environment, 2011, 45(22):3758-3767.
[4]	Qin Shanshan. Statistical analysis and forecasting of suspended particulate matters, PM10 and PM2.5[D]. Lan zhou:Lanzhou University, 2014. (in Chinese)秦珊珊. 悬浮颗粒物PM10与PM2.5的统计分析与预测[D]. 兰州:兰州大学, 2014.
[5]	Zhang Ping, Zhang Tao, He Liang, et al. Study on prediction and spatial variation of PM2.5 pollution by using improved BP artificial neural network model of computer technology and GIS[J]. Computer Modelling and New Technologies, 2014, 18(12):107-115.
[6]	Li Long, Ma Lei, He Jianfeng, et al. PM2.5 concentration prediction model of least squares support vector machine based on feature vector[J]. Journal of Computer Applications, 2014, (8):2212-2216. (in Chinese)李龙, 马磊, 贺建峰, 等. 基于特征向量的最小二乘支持向量机PM2.5浓度预测模型[J]. 计算机应用, 2014, (8):2212-2216.
[7]	Liu Jie, Yang Peng, Lv Wensheng, et al. Prediction model of PM2. 5 mass concentrations based on fuzzy time series and support vector machine[J]. Journal of University of Science and Technology Beijing, 2014, 36(12):1694-1702. (in Chinese)刘杰, 杨鹏, 吕文生, 等. 模糊时序与支持向量机建模相结合的PM2.5质量浓度预测[J]. 北京科技大学学报, 2014, 36(12):1694-1702.
[8]	Li Jianyang, Yang Zhao, Shi Shenkai. The multivariate gray model approach to predict the concentration of atmospheric fine PM2.5[C]//3rd International Conference on Energy and Environmental Protection, 2014:2362-2365.
[9]	Sun Wei, Zhang Hao, Palazoglu Ahment, et al. Prediction of 24-hour-average PM2.5 concentrations using a hidden Markov model with different emission distributions in Northern California[J]. Science of the Total Environment, 2013, 443:93-103.
[10]	Dong Ming, Yang Dong, Kuang Yan, et al. PM2.5 concentration prediction using hidden semi-Markov model-based times series data mining[J]. Expert Systems With Applications, 2009, 36(5):9046-9055.
[11]	Han Jun, Chang Bo, Lu Shaojun, et al. Image distortion calibration of imaging spectrometer with grating by SVM[J]. Infrared and Laser Engineering, 2014, 43(9):3099-3104. 韩军, 常波, 路邵军, 等. SVM的光栅成像光谱仪图像畸变校准方法[J]. 红外与激光工程, 2014, 43(9):3099-3104.
[12]	Li Jiang, Guo Lihong. Target threat assessment using improved SVM[J]. Optics and Precision Engineering, 2014, 22(5):1354-1362. (in Chinese)李姜, 郭立红. 基于改进支持向量机的目标威胁估计[J]. 光学精密工程, 2014, 22(5):1354-1362.
[13]	Wang Fangbin, Hong Jin, Sun Xiaobing, et al. Prediction of polarization pattern by SVM[J]. Optics and Precision Engineering, 2014, 22(11):2914-2922. (in Chinese)汪方斌, 洪津, 孙晓兵, 等. 基于支持向量机预测偏振模式[J]. 光学精密工程, 2014, 22(11):2914-2922.
[14]	Liang Dong, Yang Qinying, Huang Wenjiang, et al. Estimation of leaf area index based on wavelet transform and support vector machine regression in winter wheat[J]. Infrared and Laser Engineering, 2015, 44(1):335-340. (in Chinese)梁栋, 杨勤英, 黄文江, 等. 基于小波变换与支持向量机回归的冬小麦叶面积指数估算[J]. 红外与激光工程,2015, 44(1):335-340.
[15]	Jin Yan, Chu Zheng, Zhang Jin. Improved weighted support vector regression algorithm for vulnerability assessment of electronic devices illuminated or injected by high power microwave[J]. High Power Laser and Particle Beams, 2014, 26(12):177-182. (in Chinese)金焱, 褚政, 张瑾. 改进加权支持向量机回归方法器件易损性评估[J]. 强激光与粒子束, 2014, 26(12):177-182.

Dynamic model for forecasting concentration of PM2.5 one hour in advance using support vector machine

doi: 10.3788/IRLA201746.0226002

Abstract

References

Proportional views

通讯作者: 陈斌, bchen63@163.com

Article Metrics

Related

Proportional views