Dynamic forecasting model of short-term PM2.5 concentration based on machine learning

doi:10.11772/j.issn.1001-9081.2017.11.3057

Journal of Computer Applications ›› 2017, Vol. 37 ›› Issue (11): 3057-3063.DOI: 10.11772/j.issn.1001-9081.2017.11.3057

Previous Articles Next Articles

Dynamic forecasting model of short-term PM2.5 concentration based on machine learning

DAI Lijie¹, ZHANG Changjiang¹, MA Leiming²

1. College of Mathematics, Physics and Information Engineering, Zhejiang Normal University, Jinhua Zhejiang 321004, China;
2. Central Meteorological Observatory, Shanghai Meteorological Bureau, Shanghai 200030, China

Received:2017-05-16 Revised:2017-06-09 Online:2017-11-10 Published:2017-11-11
Supported by:
This work is partially supported by the National Natural Science Foundation of China (41575046), the Project of Commonweal Technique and Application Research of Zhejiang Province (2016C33010), the Science and Technology Planning Program of Jinhua City (2014-3-028).

基于机器学习的PM2.5短期浓度动态预报模型

戴李杰¹, 张长江¹, 马雷鸣²

1. 浙江师范大学数理与信息工程学院, 浙江金华 321004;
2. 上海市气象局中心气象台, 上海 200030

通讯作者: 张长江
作者简介:戴李杰(1990-),男,浙江桐庐人,硕士研究生,主要研究方向:信号与信息处理、机器学习、模式识别;张长江(1974-),男,黑龙江齐齐哈尔人,教授,博士,主要研究方向:信号与信息处理、机器学习、模式识别;马雷鸣(1975-),男,新疆石河子人,研究员,博士,主要研究方向:气象数值预报。
基金资助:
国家自然科学基金资助项目（41575046）；浙江省科技厅公益性技术应用研究计划项目（2016C33010）；浙江省金华市科技计划项目（2014-3-028）。

Abstract

Abstract: The forecasted concentration of PM2.5 forecasting model greatly deviate from the measured concentration. In order to solve this problem, the data (from February 2015 to July 2015), consisting of measured PM2.5 concentration, PM2.5 model (WRF-Chem) forecasted concentration and model forecasted data of 5 main meteorological factors, were provided by Shanghai Pudong Meteorological Bureau. Support Vector Machine (SVM) and Particle Swarm Optimization (PSO) algorithm were combined to build rolling forecasting model of hourly PM2.5 concentration in 24 hours in advance. Meanwhile, the nighttime average concentration, daytime average concentration and daily average concentration during the upcoming day were forecasted by rolling model. Compared with Radical Basis Function Neural Network (RBFNN), Multiple Linear Regression (MLR) and WRF-Chem, the experimental results show that the proposed SVM model improves the forecasting accuracy of PM2.5 concentration one hour in advance (according with the results concluded from finished research), and can comparatively well forecast PM2.5 concentration in 24 hours in advance, and effectively forecast the nighttime average concentration, daytime average concentration and daily average concentration during the upcoming day. In addition, the proposed model has comparatively high forecasting accuracies of hourly PM2.5 concentration in 12 hours in advance and nighttime average concentration during the upcoming day.

Key words: machine learning, Particle Swarm Optimization (PSO) algorithm, dynamic model, rolling forecasting

摘要： 针对目前现有的PM2.5模式预报系统的预报值偏离实际浓度较大的问题，从上海市浦东气象局获得2015年2月至7月的PM2.5实况观测浓度、PM2.5模式预报（WRF-Chem）浓度和5个主要气象因子的模式预报数据资料，联合应用支持向量机（SVM）和粒子群优化（PSO）算法建立滚动预报模型，对PM2.5未来24小时浓度进行预报，同时对未来一天的昼、夜均值及日均值浓度进行预报，并与径向基函数神经网络（RBFNN）、多元线性回归法（MLR）、模式预报（WRF-Chem）作对比。实验结果表明，相比其他预报方法，所提出的SVM模型较大提高了PM2.5未来1小时浓度预报精度，这与此前的研究结论相符；所提模型能对PM2.5未来24小时浓度进行较好的预报，能对未来一天的昼均值、夜均值及日均值进行有效预报，并且对未来12小时的逐时浓度及未来一天的夜均值浓度的预报准确度较高。

关键词: 机器学习, 粒子群优化算法, 动态模型, 滚动预报

CLC Number:

P456.8

DAI Lijie, ZHANG Changjiang, MA Leiming. Dynamic forecasting model of short-term PM2.5 concentration based on machine learning[J]. Journal of Computer Applications, 2017, 37(11): 3057-3063.

戴李杰, 张长江, 马雷鸣. 基于机器学习的PM2.5短期浓度动态预报模型[J]. 计算机应用, 2017, 37(11): 3057-3063.

References

[1] 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.(LIU H J. Developing pattern prediction, casual analysis and simulation of PM2.5 pollution in Wuhan city[D]. Changsha:Hunan University, 2014.)
[2] 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.
[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] ZHANG P, ZHANG T, HE L, 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.
[5] WU Y R, GUO J P, ZHANG X Y, et al. Synergy of satellite and ground based observations in estimation of particulate matter in eastern China[J]. Science of the Total Environment, 2012, 433(7):20-30.
[6] ZHENG H M, SHANG X X. Study on prediction of atmospheric PM2.5 based on RBF neural network[C]//Proceedings of the 20134th International Conference on Digital Manufacturing and Automation. Piscataway, NJ:IEEE, 2013:1287-1289.
[7] ZHOU Q P, JIANG H Y, WANG J Z, et al. A hybrid model for PM2.5 forecasting based on ensemble empirical mode decomposition and a general regression neural network[J]. Science of the Total Environment, 2014, 496(2):264-274.
[8] FENG X, LI Q, ZHU Y J, et al. Artificial neural networks forecasting of PM2.5 pollution using air mass trajectory based geographic model and wavelet transformation[J]. Atmospheric Environment, 2015, 107:118-128.
[9] VOUKANTSIS D, KARATZAS K, KUKKONEN J, et al. Intercomparison of air quality data using principal component analysis, and forecasting of PM10 and PM2.5 concentrations using artificial neural networks, in Thessaloniki and Helsinki[J]. Science of the Total Environment, 2011, 409(7):1266-1276.
[10] MISHRA D, GOYAL P, UPADHYAY A. Artificial intelligence based approach to forecast PM2.5 during haze episodes:a case study of Delhi, India[J]. Atmospheric Environment, 2015, 102:239-248.
[11] 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, 34(8):2212-2216. (LI L,MA L,HE J F,et al. PM2.5 concentration prediction model of least squares support vector machine based on feature vector[J]. Journal of Computer Applications, 2014, 34(8):2212-2216.)
[12] 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.(LIU J, YANG P, LYU W S, 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.)
[13] SUN W, ZHANG H, PALAZOGLU A, 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(3):93-103.
[14] YANG Z C. Modeling and forecasting daily movement of ambient air mean PM2.5 concentration based on the elliptic orbit model with weekly quasi-periodic extension:a case study[J]. Environmental Science and Pollution Research, 2014, 21(16):9959-9972.
[15] 张长江,戴李杰,马雷鸣. 应用SVM的PM2.5未来一小时浓度动态预报模型[J]. 红外与激光工程,2017, 46(2):252-259.(ZHANG C J, DAI L J, MA L M. Dynamic model for forecasting concentration of PM2.5 one hour in advance using support vector machine[J]. Infrared and Laser Engineering, 2017, 46(2):252-259.)
[16] ZHANG C J, DAI L J, MA L M. Rolling forecasting model of PM2.5 concentration based on support vector machine and particle swarm optimization[C]//Proceedings of the 2016 International Symposium on Optoelectronic Technology and Application. Bellingham, WA:SPIE, 2016:10156.
[17] 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. (LIANG D,YANG Q Y,HUANG W J,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.)
[18] 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.(JIN Y,CHU Z,ZHANG J. 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.)
[19] YOU Z Y, CHEN W R, HE G J, et al. Adaptive weight particle swarm optimization algorithm with constriction factor[C]//Proceedings of the 2010 International Conference of Information Science and Management Engineering. Washington, DC:IEEE Computer Society, 2010:245-248.

Dynamic forecasting model of short-term PM2.5 concentration based on machine learning

基于机器学习的PM2.5短期浓度动态预报模型

PDF

Knowledge

Abstract

Cite this article

share this article

References

Related Articles 15

Recommended Articles

Metrics

[1]	MAO Mingze, CAO Ruihao, YAN Chungang. Semi-supervised classification algorithm based on weight diversity [J]. Journal of Computer Applications, 2021, 41(9): 2473-2480.
[2]	GUO Mian, ZHANG Jinyou. Computation offloading policy for machine learning in mobile edge computing environments [J]. Journal of Computer Applications, 2021, 41(9): 2639-2645.
[3]	QIN Binbin, PENG Liangkang, LU Xiangming, QIAN Jiangbo. Research progress on driver distracted driving detection [J]. Journal of Computer Applications, 2021, 41(8): 2330-2337.
[4]	ZHANG Meng, GUO Jianquan. Channel structure choice of closed-loop supply chain under uncertain demand and recovery [J]. Journal of Computer Applications, 2021, 41(7): 2100-2107.
[5]	JIANG Qianyu, WANG Fengying, JIA Lipeng. Malware detection method based on perceptual hash algorithm and feature fusion [J]. Journal of Computer Applications, 2021, 41(3): 780-785.
[6]	QIN Jing, ZUO Changqing, WANG Zumin, JI Changqing, WANG Baofeng. Design of abnormal electrocardiograph monitoring model based on stacking classifier [J]. Journal of Computer Applications, 2021, 41(3): 887-890.
[7]	MENG Xiangrui, YANG Wenzhong, WANG Ting. Survey of sentiment analysis based on image and text fusion [J]. Journal of Computer Applications, 2021, 41(2): 307-317.
[8]	FAN Xiaomao, XIONG Honglin, ZHAO Gansen. Cleaning scheduling model with constraints and its solution [J]. Journal of Computer Applications, 2021, 41(2): 577-582.
[9]	Haojie LOU, Yuanlin ZHENG, Kaiyang LIAO, Hao LEI, Jia LI. Defect target detection for printed matter based on Siamese-YOLOv4 [J]. Journal of Computer Applications, 2021, 41(11): 3206-3212.
[10]	Xiaolong LIU, Shitong WANG. Open set fuzzy domain adaptation algorithm via progressive separation [J]. Journal of Computer Applications, 2021, 41(11): 3127-3131.
[11]	WANG Yahui, QIAN Yuhua, LIU Guoqing. Ordinal decision tree algorithm based on fuzzy advantage complementary mutual information [J]. Journal of Computer Applications, 2021, 41(10): 2785-2792.
[12]	JIANG Yangsheng, WANG Shengnan, TU Jiaqi, LI Sha, WANG Hongjun. Comprehensive prediction of thermal comfort and energy consumption for high-speed railway stations [J]. Journal of Computer Applications, 2021, 41(1): 249-257.
[13]	ZHU Lin, YU Haitao, LEI Xinyu, LIU Jing, WANG Ruofan. Brain network feature identification algorithm for Alzheimer's patients based on MRI image [J]. Journal of Computer Applications, 2020, 40(8): 2455-2459.
[14]	LUO Bin, YU Bo. Computation offloading strategy based on particle swarm optimization in mobile edge computing [J]. Journal of Computer Applications, 2020, 40(8): 2293-2298.
[15]	ZHOU Wenfeng, LIANG Xiaolei, TANG Kexin, LI Zhanghong, FU Xiuwen. Hybrid particle swarm optimization algorithm with topological time-varying and search disturbance [J]. Journal of Computer Applications, 2020, 40(7): 1913-1918.