Please wait a minute...


Remote Sensing Technology and Application  2022, Vol. 37 Issue (2): 424-435    DOI: 10.11873/j.issn.1004-0323.2022.2.0424
PM2.5 Remote Sensing Retrieval and Change Analysis in Beijing-Tianjin-Hebei Region based on Random Forest Model
Xinli Kang1,2(),Wenghao Zhang1,2(),Yuanping Liu1,2,Xingfa Gu3,Tao Yu3,Lili Zhang3,Huakun Xu1,2
1.School of Remote Sensing and Information Engineering,North China Institute of Aerospace Engineering,Langfang 065000,China
2.Heibei Spacer Remote Sensing Information Processing and Application of Collaborative Innovation Center,Langfang 065000,China
3.National Engineering Laboratory for Satellite Remote Sensing Applications,Aerospace Information Research Institute,Chinese Academy of Sciences,Beijing 100094,China
Download:  HTML  PDF (10038KB) 
Export:  BibTeX | EndNote (RIS)      

Atmospheric fine particulate matter PM2.5 is the main atmospheric environmental pollutant that affects human living environment and health. It is of great significance to study the seasonal variation and spatial distribution characteristics of PM2.5 mass concentration for the prevention and treatment of air pollutants. In this study, the MODIS L2 AOD products, MERRA-2 meteorological data and the PM2.5 measured data from ground stations from 2018 to 2020 were used to build the AOD-PM2.5 inversion model based on the improved random forest algorithm. The PM2.5 in Beijing-Tianjin-Hebei region was estimated, and the spatial distribution characteristics and seasonal variation of PM2.5 mass concentration were analyzed. The results showed that: (1) The mean values of determination coefficients (R2) of spring, summer, autumn and winter model were 0.78, 0.66, 0.83 and 0.83, respectively. And the accuracy of simulation is higher.(2) The PM2.5 concentrations of spring, summer, autumn and winter in Beijing-Tianjin-Hebei region from 2018 to 2020 showed significant spatial distribution characteristics and seasonal variation. The maximum of PM2.5 concentrations occurred in winter and the minimum value appeared in summer. (3) Compared with the same season over the years, the PM2.5 pollution range and PM2.5 concentration in the Beijing-Tianjin-Hebei region have improved. Compared with 2018 and 2019, the PM2.5 pollution range in spring and autumn of 2020 improved significantly.

Key words:  PM2.5      Random Forest      MODIS      MERRA-2      Beijing-Tianjin-Hebei     
Received:  07 June 2021      Published:  17 June 2022
ZTFLH:  P407  
Corresponding Authors:  Wenghao Zhang     E-mail:;
E-mail this article
Add to my bookshelf
Add to citation manager
E-mail Alert
Articles by authors
Xinli Kang
Wenghao Zhang
Yuanping Liu
Xingfa Gu
Tao Yu
Lili Zhang
Huakun Xu

Cite this article: 

Xinli Kang,Wenghao Zhang,Yuanping Liu,Xingfa Gu,Tao Yu,Lili Zhang,Huakun Xu. PM2.5 Remote Sensing Retrieval and Change Analysis in Beijing-Tianjin-Hebei Region based on Random Forest Model. Remote Sensing Technology and Application, 2022, 37(2): 424-435.

URL:     OR

Fig.1  Distribution map of ground stations in Beijing-Tianjin-Hebei region from 2018 to 2020
Fig.2  Inversion of PM2.5 concentration flow chart in Beijing-Tianjin-Hebei region
Fig.3  Statistical chart of dependent and independent variables
Fig.4  Parameter optimization of the number and the maximum depth of decision trees
Fig.5  Accuracy evaluation for random forest model
Fig.6  The inversion results in some single days
Fig.7  Seasonal average results of PM2.5 during 2018~2020
Fig.8  Statistical chart of PM2.5’s seasonal mean value during 2018~2020
1 Li Yonghui, Wang Yang, Yi Qinghuan,et al. The study on air quality change of Nanchang city from 2004 to 2015 years based on satellite remote sensing MODIS data[J]. Journal of Jiangxi Normal University(Natural Science Edition),2019,43(2):214-220.
1 李永辉,汪洋,易清传,等. 基于卫星遥感MODIS数据反演南昌市2004—2015年空气质量变化研究[J]. 江西师范大学学报(自然科学版),2019,43(2):214-220.
2 Kira M, Kyung Min N, Selin Noelle E,et al. Health damages from air pollution in China[J]. Global Environ-mental Change,2012,22(1):55-66.DOI: .
doi: 10.1016/j.gloenvcha. 2011. 08.006
3 Zhu Jia, Liao Hong,et al. Meteorological influences on PM2.5 and O3 trends and associated health burden since China's clean air actions[J]. Science of the Total Environment, 2020, 744 : 140837.doi: .
doi: 10.1016/j.scitotenv.2020.140837
4 Chen Yun, Chen Renjie, Chen Yue,et al. The prospective effects of long-term expo-sure to ambient PM2.5 and constituents on mortality in ru-ral East China[J]. Chemosphere,2021,280:130740-130740.doi: .
doi: 10.1016/J.CHEMOSPHERE. 2021. 130740
5 Chudnovsky A, Tang C, Lyapustin A,et al. A critical assessment of high-resolution aerosol optical depth retrievals for fine particulate matter predictions[J]. Atmospheric Chemistry and Physics,2013,13(21):14581-14611. DOI: .
doi: 10.5194/acp-13-10907-2013
6 Mordukhovich I, Kloog I, Coull B,et al. Association between particulate air pollution and QT interval duration in an elderly cohort[J]. Epidemiology,2016,27(2):284-290.
7 Li Zhipeng, Chen Jian. Remote sensing retrieval of atmospheric rine particle PM2.5 based on GOCI satellite and its temporal and spatial distribution[J].Remote Sensing Technology and Application,2020,35(1):163-173.
7 李志鹏,陈健.基于GOCI卫星的大气细颗粒物PM2.5的遥感反演及其时空分布规律研究[J].遥感技术与应用,2020,35(1):163-173.
8 Liu Zeyang. Aerosol optical properties study based on ground observation[D].Hefei:University of Science and Technology of China,2020.
8 刘泽阳. 基于地基观测的气溶胶光学特性研究[D].合肥:中国科学技术大学,2020.
9 He Aihong, Xin Zhao, Liu Shu,et al. Spatial and temporal distribution of PM2.5 in Pingxiang city[J]. Journal of Pingxiang University,2018,35(6):49-52.
9 何爱红,辛朝,刘澍,等.萍乡市大气污染PM2.5时空分布规律[J].萍乡学院学报,2018,35(6):49-52.
10 Shao Qi, Chen Yunhao, Li Jing. Inversion of PM2.5 concentration in Beijing based on satellite remote sensing and meteorological reanalysis data[J]. Geography and GeoInfo-rmation Science,2018,34(3):38-44.
10 [邵琦,陈云浩,李京.基于卫星遥感和气象再分析资料的北京市PM2.5浓度反演研究[J].地理与地理信息科学,2018,34(3):38-44.
11 Zhang Wenhao, Zheng Fengjie, Zhang Wenpeng,et al. Es-timating ground-level hourly PM2.5 Concentrations over north China plain with deep neural networks[J]. Journal of the Indian Society of Remote Sensing,2021(9).DOI: .
doi: 10.1007/s12524- 021-01344-3
12 Wang Jun, Christopher SA. Intercomparison between satellite‐derived aerosol optical thickness and PM2.5 mass: Implications for air quality studies[J]. Geophysical Research Letters,2003,30(21):1-14.DOI: .
doi: 10.1029/2003GL018174
13 Song W Z, Jia H F, Huang J F,et al. A satelli-tebased geographically weighted regression model for regional PM2.5 estimation over the Pearl River Delta region in China[J]. Remote Sensing of Environment,2014,154:1-7.DOI: .
doi: 10.1016/j.rse. 2014.08.008
14 Hu X F, Belle Jessica H, Meng X,et al. Estimating PM2.5 concentrations in the conterminous united states using the random forest approach[J]. Environmental science & technology,2017,51(12):6936. DOI: .
doi: 10.1021/acs.est.7b01210
15 Jia Songlin, Su Lin, Tao Jinhua,et al. A study of multiple regression method for estimating concentration of fine particulate matter using satellite remote sensing[J]. China Environmental Science,2014,34(3):565-573.
15 贾松林,苏林,陶金花,等.卫星遥感监测近地表细颗粒物多元回归方法研究[J]. 中国环境科学,2014,34(3):565-573.
16 Shen Yuan, Chen Chaoliang, Qian Jing,et al. High resolution PM2.5 estimation using remote sensing data based on random forest——A case study of Guangdong,China[J].Journal of Integration Technology,2018,7(3):31-41.
16 申原,陈朝亮,钱静,等.基于随机森林的高分辨率PM2.5遥感反演——以广东省为例[J].集成技术,2018,7(3):31-41.
17 Liu Yang, Sarnat Jeremy A, Vasu Kilaru,et al. Estimating ground-level PM2.5 in the eastern United States using satellite remote sensing[J]. Environmental science & technology,2005,39(9):3269-3278.DOI: .
doi: 10.1021/es049352m
18 Zhang Yibo, Chen Xue, Yu Shaocai,et al. City-level air quality improvement in the Beijing-Tianjin-Hebei region from 2016/17 to 2017/18 hea-ting seasons: Attributions and process analysis[J]. Environ-mental Pollution, 2021, 274(prepublish):116523-116523. doi: .
doi: 10.1016/J.ENVPOL.2021.116523
19 Wei Shimei, Pan Jinghu, Wenliang Tuo. Estimation and spatial-temporal distribution characteristics of PM2.5 concentration by remote sensing in China in 2015[J].Remote Sensing Technology and Application,2020,35(4):845-854.
19 魏石梅,潘竟虎,妥文亮.2015年中国PM2.5浓度遥感估算与时空分布特征[J].遥感技术与应用,2020,35(4):845-854.
20 Wang Jie. Spatial and temporal variability of aerosol optical depth in China based on MERRA-2 data[D]. Lanzhou: Northwest Normal University,2020.
20 王洁. 基于MERRA-2数据的中国气溶胶光学厚度时空变化研究[D]. 兰州:西北师范大学,2020.
21 Chaplot V, Darboux F, Bourennane H,et al. Accuracy of interpolation techniques for the derivation of digital elevation models in relation to landform types and data density[J]. Geomorphology,2006,77(1-2):126-141.
22 Wu Zhiming, Li Jiaochao, Wang Rui,et al. Estimation of CDOM concentration in inland lake based on random forest using Sentinel-3A OLCI[J]. Journal of Lake Sciences,2018,30(4):979-991.
22 吴志明,李建超,王睿,等.基于随机森林的内陆湖泊水体有色可溶性有机物(CDOM)浓度遥感估算[J].湖泊科学,2018,30(4):979-991.
23 Breiman L. Random forests[J]. Machine Learning,2001,45(1):5-32. DOI: .
doi: 10.1023/A:1010933404324
24 Ren Cairong, Xie Gang. Prediction of PM2.5 concentration level based on random forest and meteorological parameters[J]. Computer Engineering and Applications,2019,55(2):213-220.
24 任才溶,谢刚.基于随机森林和气象参数的PM2.5浓度等级预测[J].计算机工程与应用,2019,55(2):213-220.
25 Lin Haifeng, Xin Jinyuan, Zhang Wenyu,et al. Comparison of atmospheric matter and aeros optical depth in Beijing city[J],Environmental Science,2013,34(3):826-834.
25 林海峰,辛金元,张文煜,等.北京市近地层颗粒物浓度与气溶胶光学厚度相关性分析研究[J].环境科学,2013,34(3):826-834.
26 Guo Bin, Zhang Dingming, Pei Lin,et al. Estimating PM2.5 concentrations via random forest method using satellite, auxiliary, and ground-level station dataset at multiple temp-oral scales across China in 2017[J]. Science of the Total Environment,2021,778.DOI: .
doi: 10.1016/J.SCITOTENV.2021.146288
27 Fang Xinrui, Wen Zhaofei, Chen Gulong,et al. Remote sensing estimation of suspended sediment concentration based on Random Forest Regression Model[J]. Journal of Remote Sensing,23(4):756-772.方馨蕊,温兆飞,陈吉龙,等.随机森林回归模型的悬浮泥沙浓度遥感估算[J].遥感学报,2019,23(4):756-772.
28 Yang Yingchuan, Ge Baozhu, Hao Saiyu,et al. Inversion of PM2.5 concentration in Beijing based on visibility and AOD data[J]. Climactic and Environmental Research,2020(5):521-530.
28 杨颖川,葛宝珠,郝赛宇,等. 基于能见度及AOD数据的北京市PM2.5浓度的反演[J]. 气候与环境研究,2020(5):521-530.
29 Wang Weiqi, Zhang Zengliang, Song Bin,et al. Correlation between averaged PM2.5 concentrations and MODIS aerosol optical depth during different periods in Beijing[J]. Acta Scientiae Circumstantiae,2016,36(8):2794-2802.
29 王伟齐,臧增亮,宋彬,等.北京地区不同时段平均PM2.5浓度与MODIS气溶胶光学厚度相关性分析[J]. 环境科学学报,2016,36(8):2794-2802.
[1] . [J]. Remote Sensing Technology and Application, 1989, 4(2): 50 -55 .
[2] . [J]. Remote Sensing Technology and Application, 1989, 4(3): 1 -8 .
[3] . [J]. Remote Sensing Technology and Application, 1991, 6(2): 57 -59 .
[4] Rui YANG Su Yang. U-Net neural networks and its application in high resolution satellite image classification[J]. Remote Sensing Technology and Application, 0, (): 0 .
[5] . [J]. Remote Sensing Technology and Application, 1994, 9(2): 67 -68 .
[6] WangHong LuXian. The Metefile ExPression Method of SPatial Information in GIS[J]. Remote Sensing Technology and Application, 1995, 10(1): 49 -52 .
[7] ZHANG Bo,WANG Chao,ZHANG Hong,WU Fan. High Quality Ortho-rectification Production forHigh Resolution SAR Image[J]. Remote Sensing Technology and Application, 2009, 24(1): 93 -96 .
[8] REN Jie, BAI Yan-Chen, WANG Jin-Di. An Efficient Method for Extracting Vegetation Coverage from Digital Photographs[J]. Remote Sensing Technology and Application, 2010, 25(5): 719 -724 .
[9] . [J]. Remote Sensing Technology and Application, 1989, 4(3): 46 -53 .
[10] LIU Hai-Yan, Niu Zhen-Guo, CHEN Xiao-Ling . Applications of EOS-MODIS Data on Crop Monitoring in China[J]. Remote Sensing Technology and Application, 2005, 20(5): 531 -526 .