太阳成8722(中国)有限公司-GREEN NO.1

作者： Li, TW (Li, Tongwen); Shen, HF (Shen, Huanfeng); Yuan, QQ (Yuan, Qiangqiang); Zhang, XC (Zhang, Xuechen); Zhang, LP (Zhang, Liangpei)

来源出版物：GEOPHYSICAL RESEARCH LETTERS 卷：44 期：23 页码: 11985-11993 DOI：10.1002/2017GL075710 出版年： DEC 16 2017

摘要：Fusing satellite observations and station measurements to estimate ground-level PM2.5 is promising for monitoring PM2.5 pollution. A geo-intelligent approach, which incorporates geographical correlation into an intelligent deep learning architecture, is developed to estimate PM2.5. Specifically, it considers geographical distance and spatiotemporally correlated PM2.5 in a deep belief network (denoted as Geoi-DBN). Geoi-DBN can capture the essential features associated with PM2.5 from latent factors. It was trained and tested with data from China in 2015. The results show that Geoi-DBN performs significantly better than the traditional neural network. The out-of-sample cross-validation R-2 increases from 0.42 to 0.88, and RMSE decreases from 29.96 to 13.03 mu g/m(3). On the basis of the derived PM(2.)5 distribution, it is predicted that over 80% of the Chinese population live in areas with an annual mean PM2.5 of greater than 35 mu g/m(3). This study provides a new perspective for air pollution monitoring in large geographic regions.

入藏号：WOS:000419102400035

文献类型：Article

语种：English

扩展关键词： AEROSOL OPTICAL DEPTH; REMOTE-SENSING DATA; MULTIANGLE IMAGING SPECTRORADIOMETER; FINE PARTICULATE MATTER; AIR-QUALITY; EXPOSURE ASSESSMENT; UNITED-STATES; CHINA; POLLUTION; MODIS

通讯作者地址：Shen, HF (reprint author), Wuhan Univ, Sch Resource & Environm Sci, Wuhan, Hubei, Peoples R China.

Shen, HF (reprint author), Collaborat Innovat Ctr Geospatial Technol, Wuhan, Hubei, Peoples R China.

Shen, HF (reprint author), Wuhan Univ, Key Lab Geog Informat Syst, Minist Educ, Wuhan, Hubei, Peoples R China.

电子邮件地址：shenhf@whu.edu.cn

地址：

[Li, Tongwen; Shen, Huanfeng; Zhang, Xuechen] Wuhan Univ, Sch Resource & Environm Sci, Wuhan, Hubei, Peoples R China.

[Shen, Huanfeng; Yuan, Qiangqiang; Zhang, Liangpei] Collaborat Innovat Ctr Geospatial Technol, Wuhan, Hubei, Peoples R China.

[Shen, Huanfeng] Wuhan Univ, Key Lab Geog Informat Syst, Minist Educ, Wuhan, Hubei, Peoples R China.

[Yuan, Qiangqiang] Wuhan Univ, Sch Geodesy & Geomat, Wuhan, Hubei, Peoples R China.

[Zhang, Liangpei] Wuhan Univ, State Key Lab Informat Engn Surveying Mapping & R, Wuhan, Hubei, Peoples R China.

影响因子：4.253