太阳成8722(中国)有限公司-GREEN NO.1

标题: Remote Sensing Estimation of Regional NO(2)via Space-Time Neural Networks

作者: Li, TW (Li, Tongwen); Wang, Y (Wang, Yuan); Yuan, QQ (Yuan, Qiangqiang)

来源出版物: REMOTE SENSING  卷: 12  期: 16  文献号: 2514  DOI: 10.3390/rs12162514  出版年: AUG 2020  

摘要: Nitrogen dioxide (NO2) is an essential air pollutant related to adverse health effects. A space-time neural network model is developed for the estimation of ground-level NO(2)in this study by integrating ground NO(2)station measurements, satellite NO(2)products, simulation data, and other auxiliary data. Specifically, a geographically and temporally weighted generalized regression neural network (GTW-GRNN) model is used with the advantage to consider the spatiotemporal variations of the relationship between NO(2)and influencing factors in a nonlinear neural network framework. The case study across the Wuhan urban agglomeration (WUA), China, indicates that the GTW-GRNN model outperforms the widely used geographically and temporally weighted regression (GTWR), with the site-based cross-validation R(2)value increasing by 0.08 (from 0.61 to 0.69). Besides, the comparison between the GTW-GRNN and original global GRNN models shows that considering the spatiotemporal variations in GRNN modeling can boost estimation accuracy. All these results demonstrate that the GTW-GRNN based NO(2)estimation framework will be of great use for remote sensing of ground-level NO(2)concentrations.

入藏号: WOS:000565445000001

语言: English

文献类型: Article

作者关键词: ground NO2; TROPOMI; GTW-GRNN; GRNN

KeyWords Plus: TEMPORALLY WEIGHTED REGRESSION; LAND-USE REGRESSION; GROUND-LEVEL PM2.5; NITROGEN-DIOXIDE; AIR-POLLUTION; CHINA; NO2; MORTALITY; CITIES; METAANALYSIS

地址: [Li, Tongwen] Wuhan Univ, Sch Resource & Environm Sci, Wuhan 430079, Peoples R China.

[Wang, Yuan; Yuan, Qiangqiang] Wuhan Univ, Sch Geodesy & Geomat, Wuhan 430079, Peoples R China.

[Yuan, Qiangqiang] Wuhan Univ, Key Lab Geospace Environm & Geodesy, Minist Educ, Wuhan 430079, Peoples R China.

通讯作者地址: Yuan, QQ (corresponding author)，Wuhan Univ, Sch Geodesy & Geomat, Wuhan 430079, Peoples R China.

Yuan, QQ (corresponding author)，Wuhan Univ, Key Lab Geospace Environm & Geodesy, Minist Educ, Wuhan 430079, Peoples R China.

电子邮件地址: litw@whu.edu.cn; 2013301610195@whu.edu.cn; qqyuan@sgg.whu.edu.cn

影响因子：4.509