A Robust Deep Learning Approach for Spatiotemporal Estimation of Satellite AOD and PM2.5 | |
Li, Lianfa1,2,3 | |
刊名 | REMOTE SENSING
![]() |
2020-01-02 | |
卷号 | 12期号:2页码:27 |
关键词 | PM2.5 satellite AOD deep learning autoencoder residual network exposure estimation high spatiotemporal resolution |
DOI | 10.3390/rs12020264 |
通讯作者 | Li, Lianfa(lilf@lreis.ac.cn) |
英文摘要 | Accurate estimation of fine particulate matter with diameter <= 2.5 mu m (PM2.5) at a high spatiotemporal resolution is crucial for the evaluation of its health effects. Previous studies face multiple challenges including limited ground measurements and availability of spatiotemporal covariates. Although the multiangle implementation of atmospheric correction (MAIAC) retrieves satellite aerosol optical depth (AOD) at a high spatiotemporal resolution, massive non-random missingness considerably limits its application in PM2.5 estimation. Here, a deep learning approach, i.e., bootstrap aggregating (bagging) of autoencoder-based residual deep networks, was developed to make robust imputation of MAIAC AOD and further estimate PM2.5 at a high spatial (1 km) and temporal (daily) resolution. The base model consisted of autoencoder-based residual networks where residual connections were introduced to improve learning performance. Bagging of residual networks was used to generate ensemble predictions for better accuracy and uncertainty estimates. As a case study, the proposed approach was applied to impute daily satellite AOD and subsequently estimate daily PM2.5 in the Jing-Jin-Ji metropolitan region of China in 2015. The presented approach achieved competitive performance in AOD imputation (mean test R-2: 0.96; mean test RMSE: 0.06) and PM2.5 estimation (test R-2: 0.90; test RMSE: 22.3 mu g/m(3)). In the additional independent tests using ground AERONET AOD and PM2.5 measurements at the monitoring station of the U.S. Embassy in Beijing, this approach achieved high R-2 (0.82-0.97). Compared with the state-of-the-art machine learning method, XGBoost, the proposed approach generated more reasonable spatial variation for predicted PM2.5 surfaces. Publically available covariates used included meteorology, MERRA2 PBLH and AOD, coordinates, and elevation. Other covariates such as cloud fractions or land-use were not used due to unavailability. The results of validation and independent testing demonstrate the usefulness of the proposed approach in exposure assessment of PM2.5 using satellite AOD having massive missing values. |
资助项目 | National Natural Science Foundation of China[41471376] ; Strategic Priority Research Program of Chinese Academy of Sciences Grant[XDA19040501] |
WOS关键词 | AIR-POLLUTION ; PARTICULATE MATTER ; OPTICAL DEPTH ; RESPIRATORY SYMPTOMS ; AEROSOL PROPERTIES ; RETRIEVALS ; REGRESSION ; EXPOSURE ; CHINA ; URBAN |
WOS研究方向 | Remote Sensing |
语种 | 英语 |
出版者 | MDPI |
WOS记录号 | WOS:000515569800063 |
资助机构 | National Natural Science Foundation of China ; Strategic Priority Research Program of Chinese Academy of Sciences Grant |
内容类型 | 期刊论文 |
源URL | [http://ir.igsnrr.ac.cn/handle/311030/132503] ![]() |
专题 | 中国科学院地理科学与资源研究所 |
通讯作者 | Li, Lianfa |
作者单位 | 1.Univ Chinese Acad Sci, Beijing 100049, Peoples R China 2.Chinese Acad Sci, Inst Geog Sci & Nat Resources Res, State Key Lab Resources & Environm Informat Syst, Datun Rd, Beijing 100101, Peoples R China 3.Spatial Data Intelligence Lab Ltd Liabil Co, Casper, WY 82609 USA |
推荐引用方式 GB/T 7714 | Li, Lianfa. A Robust Deep Learning Approach for Spatiotemporal Estimation of Satellite AOD and PM2.5[J]. REMOTE SENSING,2020,12(2):27. |
APA | Li, Lianfa.(2020).A Robust Deep Learning Approach for Spatiotemporal Estimation of Satellite AOD and PM2.5.REMOTE SENSING,12(2),27. |
MLA | Li, Lianfa."A Robust Deep Learning Approach for Spatiotemporal Estimation of Satellite AOD and PM2.5".REMOTE SENSING 12.2(2020):27. |
个性服务 |
查看访问统计 |
相关权益政策 |
暂无数据 |
收藏/分享 |
除非特别说明,本系统中所有内容都受版权保护,并保留所有权利。
修改评论