Spatiotemporal imputation of MAIAC AOD using deep learning with downscaling

REMOTE SENSING OF ENVIRONMENT

卷:237

Article

Li, Lianfa^1,2  Franklin, Meredith¹  Girguis, Mariam¹  Lurmann, Frederick³  Wu, Jun⁴  Pavlovic, Nathan³  Breton, Carrie¹  Gilliland, Frank¹  Habre, Rima¹ 

[1] Univ Southern Calif, Dept Prevent Med, Los Angeles, CA 90007 USA

[2] Chinese Acad Sci, Inst Geog Sci & Nat Resources, State Key Lab Resources & Environm Informat Syst, Beijing, Peoples R China

[3] Sonoma Technol Inc, Petaluma, CA USA

[4] Univ Calif Irvine, Susan & Henry Samueli Coll Hlth Sci, Program Publ Hlth, Irvine, CA USA

关键词: Aerosol Optical Depth;    MAIAC;    MERRA-2 GMI Replay Simulation;    Deep learning;    Downscaling;    Missingness imputation;    Air quality;   

DOI  :  10.1016/j.rse.2019.111584

来源: Elsevier

【 摘 要 】

Aerosols have adverse health effects and play a significant role in the climate as well. The Multiangle Implementation of Atmospheric Correction (MAIAC) provides Aerosol Optical Depth (AOD) at high temporal (daily) and spatial (1 km) resolution, making it particularly useful to infer and characterize spatiotemporal variability of aerosols at a fine spatial scale for exposure assessment and health studies. However, clouds and conditions of high surface reflectance result in a significant proportion of missing MAIAC AOD. To fill these gaps, we present an imputation approach using deep learning with downscaling. Using a baseline autoencoder, we leverage residual connections in deep neural networks to boost learning and parameter sharing to reduce overfitting, and conduct bagging to reduce error variance in the imputations. Downscaled through a similar auto-encoder based deep residual network, Modern-Era Retrospective analysis for Research and Applications Version 2 (MERRA-2) GMI Replay Simulation (M2GMI) data were introduced to the network as an important gap-filling feature that varies in space to be used for missingness imputations. Imputing weekly MAIAC AOD from 2000 to 2016 over California, a state with considerable geographic heterogeneity, our full (non-full) residual network achieved mean R-2 = 0.94 (0.86) [RMSE = 0.007 (0.01)] in an independent test, showing considerably better performance than a regular neural network or non-linear generalized additive model (mean R-2 = 0.78-0.81; mean RMSE = 0.013-0.015). The adjusted imputed as well as combined imputed and observed MAIAC AOD showed strong correlation with Aerosol Robotic Network (AERONET) AOD (R = 0.83; R-2 = 0.69, RMSE = 0.04). Our results show that we can generate reliable imputations of missing AOD through a deep learning approach, having important downstream air quality modeling applications.

【 授权许可】

Free