{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,14]],"date-time":"2026-03-14T20:36:19Z","timestamp":1773520579344,"version":"3.50.1"},"reference-count":44,"publisher":"MDPI AG","issue":"22","license":[{"start":{"date-parts":[[2021,11,12]],"date-time":"2021-11-12T00:00:00Z","timestamp":1636675200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["No. 41971311"],"award-info":[{"award-number":["No. 41971311"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Technology Major Project of Anhui Province","award":["No.18030801111"],"award-info":[{"award-number":["No.18030801111"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Remote Sensing"],"abstract":"<jats:p>Directly establishing the relationship between satellite data and PM2.5 concentration through deep learning methods for PM2.5 concentration estimation is an important means for estimating regional PM2.5 concentration. However, due to the lack of consideration of uncertainty in deep learning methods, methods based on deep learning have certain overfitting problems in the process of PM2.5 estimation. In response to this problem, this paper designs a deep Bayesian PM2.5 estimation model that takes into account multiple scales. The model uses a Bayesian neural network to describe key parameters a priori, provide regularization effects to the neural network, perform posterior inference through parameters, and take into account the characteristics of data uncertainty, which is used to alleviate the problem of model overfitting and to improve the generalization ability of the model. In addition, different-scale Moderate-Resolution Imaging Spectroradiometer (MODIS) satellite data and ERA5 reanalysis data were used as input to the model to strengthen the model\u2019s perception of different-scale features of the atmosphere, as well as to further enhance the model\u2019s PM2.5 estimation accuracy and generalization ability. Experiments with Anhui Province as the research area showed that the R2 of this method on the independent test set was 0.78, which was higher than that of the DNN, random forest, and BNN models that do not consider the impact of the surrounding environment; moreover, the RMSE was 19.45 \u03bcg\u00b7m\u22123, which was also lower than the three compared models. In the experiment of different seasons in 2019, compared with the other three models, the estimation accuracy was significantly reduced; however, the R2 of the model in this paper could still reach 0.66 or more. Thus, the model in this paper has a higher accuracy and better generalization ability.<\/jats:p>","DOI":"10.3390\/rs13224545","type":"journal-article","created":{"date-parts":[[2021,11,14]],"date-time":"2021-11-14T20:51:53Z","timestamp":1636923113000},"page":"4545","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":11,"title":["Estimation of PM2.5 Concentration Using Deep Bayesian Model Considering Spatial Multiscale"],"prefix":"10.3390","volume":"13","author":[{"given":"Xingdi","family":"Chen","sequence":"first","affiliation":[{"name":"School of Resources and Environmental Engineering, Anhui University, Hefei 230601, China"}]},{"given":"Peng","family":"Kong","sequence":"additional","affiliation":[{"name":"Institute of Spacecraft System Engineering, Beijing 100094, China"}]},{"given":"Peng","family":"Jiang","sequence":"additional","affiliation":[{"name":"School of Resources and Environmental Engineering, Anhui University, Hefei 230601, China"}]},{"given":"Yanlan","family":"Wu","sequence":"additional","affiliation":[{"name":"School of Resources and Environmental Engineering, Anhui University, Hefei 230601, China"},{"name":"Information Materials and Intelligent Sensing Laboratory of Anhui Province, Hefei 230601, China"}]}],"member":"1968","published-online":{"date-parts":[[2021,11,12]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"110791","DOI":"10.1016\/j.jenvman.2020.110791","article-title":"Air pollution characteristics and human health risks in key cities of northwest China","volume":"269","author":"Luo","year":"2020","journal-title":"J. Environ. Manag."},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"1987","DOI":"10.1016\/S0140-6736(13)61097-1","article-title":"Rapid health transition in China, 1990\u20132010: Findings from the Global Burden of Disease Study 2010","volume":"381","author":"Yang","year":"2013","journal-title":"Lancet"},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"2095","DOI":"10.1029\/2003GL018174","article-title":"Intercomparison between satellite-derived aerosol optical thickness and PM2.5 mass: Implications for air quality studies","volume":"30","author":"Wang","year":"2003","journal-title":"Geophys. Res. Lett."},{"key":"ref_4","doi-asserted-by":"crossref","unstructured":"Li, R., Mei, X., Chen, L., Wang, Z., Jing, Y., and Wei, L. (2020). Influence of spatial resolution and retrieval frequency on applicability of satellite-predicted PM2.5 in Northern China. Remote Sens., 12.","DOI":"10.3390\/rs12040736"},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"3762","DOI":"10.1021\/acs.est.5b05833","article-title":"Global estimates of fine particulate matter using a combined geophysical-statistical method with information from satellites, models, and monitors","volume":"50","author":"Martin","year":"2016","journal-title":"Environ. Sci. Technol."},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"72","DOI":"10.1016\/j.rse.2017.12.018","article-title":"Satellite-based mapping of daily high-resolution ground PM2.5 in China via space-time regression modeling","volume":"206","author":"He","year":"2018","journal-title":"Remote Sens. Environ."},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"5304","DOI":"10.1016\/j.atmosenv.2006.04.044","article-title":"Comparison of spatial and temporal variations of aerosol optical thickness and particulate matter over Europe","volume":"40","author":"Koelemeijer","year":"2006","journal-title":"Atmos. Environ."},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"13","DOI":"10.1016\/j.rse.2016.03.023","article-title":"Estimation of long-term population exposure to PM2.5 for dense urban areas using 1-km MODIS data","volume":"179","author":"Lin","year":"2016","journal-title":"Remote Sens. Environ."},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"252","DOI":"10.1016\/j.rse.2015.02.005","article-title":"Remote sensing of atmospheric fine particulate matter (PM2.5) mass concentration near the ground from satellite observation","volume":"160","author":"Zhang","year":"2015","journal-title":"Remote Sens. Environ."},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"3311","DOI":"10.5194\/acp-8-3311-2008","article-title":"Seven year particulate matter air quality assessment from surface and satellite measurements","volume":"8","author":"Gupta","year":"2008","journal-title":"Atmos. Chem. Phys."},{"key":"ref_11","doi-asserted-by":"crossref","first-page":"177","DOI":"10.1016\/j.envpol.2015.09.042","article-title":"Estimating ground-level PM (10) in a Chinese city by combining satellite data, meteorological information and a land use regression model","volume":"208","author":"Meng","year":"2016","journal-title":"Environ. Pollut."},{"key":"ref_12","doi-asserted-by":"crossref","first-page":"7991","DOI":"10.5194\/acp-11-7991-2011","article-title":"A novel calibration approach of MODIS AOD data to predict PM 2.5 concentrations","volume":"11","author":"Lee","year":"2011","journal-title":"Atmos. Chem. Phys."},{"key":"ref_13","doi-asserted-by":"crossref","first-page":"3269","DOI":"10.1021\/es049352m","article-title":"Estimating ground-level PM2.5 in the Eastern United States using satellite remote sensing","volume":"39","author":"Liu","year":"2005","journal-title":"Environ. Sci. Technol."},{"key":"ref_14","doi-asserted-by":"crossref","first-page":"10482","DOI":"10.1021\/acs.est.5b02076","article-title":"High-resolution satellite-derived PM2.5 from optimal estimation and geographically weighted regression over North America","volume":"49","author":"Martin","year":"2015","journal-title":"Environ. Sci. Technol."},{"key":"ref_15","doi-asserted-by":"crossref","first-page":"526","DOI":"10.1016\/j.envpol.2019.02.071","article-title":"The relationships between PM2.5 and aerosol optical depth (AOD) in mainland China: About and behind the spatio-temporal variations","volume":"248","author":"Yang","year":"2019","journal-title":"Environ. Pollut."},{"key":"ref_16","doi-asserted-by":"crossref","first-page":"169","DOI":"10.1016\/j.atmosres.2015.09.008","article-title":"A nonlinear model for estimating ground-level PM10 concentration in Xi\u2019an using MODIS aerosol optical depth retrieval","volume":"168","author":"You","year":"2016","journal-title":"Atmos. Res."},{"key":"ref_17","doi-asserted-by":"crossref","first-page":"319","DOI":"10.1016\/j.envpol.2018.04.092","article-title":"Space-time PM2.5 mapping in the severe haze region of Jing-Jin-Ji (China) using a synthetic approach","volume":"240","author":"He","year":"2018","journal-title":"Environ. Pollut."},{"key":"ref_18","doi-asserted-by":"crossref","first-page":"4173","DOI":"10.1021\/acs.est.7b05381","article-title":"Predicting daily urban fine particulate matter concentrations using a random forest model","volume":"52","author":"Brokamp","year":"2018","journal-title":"Environ. Sci. Technol."},{"key":"ref_19","doi-asserted-by":"crossref","first-page":"1417","DOI":"10.1016\/j.envpol.2018.08.029","article-title":"Evaluation of machine learning techniques with multiple remote sensing datasets in estimating monthly concentrations of ground-level PM2.5","volume":"242","author":"Xu","year":"2018","journal-title":"Environ. Pollut."},{"key":"ref_20","doi-asserted-by":"crossref","first-page":"178","DOI":"10.1016\/j.isprsjprs.2020.06.019","article-title":"Geographically and temporally weighted neural networks for satellite-based mapping of ground-level PM2.5","volume":"167","author":"Li","year":"2020","journal-title":"ISPRS J. Photogramm. Remote Sens."},{"key":"ref_21","doi-asserted-by":"crossref","first-page":"477","DOI":"10.1016\/j.atmosenv.2017.01.004","article-title":"Point-surface fusion of station measurements and satellite observations for mapping PM2.5 distribution in China: Methods and assessment","volume":"152","author":"Li","year":"2017","journal-title":"Atmos. Environ."},{"key":"ref_22","doi-asserted-by":"crossref","first-page":"100473","DOI":"10.1016\/j.uclim.2019.100473","article-title":"Forecasting concentrations of air pollutants using support vector regression improved with particle swarm optimization: Case study in Aburr\u00e1 Valley, Colombia","volume":"29","author":"Correa","year":"2019","journal-title":"Urban Clim."},{"key":"ref_23","doi-asserted-by":"crossref","first-page":"561","DOI":"10.1007\/s00477-020-01787-z","article-title":"Prediction of PM2.5 concentration based on weighted bagging and image contrast-sensitive features","volume":"34","author":"Qiao","year":"2020","journal-title":"Stoch. Environ. Res. Risk Assess."},{"key":"ref_24","doi-asserted-by":"crossref","unstructured":"Tao, M., Wang, Z., Tao, J., Chen, L., Wang, J., Hou, C., Wang, L., Xu, X., and Zhu, H. (2017). How do aerosol properties affect the temporal variation of MODIS AOD bias in Eastern China?. Remote Sens., 9.","DOI":"10.3390\/rs9080800"},{"key":"ref_25","doi-asserted-by":"crossref","first-page":"14","DOI":"10.1016\/j.atmosenv.2019.04.020","article-title":"MODIS AOD sampling rate and its effect on PM2.5 estimation in North China","volume":"209","author":"Song","year":"2019","journal-title":"Atmos. Environ."},{"key":"ref_26","doi-asserted-by":"crossref","first-page":"159","DOI":"10.1016\/j.atmosenv.2019.06.004","article-title":"Performance of MODIS high-resolution MAIAC aerosol algorithm in China: Characterization and limitation","volume":"213","author":"Tao","year":"2019","journal-title":"Atmos. Environ."},{"key":"ref_27","doi-asserted-by":"crossref","first-page":"116119","DOI":"10.1016\/j.envpol.2020.116119","article-title":"Estimating hourly full-coverage PM2.5 over China based on TOA reflectance data from the Fengyun-4 A satellite","volume":"270","author":"Mao","year":"2021","journal-title":"Environ. Pollut."},{"key":"ref_28","doi-asserted-by":"crossref","first-page":"113","DOI":"10.1016\/j.atmosenv.2019.04.002","article-title":"Satellite-based PM2.5 estimation directly from reflectance at the top of the atmosphere using a machine learning algorithm","volume":"208","author":"Liu","year":"2019","journal-title":"Atmos. Environ."},{"key":"ref_29","doi-asserted-by":"crossref","first-page":"13","DOI":"10.1029\/2018JD028759","article-title":"Estimating regional ground-level PM2.5 Directly from satellite top-of-atmosphere reflectance using deep belief networks","volume":"123","author":"Shen","year":"2018","journal-title":"J. Geophys. Res. Atmos."},{"key":"ref_30","doi-asserted-by":"crossref","first-page":"200257","DOI":"10.4209\/aaqr.2020.05.0257","article-title":"Comparison of satellite-based PM2.5 Estimation from aerosol optical depth and top-of-atmosphere reflectance","volume":"21","author":"Bai","year":"2020","journal-title":"Aerosol Air Qual. Res."},{"key":"ref_31","doi-asserted-by":"crossref","first-page":"111888","DOI":"10.1016\/j.jenvman.2020.111888","article-title":"Particulate matter (PM2.5 and PM10) generation map using MODIS Level-1 satellite images and deep neural network","volume":"281","author":"Imani","year":"2021","journal-title":"J. Environ. Manag."},{"key":"ref_32","unstructured":"Hong, K.Y., Pinheiro, P.O., and Weichenthal, S. (2019). Predicting global variations in outdoor PM2.5 concentrations using satellite images and deep convolutional neural networks. arXiv."},{"key":"ref_33","doi-asserted-by":"crossref","first-page":"117451","DOI":"10.1016\/j.atmosenv.2020.117451","article-title":"Estimating ground-level PM 2.5 using micro-satellite images by a convolutional neural network and random forest approach","volume":"230","author":"Zheng","year":"2020","journal-title":"Atmos. Environ."},{"key":"ref_34","doi-asserted-by":"crossref","unstructured":"Li, G., Wu, H., Zhong, Q., He, J., Yang, W., Zhu, J., Zhao, H., Zhang, H., Zhu, Z., and Huang, F. (2021). Six air pollutants and cause-specific mortality: A multi-area study in nine counties or districts of Anhui Province, China. Environ. Sci. Pollut. Res., 1\u201315.","DOI":"10.1007\/s11356-021-15730-4"},{"key":"ref_35","doi-asserted-by":"crossref","first-page":"112766","DOI":"10.1016\/j.cma.2019.112766","article-title":"Data-driven reduced order model with temporal convolutional neural network","volume":"360","author":"Wu","year":"2020","journal-title":"Comput. Methods Appl. Mech. Eng."},{"key":"ref_36","doi-asserted-by":"crossref","unstructured":"Liu, B., Guo, J., Gong, W., Zhang, Y., Shi, L., Ma, Y., Li, J., Guo, X., Stoffelen, A., and de Leeuw, G. (2021). Intercomparison of wind observations from ESA\u2019s satellite mission Aeolus, ERA5 reanalysis and radiosonde over China. Atmos. Chem. Phys., 1\u201335.","DOI":"10.5194\/acp-2021-41"},{"key":"ref_37","doi-asserted-by":"crossref","first-page":"723","DOI":"10.1093\/mnras\/staa156","article-title":"Atmospheric parameters at the 6-m Big Telescope Alt-azimuthal site","volume":"493","author":"Shikhovtsev","year":"2020","journal-title":"Mon. Not. R. Astron. Soc."},{"key":"ref_38","doi-asserted-by":"crossref","first-page":"771","DOI":"10.3103\/S1068373920110035","article-title":"Verification of ERA-Interim and ERA5 Reanalyses Data on Surface Air Temperature in the Arctic","volume":"45","author":"Demchev","year":"2020","journal-title":"Russ. Meteorol. Hydrol."},{"key":"ref_39","doi-asserted-by":"crossref","unstructured":"Oses, N., Azpiroz, I., Marchi, S., Guidotti, D., Quartulli, M., and Olaizola, I.G. (2020). Analysis of Copernicus\u2019 ERA5 Climate Reanalysis Data as a Replacement for Weather Station Temperature Measurements in Machine Learning Models for Olive Phenology Phase Prediction. Sensors, 20.","DOI":"10.3390\/s20216381"},{"key":"ref_40","doi-asserted-by":"crossref","first-page":"561","DOI":"10.1029\/2018RS006789","article-title":"Consistency Evaluation of Precipitable Water Vapor Derived From ERA5, ERA-Interim, GNSS, and Radiosondes Over China","volume":"54","author":"Zhang","year":"2019","journal-title":"Radio Sci."},{"key":"ref_41","doi-asserted-by":"crossref","first-page":"1999","DOI":"10.1002\/qj.3803","article-title":"The ERA5 global reanalysis","volume":"146","author":"Hersbach","year":"2020","journal-title":"Q. J. R. Meteorol. Soc."},{"key":"ref_42","doi-asserted-by":"crossref","first-page":"2225","DOI":"10.1016\/j.patrec.2010.03.014","article-title":"VSURF: Variable Selection Using Random Forests","volume":"31","author":"Genuer","year":"2016","journal-title":"Pattern Recognit. Lett."},{"key":"ref_43","doi-asserted-by":"crossref","unstructured":"Strobl, C., Boulesteix, A.L., Zeileis, A., and Hothorn, T. (2007). Bias in random forest variable importance measures: Illustrations, sources and a solution. BMC Bioinform., 8.","DOI":"10.1186\/1471-2105-8-25"},{"key":"ref_44","doi-asserted-by":"crossref","first-page":"147712","DOI":"10.1016\/j.scitotenv.2021.147712","article-title":"Quantifying the role of PM2.5 dropping in variations of ground-level ozone: Inter-comparison between Beijing and Los Angeles","volume":"788","author":"Shao","year":"2021","journal-title":"Sci. Total Environ."}],"container-title":["Remote Sensing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2072-4292\/13\/22\/4545\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,11]],"date-time":"2025-10-11T07:29:07Z","timestamp":1760167747000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2072-4292\/13\/22\/4545"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,11,12]]},"references-count":44,"journal-issue":{"issue":"22","published-online":{"date-parts":[[2021,11]]}},"alternative-id":["rs13224545"],"URL":"https:\/\/doi.org\/10.3390\/rs13224545","relation":{},"ISSN":["2072-4292"],"issn-type":[{"value":"2072-4292","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021,11,12]]}}}