{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,21]],"date-time":"2026-02-21T19:27:02Z","timestamp":1771702022673,"version":"3.50.1"},"reference-count":56,"publisher":"MDPI AG","issue":"6","license":[{"start":{"date-parts":[[2022,3,21]],"date-time":"2022-03-21T00:00:00Z","timestamp":1647820800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"Hong Kong Research Grants Council","award":["CRF C4139-20G"],"award-info":[{"award-number":["CRF C4139-20G"]}]},{"name":"Hong Kong Research Grants Council","award":["AoE\/E-603\/18"],"award-info":[{"award-number":["AoE\/E-603\/18"]}]},{"name":"Strategic Priority Research Program of the Chinese Academy of Sciences","award":["XDA19090108"],"award-info":[{"award-number":["XDA19090108"]}]},{"name":"National Key R\\&amp;D Program of China","award":["2019YFC1510400"],"award-info":[{"award-number":["2019YFC1510400"]}]},{"name":"National Key R\\&amp;D Program of China","award":["2017YFB0503605"],"award-info":[{"award-number":["2017YFB0503605"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Remote Sensing"],"abstract":"<jats:p>Aerosol optical depth (AOD) data derived from satellite products have been widely used to estimate fine particulate matter (PM2.5) concentrations. However, existing approaches to estimate PM2.5 concentrations are invariably limited by the availability of AOD data, which can be missing over large areas due to satellite measurements being obstructed by, for example, clouds, snow cover or high concentrations of air pollution. In this study, we addressed this shortcoming by developing a novel method for determining PM2.5 concentrations with high spatial coverage by integrating AOD-based estimations and smartphone photograph-based estimations. We first developed a multiple-input fuzzy neural network (MIFNN) model to measure PM2.5 concentrations from smartphone photographs. We then designed an ensemble learning model (AutoELM) to determine PM2.5 concentrations based on the Collection-6 Multi-Angle Implementation of Atmospheric Correction AOD product. The R2 values of the MIFNN model and AutoELM model are 0.85 and 0.80, respectively, which are superior to those of other state-of-the-art models. Subsequently, we used crowdsourced smartphone photographs obtained from social media to validate the transferability of the MIFNN model, which we then applied to generate smartphone photograph-based estimates of PM2.5 concentrations. These estimates were fused with AOD-based estimates to generate a new PM2.5 distribution product with broader coverage than existing products, equating to an average increase of 12% in map coverage of PM2.5 concentrations, which grows to an impressive 25% increase in map coverage in densely populated areas. Our findings indicate that the robust estimation accuracy of the ensemble learning model is due to its detection of nonlinear correlations and high-order interactions. Furthermore, our findings demonstrate that the synergy of smartphone photograph-based estimations and AOD-based estimations generates significantly greater spatial coverage of PM2.5 distribution than AOD-based estimations alone, especially in densely populated areas where more smartphone photographs are available.<\/jats:p>","DOI":"10.3390\/rs14061515","type":"journal-article","created":{"date-parts":[[2022,3,21]],"date-time":"2022-03-21T21:48:42Z","timestamp":1647899322000},"page":"1515","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":13,"title":["Estimating High-Resolution PM2.5 Concentrations by Fusing Satellite AOD and Smartphone Photographs Using a Convolutional Neural Network and Ensemble Learning"],"prefix":"10.3390","volume":"14","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-4155-2330","authenticated-orcid":false,"given":"Fei","family":"Wang","sequence":"first","affiliation":[{"name":"Department of Geography and Resources Management, The Chinese University of Hong Kong, Hong Kong 999077, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0844-2973","authenticated-orcid":false,"given":"Shiqi","family":"Yao","sequence":"additional","affiliation":[{"name":"Department of Geography and Resources Management, The Chinese University of Hong Kong, Hong Kong 999077, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4760-5958","authenticated-orcid":false,"given":"Haowen","family":"Luo","sequence":"additional","affiliation":[{"name":"Department of Geography and Resources Management, The Chinese University of Hong Kong, Hong Kong 999077, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5063-3522","authenticated-orcid":false,"given":"Bo","family":"Huang","sequence":"additional","affiliation":[{"name":"Department of Geography and Resources Management, The Chinese University of Hong Kong, Hong Kong 999077, China"},{"name":"Institude of Space and Earth Information Science, The Chinese University of Hong Kong, Hong Kong 999077, China"},{"name":"Shenzhen Research Institute, The Chinese University of Hong Kong, Shenzhen 518057, China"}]}],"member":"1968","published-online":{"date-parts":[[2022,3,21]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"119018","DOI":"10.1016\/j.jclepro.2019.119018","article-title":"How does urban expansion impact people\u2019s exposure to green environments? A comparative study of 290 Chinese cities","volume":"246","author":"Song","year":"2020","journal-title":"J. Clean. Prod."},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"106778","DOI":"10.1016\/j.envint.2021.106778","article-title":"Observed inequality in urban greenspace exposure in China","volume":"156","author":"Song","year":"2021","journal-title":"Environ. Int."},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"680","DOI":"10.1097\/EDE.0b013e3181812bb7","article-title":"The role of particle composition on the association between PM2.5 and mortality","volume":"19","author":"Franklin","year":"2008","journal-title":"Epidemiology"},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"288","DOI":"10.1016\/j.envpol.2019.06.057","article-title":"Dynamic assessment of PM2.5 exposure and health risk using remote sensing and geo-spatial big data","volume":"253","author":"Song","year":"2019","journal-title":"Environ. Pollut."},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"43322","DOI":"10.18632\/oncotarget.17313","article-title":"Relationship between exposure to PM2.5 and lung cancer incidence and mortality: A meta-analysis","volume":"8","author":"Huang","year":"2017","journal-title":"Oncotarget"},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1016\/j.envpol.2013.05.057","article-title":"A five-year study of particulate matter (PM2.5) and cerebrovascular diseases","volume":"181","author":"Ibarra","year":"2013","journal-title":"Environ. Pollut."},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"8187","DOI":"10.3390\/ijerph120708187","article-title":"PM2.5 and cardiovascular diseases in the elderly: An overview","volume":"12","author":"Wang","year":"2015","journal-title":"Int. J. Environ. Res. Public Health"},{"key":"ref_8","first-page":"E69","article-title":"The impact of PM2.5 on the human respiratory system","volume":"8","author":"Xing","year":"2016","journal-title":"J. Thorac. Dis."},{"key":"ref_9","first-page":"907","article-title":"Optimization of site locations of regional air quality monitoring network: Methodology study","volume":"30","author":"Liu","year":"2010","journal-title":"China Environ. Sci."},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"1156","DOI":"10.1016\/j.scitotenv.2014.11.024","article-title":"Estimating PM2.5 in Xi\u2019an, China using aerosol optical depth: A comparison between the MODIS and MISR retrieval models","volume":"505","author":"You","year":"2015","journal-title":"Sci. Total Environ."},{"key":"ref_11","doi-asserted-by":"crossref","first-page":"156","DOI":"10.1016\/j.atmosenv.2016.03.040","article-title":"Satellite-derived high resolution PM2.5 concentrations in Yangtze River Delta Region of China using improved linear mixed effects model","volume":"133","author":"Ma","year":"2016","journal-title":"Atmos. Environ."},{"key":"ref_12","doi-asserted-by":"crossref","first-page":"117","DOI":"10.1016\/j.rse.2014.09.015","article-title":"Using satellite remote sensing data to estimate the high-resolution distribution of ground-level PM2.5","volume":"156","author":"Lin","year":"2015","journal-title":"Remote Sens. Environ."},{"key":"ref_13","doi-asserted-by":"crossref","first-page":"94","DOI":"10.1016\/j.envpol.2016.11.043","article-title":"Impact of diurnal variability and meteorological factors on the PM2.5-AOD relationship: Implications for PM2.5 remote sensing","volume":"221","author":"Guo","year":"2017","journal-title":"Environ. Pollut."},{"key":"ref_14","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_15","doi-asserted-by":"crossref","first-page":"111221","DOI":"10.1016\/j.rse.2019.111221","article-title":"Estimating 1-km-resolution PM2.5 concentrations across China using the space-time random forest approach","volume":"231","author":"Wei","year":"2019","journal-title":"Remote Sens. Environ."},{"key":"ref_16","doi-asserted-by":"crossref","first-page":"262","DOI":"10.1016\/j.rse.2015.05.016","article-title":"Estimating long-term PM2.5 concentrations in China using satellite-based aerosol optical depth and a chemical transport model","volume":"166","author":"Geng","year":"2015","journal-title":"Remote Sens. Environ."},{"key":"ref_17","doi-asserted-by":"crossref","first-page":"316","DOI":"10.1016\/j.rse.2016.07.015","article-title":"VIIRS-based remote sensing estimation of ground-level PM2.5 concentrations in Beijing\u2013Tianjin\u2013Hebei: A spatiotemporal statistical model","volume":"184","author":"Wu","year":"2016","journal-title":"Remote Sens. Environ."},{"key":"ref_18","doi-asserted-by":"crossref","first-page":"288","DOI":"10.1016\/j.atmosenv.2018.02.011","article-title":"Assimilating AOD retrievals from GOCI and VIIRS to forecast surface PM2.5 episodes over Eastern China","volume":"179","author":"Pang","year":"2018","journal-title":"Atmos. Environ."},{"key":"ref_19","doi-asserted-by":"crossref","first-page":"573","DOI":"10.1016\/j.rse.2018.09.001","article-title":"Estimation of PM2.5 concentrations at a high spatiotemporal resolution using constrained mixed-effect bagging models with MAIAC aerosol optical depth","volume":"217","author":"Li","year":"2018","journal-title":"Remote Sens. Environ."},{"key":"ref_20","doi-asserted-by":"crossref","first-page":"105536","DOI":"10.1016\/j.envint.2020.105536","article-title":"Spatiotemporal trends of PM2.5 concentrations in central China from 2003 to 2018 based on MAIAC-derived high-resolution data","volume":"137","author":"He","year":"2020","journal-title":"Environ. Int."},{"key":"ref_21","doi-asserted-by":"crossref","first-page":"11195","DOI":"10.1021\/es301948k","article-title":"Development of land use regression models for PM2.5, PM2.5 absorbance, PM10 and PMcoarse in 20 European study areas; results of the ESCAPE project","volume":"46","author":"Eeftens","year":"2012","journal-title":"Environ. Sci. Technol."},{"key":"ref_22","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1016\/j.envres.2012.11.003","article-title":"Estimating ground-level PM2.5 concentrations in the southeastern US using geographically weighted regression","volume":"121","author":"Hu","year":"2013","journal-title":"Environ. Res."},{"key":"ref_23","doi-asserted-by":"crossref","first-page":"113395","DOI":"10.1016\/j.envpol.2019.113395","article-title":"Estimating PM2.5 concentration of the conterminous United States via interpretable convolutional neural networks","volume":"256","author":"Park","year":"2020","journal-title":"Environ. Pollut."},{"key":"ref_24","doi-asserted-by":"crossref","first-page":"117242","DOI":"10.1016\/j.atmosenv.2019.117242","article-title":"Estimating hourly and continuous ground-level PM2.5 concentrations using an ensemble learning algorithm: The ST-stacking model","volume":"223","author":"Feng","year":"2020","journal-title":"Atmos. Environ."},{"key":"ref_25","doi-asserted-by":"crossref","unstructured":"Liu, C., Tsow, F., Zou, Y., and Tao, N. (2016). Particle pollution estimation based on image analysis. PLoS ONE, 11.","DOI":"10.1371\/journal.pone.0145955"},{"key":"ref_26","doi-asserted-by":"crossref","unstructured":"Liu, X., Song, Z., Ngai, E., Ma, J., and Wang, W. (May, January 26). PM2.5 monitoring using images from smartphones in participatory sensing. Proceedings of the 2015 IEEE Conference on Computer Communications Workshops (INFOCOM WKSHPS), Hong Kong, China.","DOI":"10.1109\/INFCOMW.2015.7179456"},{"key":"ref_27","first-page":"100063","article-title":"Estimating PM2.5 from photographs","volume":"5","author":"Pudasaini","year":"2020","journal-title":"Atmos. Environ. X"},{"key":"ref_28","doi-asserted-by":"crossref","first-page":"4278","DOI":"10.1109\/TNNLS.2021.3105394","article-title":"PM2.5 Monitoring: Use Information Abundance Measurement and Wide and Deep Learning","volume":"32","author":"Gu","year":"2021","journal-title":"IEEE Trans. Neural Netw. Learn. Syst."},{"key":"ref_29","unstructured":"Liu, Y., Racah, E., Correa, J., Khosrowshahi, A., Lavers, D., Kunkel, K., Wehner, M., and Collins, W. (2016). Application of deep convolutional neural networks for detecting extreme weather in climate datasets. arXiv."},{"key":"ref_30","unstructured":"Qian, R., Zhang, B., Yue, Y., Wang, Z., and Coenen, F. (2015, January 15\u201317). Robust Chinese traffic sign detection and recognition with deep convolutional neural network. Proceedings of the 2015 11th International Conference on Natural Computation (ICNC), Zhangjiajie, China."},{"key":"ref_31","doi-asserted-by":"crossref","first-page":"9673724","DOI":"10.1155\/2020\/9673724","article-title":"Identification and classification of atmospheric particles based on SEM images using convolutional neural network with attention mechanism","volume":"2020","author":"Yin","year":"2020","journal-title":"Complexity"},{"key":"ref_32","doi-asserted-by":"crossref","unstructured":"Zhang, C., Yan, J., Li, C., Rui, X., Liu, L., and Bie, R. (2016, January 15\u201319). On estimating air pollution from photos using convolutional neural network. Proceedings of the 24th ACM International Conference on Multimedia, Amsterdam, The Netherlands.","DOI":"10.1145\/2964284.2967230"},{"key":"ref_33","doi-asserted-by":"crossref","unstructured":"Bo, Q., Yang, W., Rijal, N., Xie, Y., Feng, J., and Zhang, J. (2018, January 7\u201310). Particle pollution estimation from images using convolutional neural network and weather features. Proceedings of the 2018 25th IEEE International Conference on Image Processing (ICIP), Athens, Greece.","DOI":"10.1109\/ICIP.2018.8451306"},{"key":"ref_34","doi-asserted-by":"crossref","first-page":"3918","DOI":"10.1109\/TII.2019.2943631","article-title":"Discern Depth Under Foul Weather: Estimate PM2.5 for Depth Inference","volume":"16","author":"Li","year":"2019","journal-title":"IEEE Trans. Ind. Inform."},{"key":"ref_35","doi-asserted-by":"crossref","unstructured":"Rijal, N., Gutta, R.T., Cao, T., Lin, J., Bo, Q., and Zhang, J. (2018, January 27\u201329). Ensemble of deep neural networks for estimating particulate matter from images. Proceedings of the 2018 IEEE 3rd International Conference on Image, Vision and Computing (ICIVC), Chongqing, China.","DOI":"10.1109\/ICIVC.2018.8492790"},{"key":"ref_36","doi-asserted-by":"crossref","first-page":"85","DOI":"10.1016\/j.jes.2020.04.042","article-title":"PM2.5 concentration estimation using convolutional neural network and gradient boosting machine","volume":"98","author":"Luo","year":"2020","journal-title":"J. Environ. Sci."},{"key":"ref_37","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_38","unstructured":"Dorogush, A.V., Ershov, V., and Gulin, A. (2018). CatBoost: Gradient boosting with categorical features support. arXiv."},{"key":"ref_39","doi-asserted-by":"crossref","unstructured":"Chen, T., and Guestrin, C. (2016, January 13\u201317). Xgboost: A scalable tree boosting system. Proceedings of the 22nd ACM Sigkdd International Conference on Knowledge Discovery and Data Mining, San Francisco, CA, USA.","DOI":"10.1145\/2939672.2939785"},{"key":"ref_40","doi-asserted-by":"crossref","unstructured":"Machado, M.R., Karray, S., and de Sousa, I.T. (2019, January 19\u201321). LightGBM: An effective decision tree gradient boosting method to predict customer loyalty in the finance industry. Proceedings of the 2019 14th International Conference on Computer Science & Education (ICCSE), Toronto, ON, Canada.","DOI":"10.1109\/ICCSE.2019.8845529"},{"key":"ref_41","unstructured":"CSIS (2022, February 14). Is Air Quality in China a Social Problem?. Available online: https:\/\/chinapower.csis.org\/air-quality\/."},{"key":"ref_42","doi-asserted-by":"crossref","first-page":"5741","DOI":"10.5194\/amt-11-5741-2018","article-title":"MODIS collection 6 MAIAC algorithm","volume":"11","author":"Lyapustin","year":"2018","journal-title":"Atmos. Meas. Tech."},{"key":"ref_43","doi-asserted-by":"crossref","first-page":"3176","DOI":"10.1109\/TIE.2018.2840515","article-title":"Highly efficient picture-based prediction of PM2.5 concentration","volume":"66","author":"Gu","year":"2019","journal-title":"IEEE Trans. Ind. Electron."},{"key":"ref_44","doi-asserted-by":"crossref","first-page":"76","DOI":"10.1063\/1.3037551","article-title":"Optics of the Atmosphere: Scattering by Molecules and Particles","volume":"30","author":"McCartney","year":"1977","journal-title":"Phys. Today"},{"key":"ref_45","doi-asserted-by":"crossref","first-page":"233","DOI":"10.1023\/A:1016328200723","article-title":"Vision and the atmosphere","volume":"48","author":"Narasimhan","year":"2002","journal-title":"Int. J. Comput. Vis."},{"key":"ref_46","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/1360612.1360671","article-title":"Single image dehazing","volume":"27","author":"Fattal","year":"2008","journal-title":"ACM Trans. Graph. (TOG)"},{"key":"ref_47","first-page":"33","article-title":"Theorie der horizontalen Sichtweite","volume":"12","author":"Koschmieder","year":"1924","journal-title":"Beitr. Phys. Freien Atmos."},{"key":"ref_48","doi-asserted-by":"crossref","first-page":"333","DOI":"10.1021\/ed039p333","article-title":"The beer-lambert law","volume":"39","author":"Swinehart","year":"1962","journal-title":"J. Chem. Educ."},{"key":"ref_49","doi-asserted-by":"crossref","first-page":"1176","DOI":"10.1080\/00022470.1985.10466020","article-title":"Relationships between aerosol extinction coefficients derived from airport visual range observations and alternative measures of airborne particle mass","volume":"35","author":"Ozkaynak","year":"1985","journal-title":"J. Air Pollut. Control. Assoc."},{"key":"ref_50","first-page":"2341","article-title":"Single image haze removal using dark channel prior","volume":"33","author":"He","year":"2010","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"ref_51","doi-asserted-by":"crossref","first-page":"122","DOI":"10.1080\/00022470.1980.10465927","article-title":"Human perception of visual air quality","volume":"30","author":"Malm","year":"1980","journal-title":"J. Air Pollut. Control Assoc."},{"key":"ref_52","doi-asserted-by":"crossref","unstructured":"Szegedy, C., Vanhoucke, V., Ioffe, S., Shlens, J., and Wojna, Z. (2016, January 27\u201330). Rethinking the inception architecture for computer vision. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Las Vegas, NV, USA.","DOI":"10.1109\/CVPR.2016.308"},{"key":"ref_53","doi-asserted-by":"crossref","unstructured":"Zhou, S., Li, W., and Qiao, J. (2017, January 26\u201328). Prediction of PM2.5 concentration based on recurrent fuzzy neural network. Proceedings of the 2017 36th Chinese Control Conference (CCC), Dalian, China.","DOI":"10.23919\/ChiCC.2017.8027970"},{"key":"ref_54","doi-asserted-by":"crossref","unstructured":"He, Z., Ye, X., Gu, K., and Qiao, J. (2018, January 25\u201327). Learn to predict PM2.5 concentration with image contrast-sensitive features. Proceedings of the 2018 37th Chinese Control Conference (CCC), Wuhan, China.","DOI":"10.23919\/ChiCC.2018.8482979"},{"key":"ref_55","unstructured":"Erickson, N., Mueller, J., Shirkov, A., Zhang, H., Larroy, P., Li, M., and Smola, A. (2020). Autogluon-tabular: Robust and accurate automl for structured data. arXiv."},{"key":"ref_56","doi-asserted-by":"crossref","first-page":"140","DOI":"10.1016\/j.rse.2017.06.001","article-title":"Estimating ground-level PM2.5 concentrations in Beijing using a satellite-based geographically and temporally weighted regression model","volume":"198","author":"Guo","year":"2017","journal-title":"Remote Sens. Environ."}],"container-title":["Remote Sensing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2072-4292\/14\/6\/1515\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,10]],"date-time":"2025-10-10T22:40:19Z","timestamp":1760136019000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2072-4292\/14\/6\/1515"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,3,21]]},"references-count":56,"journal-issue":{"issue":"6","published-online":{"date-parts":[[2022,3]]}},"alternative-id":["rs14061515"],"URL":"https:\/\/doi.org\/10.3390\/rs14061515","relation":{},"ISSN":["2072-4292"],"issn-type":[{"value":"2072-4292","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022,3,21]]}}}