{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,14]],"date-time":"2026-03-14T10:16:15Z","timestamp":1773483375106,"version":"3.50.1"},"reference-count":44,"publisher":"MDPI AG","issue":"14","license":[{"start":{"date-parts":[[2022,7,17]],"date-time":"2022-07-17T00:00:00Z","timestamp":1658016000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"UK Medical Research","award":["grant MR\/S003983\/1"],"award-info":[{"award-number":["grant MR\/S003983\/1"]}]},{"name":"UK Medical Research","award":["209376\/Z\/17\/Z"],"award-info":[{"award-number":["209376\/Z\/17\/Z"]}]},{"DOI":"10.13039\/100004440","name":"Pathways to Equitable Healthy Cities grant from the Wellcome Trust","doi-asserted-by":"publisher","award":["grant MR\/S003983\/1"],"award-info":[{"award-number":["grant MR\/S003983\/1"]}],"id":[{"id":"10.13039\/100004440","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100004440","name":"Pathways to Equitable Healthy Cities grant from the Wellcome Trust","doi-asserted-by":"publisher","award":["209376\/Z\/17\/Z"],"award-info":[{"award-number":["209376\/Z\/17\/Z"]}],"id":[{"id":"10.13039\/100004440","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Remote Sensing"],"abstract":"<jats:p>High spatial resolution information on urban air pollution levels is unavailable in many areas globally, partially due to the high input data needs of existing estimation approaches. We introduced a computer vision method to estimate annual means for air pollution levels from street-level images. We used annual mean estimates of NO2 and PM2.5 concentrations from locally calibrated models as labels from London, New York, and Vancouver to allow for compilation of a sufficiently large dataset (~250 k images for each city). Our experimental setup is designed to quantify intra- and intercity transferability of image-based model estimates. Performances were high and comparable to traditional land-use regression (LUR) and dispersion models when training and testing images from the same city (R2 values between 0.51 and 0.95 when validated on data from ground monitoring stations). Similar to LUR models, transferability of models between cities in different geographies is more difficult. Specifically, transferability between the three cities (London, New York, and Vancouver), which have similar pollution source profiles, was moderately successful (R2 values between zero and 0.67). Comparatively, performances when transferring models trained on cities with very different source profiles, such as Accra in Ghana and Hong Kong, were lower (R2 between zero and 0.21). This suggests a need for local calibration, using additional measurement data from cities that share similar source profiles.<\/jats:p>","DOI":"10.3390\/rs14143429","type":"journal-article","created":{"date-parts":[[2022,7,18]],"date-time":"2022-07-18T01:53:22Z","timestamp":1658109202000},"page":"3429","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":15,"title":["What You See Is What You Breathe? Estimating Air Pollution Spatial Variation Using Street-Level Imagery"],"prefix":"10.3390","volume":"14","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-9246-3966","authenticated-orcid":false,"given":"Esra","family":"Suel","sequence":"first","affiliation":[{"name":"Global Environmental Health Research Group, School of Public Health, Imperial College, London SW7 2BX, UK"},{"name":"Chair of Geoinformation Engineering, ETH Zurich, 8092 Zurich, Switzerland"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2208-2062","authenticated-orcid":false,"given":"Meytar","family":"Sorek-Hamer","sequence":"additional","affiliation":[{"name":"Universities Space Research Association (USRA), Mountain View, CA 94035, USA"},{"name":"NASA Ames Research Center, Silicon Valley, CA 94035, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Izabela","family":"Moise","sequence":"additional","affiliation":[{"name":"Swiss Data Science Center, ETH Zurich, 8092 Zurich, Switzerland"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7434-993X","authenticated-orcid":false,"given":"Michael","family":"von Pohle","sequence":"additional","affiliation":[{"name":"Universities Space Research Association (USRA), Mountain View, CA 94035, USA"},{"name":"NASA Ames Research Center, Silicon Valley, CA 94035, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Adwait","family":"Sahasrabhojanee","sequence":"additional","affiliation":[{"name":"Universities Space Research Association (USRA), Mountain View, CA 94035, USA"},{"name":"NASA Ames Research Center, Silicon Valley, CA 94035, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ata Akbari","family":"Asanjan","sequence":"additional","affiliation":[{"name":"Universities Space Research Association (USRA), Mountain View, CA 94035, USA"},{"name":"NASA Ames Research Center, Silicon Valley, CA 94035, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Raphael E.","family":"Arku","sequence":"additional","affiliation":[{"name":"Department of Environmental Health Sciences, School of Public Health and Health Sciences, University of Massachusetts Amherst, Amherst, MA 01003, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Abosede S.","family":"Alli","sequence":"additional","affiliation":[{"name":"Department of Environmental Health Sciences, School of Public Health and Health Sciences, University of Massachusetts Amherst, Amherst, MA 01003, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5983-0426","authenticated-orcid":false,"given":"Benjamin","family":"Barratt","sequence":"additional","affiliation":[{"name":"Global Environmental Health Research Group, School of Public Health, Imperial College, London SW7 2BX, UK"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Sierra N.","family":"Clark","sequence":"additional","affiliation":[{"name":"Global Environmental Health Research Group, School of Public Health, Imperial College, London SW7 2BX, UK"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1565-095X","authenticated-orcid":false,"given":"Ariane","family":"Middel","sequence":"additional","affiliation":[{"name":"Schools of Arts, Media and Engineering, Arizona State University, Tempe, AZ 85281, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3803-2246","authenticated-orcid":false,"given":"Emily","family":"Deardorff","sequence":"additional","affiliation":[{"name":"Universities Space Research Association (USRA), Mountain View, CA 94035, USA"},{"name":"NASA Ames Research Center, Silicon Valley, CA 94035, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Violet","family":"Lingenfelter","sequence":"additional","affiliation":[{"name":"Universities Space Research Association (USRA), Mountain View, CA 94035, USA"},{"name":"NASA Ames Research Center, Silicon Valley, CA 94035, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5987-1033","authenticated-orcid":false,"given":"Nikunj C.","family":"Oza","sequence":"additional","affiliation":[{"name":"NASA Ames Research Center, Silicon Valley, CA 94035, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Nishant","family":"Yadav","sequence":"additional","affiliation":[{"name":"Universities Space Research Association (USRA), Mountain View, CA 94035, USA"},{"name":"NASA Ames Research Center, Silicon Valley, CA 94035, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Majid","family":"Ezzati","sequence":"additional","affiliation":[{"name":"Global Environmental Health Research Group, School of Public Health, Imperial College, London SW7 2BX, UK"},{"name":"Regional Institute for Population Studies, University of Ghana, Accra P.O. Box LG 96, Ghana"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9103-9343","authenticated-orcid":false,"given":"Michael","family":"Brauer","sequence":"additional","affiliation":[{"name":"School of Population and Public Health (SPPH), University of British Columbia, Vancouver, BC V6T 1Z3, Canada"},{"name":"Institute for Health Metrics and Evaluation, University of Washington, Washington, DC 98195, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"1968","published-online":{"date-parts":[[2022,7,17]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"462","DOI":"10.1016\/S0140-6736(17)32345-0","article-title":"The Lancet Commission on pollution and health","volume":"391","author":"Landrigan","year":"2018","journal-title":"Lancet"},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"1907","DOI":"10.1016\/S0140-6736(17)30505-6","article-title":"Estimates and 25-year trends of the global burden of disease attributable to ambient air pollution: An analysis of data from the Global Burden of Diseases Study 2015","volume":"389","author":"Cohen","year":"2017","journal-title":"Lancet"},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"43","DOI":"10.1186\/1476-069X-12-43","article-title":"Long-term air pollution exposure and cardio-respiratory mortality: A review","volume":"12","author":"Hoek","year":"2013","journal-title":"Environ. Health"},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"409","DOI":"10.1016\/j.chest.2018.10.042","article-title":"Air Pollution and Noncommunicable Diseases: A Review by the Forum of International Respiratory Societies\u2019 Environmental Committee, Part 1: The Damaging Effects of Air Pollution","volume":"155","author":"Schraufnagel","year":"2019","journal-title":"Chest"},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"652","DOI":"10.1021\/es2025752","article-title":"Exposure assessment for estimation of the global burden of disease attributable to outdoor air pollution","volume":"46","author":"Brauer","year":"2012","journal-title":"Environ. Sci. Technol."},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"127","DOI":"10.1080\/08958370701495998","article-title":"A review of land-use regression models for characterizing intraurban air pollution exposure","volume":"19","author":"Ryan","year":"2007","journal-title":"Inhal. Toxicol."},{"key":"ref_7","first-page":"100040","article-title":"No one knows which city has the highest concentration of fine particulate matter","volume":"3","author":"Martin","year":"2019","journal-title":"Atmos. Environ."},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"3","DOI":"10.1016\/j.envint.2018.11.042","article-title":"A picture tells a thousand\u2026 exposures: Opportunities and challenges of deep learning image analyses in exposure science and environmental epidemiology","volume":"122","author":"Weichenthal","year":"2019","journal-title":"Environ. Int."},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"6999","DOI":"10.1021\/acs.est.7b00891","article-title":"High-Resolution Air Pollution Mapping with Google Street View Cars: Exploiting Big Data","volume":"51","author":"Apte","year":"2017","journal-title":"Environ. Sci. Technol."},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"12563","DOI":"10.1021\/acs.est.8b03395","article-title":"Mapping air pollution with google street view cars: Efficient Approaches with mobile monitoring and land use regression","volume":"52","author":"Messier","year":"2018","journal-title":"Environ. Sci. Technol."},{"key":"ref_11","doi-asserted-by":"crossref","first-page":"432","DOI":"10.1097\/01.EE9.0000610860.14938.ad","article-title":"A New Method of Estimating Global PM2. 5 Concentrations using Satellite Images","volume":"3","author":"Hong","year":"2019","journal-title":"Environ. Epidemiol."},{"key":"ref_12","doi-asserted-by":"crossref","first-page":"10688","DOI":"10.1021\/acs.est.0c00412","article-title":"Predicting Traffic-Related Air Pollution Using Feature Extraction from Built Environment Images","volume":"54","author":"Ganji","year":"2020","journal-title":"Environ. Sci. Technol."},{"key":"ref_13","doi-asserted-by":"crossref","first-page":"106044","DOI":"10.1016\/j.envint.2020.106044","article-title":"Predicting outdoor ultrafine particle number concentrations, particle size, and noise using street-level images and audio data","volume":"144","author":"Hong","year":"2020","journal-title":"Environ. Int."},{"key":"ref_14","doi-asserted-by":"crossref","first-page":"228","DOI":"10.1097\/MOP.0000000000000326","article-title":"The Use of Satellite Remote Sensing in Epidemiological Studies","volume":"28","author":"Just","year":"2016","journal-title":"Curr. Opin. Pediatr."},{"key":"ref_15","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1038\/s41598-019-42036-w","article-title":"Measuring social, environmental and health inequalities using deep learning and street imagery","volume":"9","author":"Suel","year":"2019","journal-title":"Sci. Rep."},{"key":"ref_16","doi-asserted-by":"crossref","first-page":"2695","DOI":"10.1021\/acs.est.0c05572","article-title":"Using Street View Imagery to Predict Street-Level Particulate Air Pollution","volume":"55","author":"Qi","year":"2021","journal-title":"Environ. Sci. Technol."},{"key":"ref_17","doi-asserted-by":"crossref","first-page":"7561","DOI":"10.1016\/j.atmosenv.2008.05.057","article-title":"A review of land-use regression models to assess spatial variation of outdoor air pollution","volume":"42","author":"Hoek","year":"2008","journal-title":"Atmos. Environ."},{"key":"ref_18","doi-asserted-by":"crossref","first-page":"35798","DOI":"10.1136\/bmjopen-2019-035798","article-title":"High-resolution spatiotemporal measurement of air and environmental noise pollution in Sub-Saharan African cities: Pathways to Equitable Health Cities Study protocol for Accra, Ghana","volume":"10","author":"Clark","year":"2020","journal-title":"BMJ Open"},{"key":"ref_19","doi-asserted-by":"crossref","first-page":"436","DOI":"10.1038\/nature14539","article-title":"Deep learning","volume":"521","author":"LeCun","year":"2015","journal-title":"Nature"},{"key":"ref_20","doi-asserted-by":"crossref","first-page":"112339","DOI":"10.1016\/j.rse.2021.112339","article-title":"Multimodal deep learning from satellite and street-level imagery for measuring income, overcrowding, and environmental deprivation in urban areas","volume":"257","author":"Suel","year":"2021","journal-title":"Remote Sens. Environ."},{"key":"ref_21","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1016\/j.envres.2016.07.005","article-title":"Development of West-European PM2. 5 and NO2 land use regression models incorporating satellite-derived and chemical transport modelling data","volume":"151","author":"Gulliver","year":"2016","journal-title":"Environ. Res."},{"key":"ref_22","doi-asserted-by":"crossref","first-page":"10","DOI":"10.1016\/j.atmosenv.2013.02.037","article-title":"Development of NO2 and NOx land use regression models for estimating air pollution exposure in 36 study areas in Europe\u2014The ESCAPE project","volume":"72","author":"Beelen","year":"2013","journal-title":"Atmos. Environ."},{"key":"ref_23","unstructured":"City of New York (2022, July 14). The New York City Community Air Survey: Neighborhood Air Quality 2008\u20132014, Available online: https:\/\/www1.nyc.gov\/site\/doh\/data\/data-sets\/air-quality-nyc-community-air-survey.page."},{"key":"ref_24","doi-asserted-by":"crossref","first-page":"2422","DOI":"10.1021\/es0606780","article-title":"Application of land use regression to estimate long-term concentrations of traffic-related nitrogen oxides and fine particulate matter","volume":"41","author":"Henderson","year":"2007","journal-title":"Environ. Sci. Technol."},{"key":"ref_25","doi-asserted-by":"crossref","first-page":"12297","DOI":"10.1021\/acs.est.5b02882","article-title":"National spatiotemporal exposure surface for NO2: Monthly scaling of a satellite-derived land-use regression, 2000\u20142010","volume":"49","author":"Bechle","year":"2015","journal-title":"Environ. Sci. Technol."},{"key":"ref_26","doi-asserted-by":"crossref","first-page":"5299","DOI":"10.1136\/bmj.j5299","article-title":"Impact of London\u2019s road traffic air and noise pollution on birth weight: Retrospective population based cohort study","volume":"359","author":"Smith","year":"2017","journal-title":"BMJ"},{"key":"ref_27","unstructured":"Clean Air for London (2022, July 14). London Atmospheric Emissions Inventory (LAEI) 2010, Available online: https:\/\/data.london.gov.uk\/dataset\/london-atmospheric-emissions-inventory-2010."},{"key":"ref_28","doi-asserted-by":"crossref","first-page":"312","DOI":"10.1016\/j.atmosenv.2012.09.056","article-title":"Temporal stability of land use regression models for traffic-related air pollution","volume":"64","author":"Wang","year":"2013","journal-title":"Atmos. Environ."},{"key":"ref_29","unstructured":"U.S. EPA (2022, July 14). US EPA Air Quality Download Data, Available online: https:\/\/aqs.epa.gov\/aqsweb\/airdata\/download_files.html."},{"key":"ref_30","unstructured":"Government of Canada (2022, July 14). Environment and Climate Change Canada Data, Available online: http:\/\/data.ec.gc.ca\/data\/?lang=en."},{"key":"ref_31","unstructured":"Imperial College (2022, July 14). London Air Quality Network. Available online: https:\/\/www.londonair.org.uk\/london\/asp\/reportdetail.asp?ReportID=lars2010."},{"key":"ref_32","first-page":"100030","article-title":"A trend analysis approach for air quality network data","volume":"2","author":"Lang","year":"2019","journal-title":"Atmos. Environ."},{"key":"ref_33","doi-asserted-by":"crossref","first-page":"306","DOI":"10.1016\/j.scitotenv.2017.03.094","article-title":"Land use regression modelling of air pollution in high density high rise cities: A case study in Hong Kong","volume":"592","author":"Lee","year":"2017","journal-title":"Sci. Total Environ."},{"key":"ref_34","doi-asserted-by":"crossref","first-page":"074013","DOI":"10.1088\/1748-9326\/ac074a","article-title":"Spatial-temporal patterns of ambient fine particulate matter (PM2.5) and black carbon (BC) pollution in Accra","volume":"16","author":"Alli","year":"2021","journal-title":"Environ. Res. Lett."},{"key":"ref_35","doi-asserted-by":"crossref","first-page":"149931","DOI":"10.1016\/j.scitotenv.2021.149931","article-title":"Nitrogen oxides (NO and NO2) pollution in the Accra metropolis: Spatiotemporal patterns and the role of meteorology","volume":"803","author":"Wang","year":"2022","journal-title":"Sci. Total Environ."},{"key":"ref_36","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., and Sun, J. (2016, January 27\u201330). Deep residual learning for image recognition. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Las Vegas, NV, USA.","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref_37","doi-asserted-by":"crossref","unstructured":"Zhou, B., Khosla, A., Lapedriza, A., Oliva, A., and Torralba, A. Learning Deep Features for Discriminative Localization. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2016.","DOI":"10.1109\/CVPR.2016.319"},{"key":"ref_38","unstructured":"Torch Contributors (2022, July 13). Torchvision Models. Available online: https:\/\/pytorch.org\/vision\/stable\/models.html."},{"key":"ref_39","doi-asserted-by":"crossref","first-page":"151","DOI":"10.1016\/S0048-9697(00)00429-0","article-title":"A regression-based method for mapping traffic-related air pollution: Application and testing in four contrasting urban environments","volume":"253","author":"Briggs","year":"2000","journal-title":"Sci. Total Environ."},{"key":"ref_40","doi-asserted-by":"crossref","first-page":"185","DOI":"10.1038\/sj.jea.7500388","article-title":"A review and evaluation of intraurban air pollution exposure models","volume":"15","author":"Jerrett","year":"2005","journal-title":"J. Expo. Anal. Environ. Epidemiol."},{"key":"ref_41","doi-asserted-by":"crossref","first-page":"107","DOI":"10.1038\/jes.2008.15","article-title":"Intercity transferability of land use regression models for estimating ambient concentrations of nitrogen dioxide","volume":"19","author":"Poplawski","year":"2009","journal-title":"J. Expo. Sci. Environ. Epidemiol."},{"key":"ref_42","unstructured":"Simonyan, K., Vedaldi, A., and Zisserman, A. (2017, October 14). Deep Inside Convolutional Networks: Visualising Image Classification Models and Saliency Maps. Available online: http:\/\/arxiv.org\/abs\/1312.6034."},{"key":"ref_43","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1038\/s41467-021-23853-y","article-title":"Source sector and fuel contributions to ambient PM2.5 and attributable mortality across multiple spatial scales","volume":"12","author":"McDuffie","year":"2021","journal-title":"Nat. Commun."},{"key":"ref_44","doi-asserted-by":"crossref","first-page":"2270","DOI":"10.1021\/es903276s","article-title":"Air Pollution in Accra Neighborhoods: Spatial, Socioeconomic, and Temporal Patterns","volume":"44","author":"Dionisio","year":"2010","journal-title":"Environ. Sci. Technol."}],"container-title":["Remote Sensing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2072-4292\/14\/14\/3429\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,10]],"date-time":"2025-10-10T23:52:22Z","timestamp":1760140342000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2072-4292\/14\/14\/3429"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,7,17]]},"references-count":44,"journal-issue":{"issue":"14","published-online":{"date-parts":[[2022,7]]}},"alternative-id":["rs14143429"],"URL":"https:\/\/doi.org\/10.3390\/rs14143429","relation":{},"ISSN":["2072-4292"],"issn-type":[{"value":"2072-4292","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022,7,17]]}}}