{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,25]],"date-time":"2026-08-25T13:21:35Z","timestamp":1787664095849,"version":"build-2736575974"},"reference-count":46,"publisher":"SAGE Publications","issue":"3","license":[{"start":{"date-parts":[[2026,8,20]],"date-time":"2026-08-20T00:00:00Z","timestamp":1787184000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/journals.sagepub.com\/page\/policies\/text-and-data-mining-license"}],"funder":[{"DOI":"10.13039\/100010269","name":"Wellcome Trust","doi-asserted-by":"publisher","award":["Pathways to Equitable Healthy Cities-209376\/Z\/17\/Z"],"award-info":[{"award-number":["Pathways to Equitable Healthy Cities-209376\/Z\/17\/Z"]}],"id":[{"id":"10.13039\/100010269","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["journals.sagepub.com"],"crossmark-restriction":true},"short-container-title":["Transactions in Urban Data, Science, and Technology"],"published-print":{"date-parts":[[2026,9]]},"abstract":"<jats:p>Fine-scale, geocoded neighborhood socioeconomic status (nSES) data are foundational inputs for urban studies and spatial inequality research, yet remain scarce in emerging economies that together account for over 70% of the global population. Here, we use publicly available satellite and street view imagery to estimate nSES at fine spatial resolution, proposing an ensemble regression framework that unites multi-view images to measure intra-urban inequality. We estimate eight indicators\u2014spanning household registration (hukou), housing, income, employment, and education\u2014as numeric values rather than broad quantile bands, enabling direct cross-neighborhood comparison. Family and individual SES from a representative survey serve as training data. The proposed fusion model outperforms single ensemble regression models and single-view image-based models in mean absolute percentage error. To interpret image-based prediction, we apply SHAP-based feature attribution and modality-contribution analysis, identifying the built-environment features that drive predictions and revealing that satellite and street view imagery play complementary rather than redundant roles. Neighborhood inequalities at traffic analysis zone and township scales in central Beijing are visualized for the first time. We further transfer the trained model to Shanghai, where no comparable public nSES dataset exists, providing a limited proof-of-concept against real-estate data for two of the eight indicators and outlining a replicable pathway for data-scarce cities.<\/jats:p>","DOI":"10.1177\/27541231261473758","type":"journal-article","created":{"date-parts":[[2026,8,21]],"date-time":"2026-08-21T03:56:51Z","timestamp":1787284611000},"page":"303-331","update-policy":"https:\/\/doi.org\/10.1177\/sage-journals-update-policy","source":"Crossref","is-referenced-by-count":0,"title":["Measuring neighborhood socioeconomic status from sky and street: An ensemble learning framework"],"prefix":"10.1177","volume":"5","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-6650-7726","authenticated-orcid":false,"given":"Yan","family":"Li","sequence":"first","affiliation":[{"name":"School of Architecture, Tsinghua University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8657-6988","authenticated-orcid":false,"given":"Ying","family":"Long","sequence":"additional","affiliation":[{"name":"School of Architecture and Hang Lung Center for Real Estate, Key Laboratory of Ecological Planning &amp; Green Building, Ministry of Education, Tsinghua University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Esra","family":"Suel","sequence":"additional","affiliation":[{"name":"Centre for Advanced Spatial Analysis, University College London, London, UK"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9207-4039","authenticated-orcid":false,"given":"Yuyang","family":"Zhang","sequence":"additional","affiliation":[{"name":"School of Architecture, Tsinghua University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Brian E.","family":"Robinson","sequence":"additional","affiliation":[{"name":"Department of Geography, McGill University, Montreal, Canada"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Alicia Catherine","family":"Cavanaugh","sequence":"additional","affiliation":[{"name":"Department of Geography, McGill University, Montreal, Canada"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Nanxi","family":"Su","sequence":"additional","affiliation":[{"name":"School of Architecture, Tsinghua University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Majid","family":"Ezzati","sequence":"additional","affiliation":[{"name":"MRC Centre for Environment and Health, School of Public Health, Imperial College London, London, UK"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"179","published-online":{"date-parts":[[2026,8,20]]},"reference":[{"key":"e_1_3_4_2_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4302-5990-9_4"},{"key":"e_1_3_4_3_1","doi-asserted-by":"crossref","unstructured":"Belgiu M Dr\u0103gu\u0163 L (2016) Random forest in remote sensing: A review of applications and future directions. ISPRS Journal of Photogrammetry and Remote Sensing 114: 24\u201331. https:\/\/doi.org\/10.1016\/j.isprsjprs.2016.01.011","DOI":"10.1016\/j.isprsjprs.2016.01.011"},{"key":"e_1_3_4_4_1","doi-asserted-by":"publisher","DOI":"10.1023\/A:1010933404324"},{"key":"e_1_3_4_5_1","doi-asserted-by":"crossref","unstructured":"Caban-Martinez AJ Lee DJ Goodman E et al. (2011) Health indicators among unemployed and employed young adults. Journal of Occupational and Environmental Medicine 53(2): 196\u2013203. https:\/\/doi.org\/10.1097\/jom.0b013e318209915e","DOI":"10.1097\/JOM.0b013e318209915e"},{"key":"e_1_3_4_6_1","doi-asserted-by":"crossref","unstructured":"Chen J Chen L Li Y et al. (2023) Measuring physical disorder in urban street spaces: A large-scale analysis using street view images and deep learning. Annals of the American Association of Geographers 113(2): 469\u2013487. https:\/\/doi.org\/10.1080\/24694452.2022.2114417","DOI":"10.1080\/24694452.2022.2114417"},{"key":"e_1_3_4_7_1","doi-asserted-by":"crossref","unstructured":"Deng FF Huang Y (2004) Uneven land reform and urban sprawl in China: The case of Beijing. Progress in Planning 61(3): 211\u2013236. https:\/\/doi.org\/10.1016\/j.progress.2003.10.004","DOI":"10.1016\/j.progress.2003.10.004"},{"key":"e_1_3_4_8_1","doi-asserted-by":"crossref","unstructured":"Dong L Ratti C Zheng S (2019) Predicting neighborhoods\u2019 socioeconomic attributes using restaurant data. Proceedings of the National Academy of Sciences 116(31): 15447\u201315452. https:\/\/doi.org\/10.1073\/pnas.1903064116","DOI":"10.1073\/pnas.1903064116"},{"key":"e_1_3_4_9_1","doi-asserted-by":"crossref","unstructured":"D\u017eeroski S \u017denko B (2004) Is combining classifiers with stacking better than selecting the best one? Machine Learning 54(3): 255\u2013273. https:\/\/doi.org\/10.1023\/b:mach.0000015881.36452.6e","DOI":"10.1023\/B:MACH.0000015881.36452.6e"},{"key":"e_1_3_4_10_1","doi-asserted-by":"crossref","unstructured":"Fan Z Zhang F Loo BP et al. (2023) Urban visual intelligence: Uncovering hidden city profiles with street view images. Proceedings of the National Academy of Sciences 120(27): Article number e2220417120. https:\/\/doi.org\/10.1073\/pnas.2220417120","DOI":"10.1073\/pnas.2220417120"},{"key":"e_1_3_4_11_1","doi-asserted-by":"publisher","DOI":"10.1145\/3711896.3736878"},{"key":"e_1_3_4_12_1","doi-asserted-by":"crossref","unstructured":"Gebru T Krause J Wang Y et al. (2017) Using deep learning and Google Street View to estimate the demographic makeup of neighborhoods across the United States. Proceedings of the National Academy of Sciences 114(50): 13108\u201313113. https:\/\/doi.org\/10.1073\/pnas.1700035114","DOI":"10.1073\/pnas.1700035114"},{"key":"e_1_3_4_13_1","first-page":"2","article-title":"Folding Beijing (K. Liu, Trans.)","author":"Hao J","year":"2015","unstructured":"Hao J (2015) Folding Beijing (K. Liu, Trans.). Uncanny Magazine, 2.","journal-title":"Uncanny Magazine"},{"key":"e_1_3_4_14_1","doi-asserted-by":"crossref","unstructured":"Hutengs C Vohland M (2016) Downscaling land surface temperatures at regional scales with random forest regression. Remote Sensing of Environment 178: 127\u2013141. https:\/\/doi.org\/10.1016\/j.rse.2016.03.006","DOI":"10.1016\/j.rse.2016.03.006"},{"key":"e_1_3_4_15_1","doi-asserted-by":"crossref","unstructured":"Jafarzadeh H Mahdianpari M Gill E et al. (2021) Bagging and boosting ensemble classifiers for classification of multispectral hyperspectral and PolSAR data: A comparative evaluation. Remote Sensing 13(21): 4405. https:\/\/doi.org\/10.3390\/rs13214405","DOI":"10.3390\/rs13214405"},{"key":"e_1_3_4_16_1","doi-asserted-by":"crossref","unstructured":"Jean N Burke M Xie M et al. (2016) Combining satellite imagery and machine learning to predict poverty. Science 353(6301): 790\u2013794. https:\/\/doi.org\/10.1126\/science.aaf7894","DOI":"10.1126\/science.aaf7894"},{"key":"e_1_3_4_17_1","doi-asserted-by":"crossref","unstructured":"Kuffer M Pfeffer K Sliuzas R (2016) Slums from space\u201415 years of slum mapping using remote sensing. Remote Sensing 8(6): 455. https:\/\/doi.org\/10.3390\/rs8060455","DOI":"10.3390\/rs8060455"},{"key":"e_1_3_4_18_1","volume-title":"Industrial and Business Forecasting Methods: A Practical Guide to Exponential Smoothing and Curve Fitting","author":"Lewis CD","year":"1982","unstructured":"Lewis CD (1982) Industrial and Business Forecasting Methods: A Practical Guide to Exponential Smoothing and Curve Fitting. Butterworth-Heinemann."},{"key":"e_1_3_4_19_1","volume-title":"10th International Conference on Geographic Information Science (GIScience)","author":"Li Y","year":"2018","unstructured":"Li Y, Chen Y, Rajabifard A, et al. (2018) Estimating building age from Google street view images using deep learning (short paper). In: 10th International Conference on Geographic Information Science (GIScience). Schloss Dagstuhl\u2014Leibniz-Zentrum f\u00fcr Informatik."},{"key":"e_1_3_4_20_1","doi-asserted-by":"crossref","unstructured":"Li Y Long Y (2024) Inferring storefront vacancy using mobile sensing images and computer vision approaches. Computers Environment and Urban Systems 108: Article number 102071. https:\/\/doi.org\/10.1016\/j.compenvurbsys.2023.102071","DOI":"10.1016\/j.compenvurbsys.2023.102071"},{"key":"e_1_3_4_21_1","doi-asserted-by":"crossref","unstructured":"Li Y Sarvi M Khoshelham K et al. (2020) Multi-view crowd congestion monitoring system based on an ensemble of convolutional neural network classifiers. Journal of Intelligent Transportation Systems 24(5): 437\u2013448. https:\/\/doi.org\/10.1080\/15472450.2020.1746909","DOI":"10.1080\/15472450.2020.1746909"},{"key":"e_1_3_4_22_1","doi-asserted-by":"crossref","unstructured":"Li Y Meng X Zhao H et al. (2023a) Identifying abandoned buildings in shrinking cities with mobile sensing images. Urban Informatics 2(1): 3. https:\/\/doi.org\/10.1007\/s44212-023-00025-5","DOI":"10.1007\/s44212-023-00025-5"},{"key":"e_1_3_4_23_1","doi-asserted-by":"crossref","unstructured":"Li Y Zhang Y Wu Q et al. (2023b) Greening the concrete jungle: Unveiling the co-mitigation of greenspace configuration on PM2.5 and land surface temperature with explanatory machine learning. Urban Forestry & Urban Greening 88: 128086. https:\/\/doi.org\/10.1016\/j.ufug.2023.128086","DOI":"10.1016\/j.ufug.2023.128086"},{"key":"e_1_3_4_24_1","doi-asserted-by":"publisher","DOI":"10.1145\/3637528.3671578"},{"key":"e_1_3_4_25_1","doi-asserted-by":"crossref","unstructured":"Li Y Ma Y Long Y (2024b) Protocol for assessing neighborhood physical disorder using the YOLOv8 deep learning model. STAR Protocols 5(1): Article number 102778. https:\/\/doi.org\/10.1016\/j.xpro.2023.102778","DOI":"10.1016\/j.xpro.2023.102778"},{"key":"e_1_3_4_26_1","doi-asserted-by":"crossref","unstructured":"Liu N Deng Q Hu P et al. (2023) Associations between urban exposome and recurrence risk among survivors of acute myocardial infarction in Beijing China. Environmental Research 238: 117267. https:\/\/doi.org\/10.1016\/j.envres.2023.117267","DOI":"10.1016\/j.envres.2023.117267"},{"key":"e_1_3_4_27_1","doi-asserted-by":"crossref","unstructured":"Long Y Thill J-C (2015) Combining smart card data and household travel survey to analyze jobs\u2013housing relationships in Beijing. Computers Environment and Urban Systems 53: 19\u201335. https:\/\/doi.org\/10.1016\/j.compenvurbsys.2015.02.005","DOI":"10.1016\/j.compenvurbsys.2015.02.005"},{"key":"e_1_3_4_28_1","article-title":"A unified approach to interpreting model predictions","author":"Lundberg SM","year":"2017","unstructured":"Lundberg SM, Lee S-I (2017) A unified approach to interpreting model predictions. In: Advances in neural information processing systems 30 (NeurIPS).","journal-title":"Advances in neural information processing systems 30 (NeurIPS)"},{"key":"e_1_3_4_29_1","doi-asserted-by":"crossref","unstructured":"Ma Y Li Y Long Y (2025) Measuring temporal evolution of nationwide urban physical disorder: An approach combining time-series street view imagery with deep learning. Annals of the American Association of Geographers 115(4): 923\u2013948. https:\/\/doi.org\/10.1080\/24694452.2025.2467330","DOI":"10.1080\/24694452.2025.2467330"},{"key":"e_1_3_4_30_1","doi-asserted-by":"crossref","unstructured":"Mutanga O Adam E Cho MA (2012) High density biomass estimation for wetland vegetation using WorldView-2 imagery and random forest regression algorithm. International Journal of Applied Earth Observation and Geoinformation 18: 399\u2013406. https:\/\/doi.org\/10.1016\/j.jag.2012.03.012","DOI":"10.1016\/j.jag.2012.03.012"},{"key":"e_1_3_4_31_1","doi-asserted-by":"crossref","unstructured":"Naik N Kominers SD Raskar R et al. (2017) Computer vision uncovers predictors of physical urban change. Proceedings of the National Academy of Sciences 114(29): 7571\u20137576. https:\/\/doi.org\/10.1073\/pnas.1619003114","DOI":"10.1073\/pnas.1619003114"},{"key":"e_1_3_4_32_1","doi-asserted-by":"crossref","unstructured":"Niu T Chen Y Yuan Y (2020) Measuring urban poverty using multi-source data and a random forest algorithm: A case study in Guangzhou. Sustainable Cities and Society 54: 102014. https:\/\/doi.org\/10.1016\/j.scs.2020.102014","DOI":"10.1016\/j.scs.2020.102014"},{"key":"e_1_3_4_33_1","doi-asserted-by":"crossref","unstructured":"Organisation for Economic Co-operation and Development (2018) Education at a Glance 2018: OECD Indicators. OECD Publishing. https:\/\/doi.org\/10.1787\/eag-2018-en","DOI":"10.1787\/eag-2018-en"},{"key":"e_1_3_4_34_1","doi-asserted-by":"crossref","unstructured":"Russakovsky O Deng J Su H et al. (2015) ImageNet large scale visual recognition challenge. International Journal of Computer Vision 115(3): 211\u2013252. https:\/\/doi.org\/10.1007\/s11263-015-0816-y","DOI":"10.1007\/s11263-015-0816-y"},{"key":"e_1_3_4_35_1","doi-asserted-by":"crossref","unstructured":"Sampson RJ Morenoff JD Gannon-Rowley T (2002) Assessing \u201cneighborhood effects\u201d: Social processes and new directions in research. Annual Review of Sociology 28(1): 443\u2013478. https:\/\/doi.org\/10.1146\/annurev.soc.28.110601.141114","DOI":"10.1146\/annurev.soc.28.110601.141114"},{"key":"e_1_3_4_36_1","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN.2004.1380102"},{"key":"e_1_3_4_37_1","doi-asserted-by":"crossref","unstructured":"Song Q Smith JP (2019) Hukou system mechanisms and health stratification across the life course in rural and urban China. Health & Place 58: 102150. https:\/\/doi.org\/10.1016\/j.healthplace.2019.102150","DOI":"10.1016\/j.healthplace.2019.102150"},{"key":"e_1_3_4_38_1","doi-asserted-by":"crossref","unstructured":"Suel E Bhatt S Brauer M et al. (2021) Multimodal deep learning from satellite and street-level imagery for measuring income overcrowding and environmental deprivation in urban areas. Remote Sensing of Environment 257: 112339. https:\/\/doi.org\/10.1016\/j.rse.2021.112339","DOI":"10.1016\/j.rse.2021.112339"},{"key":"e_1_3_4_39_1","doi-asserted-by":"crossref","unstructured":"Suel E Polak JW Bennett JE et al. (2019) Measuring social environmental and health inequalities using deep learning and street imagery. Scientific Reports 9(1): 1\u201310. https:\/\/doi.org\/10.1038\/s41598-019-42036-w","DOI":"10.1038\/s41598-019-42036-w"},{"key":"e_1_3_4_40_1","doi-asserted-by":"crossref","unstructured":"Wan C Su S (2016) Neighborhood housing deprivation and public health: Theoretical linkage empirical evidence and implications for urban planning. Habitat International 57: 11\u201323. https:\/\/doi.org\/10.1016\/j.habitatint.2016.06.010","DOI":"10.1016\/j.habitatint.2016.06.010"},{"key":"e_1_3_4_41_1","doi-asserted-by":"crossref","unstructured":"Wang X Sutton PC Qi B (2019) Global mapping of GDP at 1 km2 using VIIRS nighttime satellite imagery. ISPRS International Journal of Geo-Information 8(12): 580. https:\/\/doi.org\/10.3390\/ijgi8120580","DOI":"10.3390\/ijgi8120580"},{"key":"e_1_3_4_42_1","doi-asserted-by":"crossref","unstructured":"Wolpert DH (1992) Stacked generalization. Neural Networks 5(2): 241\u2013259. https:\/\/doi.org\/10.1016\/s0893-6080(05)80023-1","DOI":"10.1016\/S0893-6080(05)80023-1"},{"key":"e_1_3_4_43_1","volume-title":"Developing an Area-Based Socioeconomic Measure from American Community Survey Data","author":"Yang J","year":"2014","unstructured":"Yang J, Schupp C, Harrati A, et al. (2014) Developing an Area-Based Socioeconomic Measure from American Community Survey Data. Cancer Prevention Institute of California."},{"key":"e_1_3_4_44_1","doi-asserted-by":"crossref","unstructured":"Yue X Antonietti A Alirezaei M et al. (2022) Using convolutional neural networks to derive neighborhood built environments from Google Street View images and examine their associations with health outcomes. International Journal of Environmental Research and Public Health 19(19): 12095. https:\/\/doi.org\/10.3390\/ijerph191912095","DOI":"10.3390\/ijerph191912095"},{"key":"e_1_3_4_45_1","doi-asserted-by":"crossref","unstructured":"Zhang Y Wu Q Wu L et al. (2021) Measuring community green inequity: A fine-scale assessment of Beijing urban area. Land 10(11): 1197. https:\/\/doi.org\/10.3390\/land10111197","DOI":"10.3390\/land10111197"},{"key":"e_1_3_4_46_1","doi-asserted-by":"crossref","unstructured":"Zhang Y Liu N Li Y et al. (2023) Neighborhood infrastructure-related risk factors and non-communicable diseases: A systematic meta-review. Environmental Health 22(1): 2. https:\/\/doi.org\/10.1186\/s12940-022-00955-8","DOI":"10.1186\/s12940-022-00955-8"},{"key":"e_1_3_4_47_1","doi-asserted-by":"crossref","unstructured":"Zhao X Yu B Liu Y et al. (2019) Estimation of poverty using random forest regression with multi-source data: A case study in Bangladesh. Remote Sensing 11(4): 375. https:\/\/doi.org\/10.3390\/rs11040375","DOI":"10.3390\/rs11040375"}],"container-title":["Transactions in Urban Data, Science, and Technology"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/journals.sagepub.com\/doi\/pdf\/10.1177\/27541231261473758","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/journals.sagepub.com\/doi\/full-xml\/10.1177\/27541231261473758","content-type":"application\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/journals.sagepub.com\/doi\/pdf\/10.1177\/27541231261473758","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,8,25]],"date-time":"2026-08-25T12:48:39Z","timestamp":1787662119000},"score":1,"resource":{"primary":{"URL":"https:\/\/journals.sagepub.com\/doi\/10.1177\/27541231261473758"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,8,20]]},"references-count":46,"journal-issue":{"issue":"3","published-print":{"date-parts":[[2026,9]]}},"alternative-id":["10.1177\/27541231261473758"],"URL":"https:\/\/doi.org\/10.1177\/27541231261473758","relation":{},"ISSN":["2754-1231","2754-1231"],"issn-type":[{"value":"2754-1231","type":"print"},{"value":"2754-1231","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,8,20]]}}}