{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,5]],"date-time":"2026-05-05T03:56:05Z","timestamp":1777953365399,"version":"3.51.4"},"reference-count":37,"publisher":"Association for Computing Machinery (ACM)","issue":"4","license":[{"start":{"date-parts":[[2026,3,31]],"date-time":"2026-03-31T00:00:00Z","timestamp":1774915200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/100000001","name":"National Science Foundation","doi-asserted-by":"publisher","award":["2411273"],"award-info":[{"award-number":["2411273"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":["Commun. ACM"],"published-print":{"date-parts":[[2026,4,1]]},"abstract":"<jats:p>Finding where the trees are in a city and monitoring any changes are essential for sustainable urban management. Historically, urban forests are mainly inventoried via manual processes often limited to public lands. Leveraging advances in computing, we present a novel generative artificial intelligence (AI) method along with a first-ever national-scale dataset, to automatically localize trees in cities across the nation using satellite imagery. Our monitoring approach is fully automated and can be completed for 330 U.S. cities within less than a day of computing, enabling actionable knowledge of changes in urban trees and supporting sustainable development decisions. We successfully localized and counted over 278 million trees, achieving an average tree count accuracy of 92.5% and spatial accuracy of 1.5m for 2024\u20132025. Our computational approach allows for novel nationwide analysis to be performed. For example, we can localize approximately 117 million trees on private lands and 161 million on public lands. Further, we show and quantify that urban tree distribution exhibits strong spatial disparity, with low-income communities having substantially fewer trees and less canopy cover than others. In addition, we compare tree count and layouts before and after multiple major events (e.g., major fires and destructive weather phenomena). Overall, our approach enhances computational urban planning, including weather and extreme event forecasting, for the development of sustainable cities.<\/jats:p>","DOI":"10.1145\/3762636","type":"journal-article","created":{"date-parts":[[2026,3,30]],"date-time":"2026-03-30T19:53:22Z","timestamp":1774900402000},"page":"50-59","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Where Are the City Trees? Monitoring Urban Trees across the U.S. Using Generative AI"],"prefix":"10.1145","volume":"69","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-2751-009X","authenticated-orcid":false,"given":"Adnan","family":"Firoze","sequence":"first","affiliation":[{"name":"Purdue University System, Computer Science, West Lafayette, Indiana, United States"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Akshaj","family":"Uppala","sequence":"additional","affiliation":[{"name":"Purdue University System, Computer Science, West Lafayette, Indiana, United States"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Lindsay","family":"Darling","sequence":"additional","affiliation":[{"name":"Purdue University System, Computer Science, West Lafayette, Indiana, United States"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Raymond A.","family":"Yeh","sequence":"additional","affiliation":[{"name":"Purdue University System, Computer Science, West Lafayette, Indiana, United States"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Bedrich","family":"Benes","sequence":"additional","affiliation":[{"name":"Purdue University System, Computer Science, West Lafayette, Indiana, United States"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Brady","family":"Hardiman","sequence":"additional","affiliation":[{"name":"Purdue University System, Computer Science, West Lafayette, Indiana, United States"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Songlin","family":"Fei","sequence":"additional","affiliation":[{"name":"Purdue University System, Computer Science, West Lafayette, Indiana, United States"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9794-462X","authenticated-orcid":false,"given":"Daniel","family":"Aliaga","sequence":"additional","affiliation":[{"name":"Purdue University, Computer Science, West Lafayette, Indiana, United States"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2026,3,31]]},"reference":[{"key":"e_1_3_2_2_2","doi-asserted-by":"crossref","unstructured":"Beery S. et al. The auto arborist dataset: A large-scale benchmark for multiview urban forest monitoring under domain shift. In Proceedings of the 2022 IEEE\/CVF Conf. on Computer Vision and Pattern Recognition (2022) 21262\u201321275.","DOI":"10.1109\/CVPR52688.2022.02061"},{"key":"e_1_3_2_3_2","doi-asserted-by":"crossref","unstructured":"Chen S. Sun P. Song Y. and Luo P. DiffusionDet: Diffusion model for object detection. In Proceedings of IEEE\/CVF Int. Conf. Comput. Vis. (2023) 3423\u20133433.","DOI":"10.1109\/ICCV51070.2023.01816"},{"key":"e_1_3_2_4_2","doi-asserted-by":"crossref","unstructured":"Couairon R. et al. FlexIT: Towards flexible semantic image translation. In Proceedings of IEEE\/CVF Conf. Comput. Vis. Pattern Recognit. (2022) 14048\u201314058.","DOI":"10.1109\/CVPR52688.2022.01773"},{"key":"e_1_3_2_5_2","doi-asserted-by":"publisher","DOI":"10.1073\/pnas.1917213116"},{"key":"e_1_3_2_6_2","unstructured":"Earth Define. US Tree Map\u00a0(2023)."},{"key":"e_1_3_2_7_2","doi-asserted-by":"crossref","unstructured":"Firoze A. et al. Tree instance segmentation with temporal contour graph. In Proceedings of 2023 IEEE\/CVF Conf. Comput. Vis. Pattern Recognit. (2023) 2193\u20132202.","DOI":"10.1109\/CVPR52729.2023.00218"},{"key":"e_1_3_2_8_2","doi-asserted-by":"publisher","DOI":"10.1007\/s00371-022-02526-x"},{"key":"e_1_3_2_9_2","doi-asserted-by":"publisher","DOI":"10.1038\/s41558-021-01092-9"},{"key":"e_1_3_2_10_2","doi-asserted-by":"publisher","DOI":"10.1145\/3339399"},{"key":"e_1_3_2_11_2","doi-asserted-by":"crossref","unstructured":"Huang Z. Huang L. Huang Y. and Liu W. Mask scoring R-CNN. In Proceedings of IEEE\/CVF Conf. Comput. Vis. Pattern Recognit. (2019) 6409\u20136418.","DOI":"10.1109\/CVPR.2019.00657"},{"key":"e_1_3_2_12_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.ufug.2022.127760"},{"key":"e_1_3_2_13_2","unstructured":"Jiang Y. et al. TransGAN: Two pure transformers can make one strong GAN and that can scale up. arXiv preprint arXiv:2102.07074 (2021)."},{"key":"e_1_3_2_14_2","doi-asserted-by":"crossref","unstructured":"Kim S. Kim J. and Kwak S. Dense text-to-image generation with attention modulation. In Proceedings of IEEE\/CVF Int. Conf. Comput. Vis. (2023) 7700\u20137710.","DOI":"10.1109\/ICCV51070.2023.00708"},{"key":"e_1_3_2_15_2","doi-asserted-by":"crossref","unstructured":"Kim Y. et al. MUNICH v2.0: A street-network model coupled with SSH-aerosol (v1.2) for multi-pollutant modelling (2022).","DOI":"10.5194\/gmd-2022-26"},{"issue":"1","key":"e_1_3_2_16_2","first-page":"273","article-title":"The integrated WRF\/urban modelling system: Development, evaluation, and applications to urban environmental problems","volume":"31","author":"Kusaka H.","year":"2011","unstructured":"Kusaka, H. et al. The integrated WRF\/urban modelling system: Development, evaluation, and applications to urban environmental problems. Intern. J. of Climatology 31, 1 (2011), 273\u2013288.","journal-title":"Intern. J. of Climatology"},{"key":"e_1_3_2_17_2","doi-asserted-by":"crossref","unstructured":"Lazarow J. Xu W. and Tu Z. Instance segmentation with mask-supervised polygonal boundary transformers. In Proceedings of IEEE\/CVF Conf. Comput. Vis. Pattern Recognit. (2022) 1292\u20131302.","DOI":"10.1109\/CVPR52688.2022.00434"},{"key":"e_1_3_2_18_2","doi-asserted-by":"crossref","unstructured":"Lee J.J. et al. Tree-D Fusion: Simulation-ready tree dataset from single images with diffusion priors. In ECCV 2024. Springer-Verlag (2024) 439\u2013460.","DOI":"10.1007\/978-3-031-72940-9_25"},{"key":"e_1_3_2_19_2","first-page":"6109","article-title":"Fabric defect data augmentation using conditional generative adversarial networks","volume":"28","author":"Li Z.","year":"2024","unstructured":"Li, Z., Wang, Y., and Liu, Q. Fabric defect data augmentation using conditional generative adversarial networks. Soft Computing 28\u00a0(2024), 6109\u20136122.","journal-title":"Soft Computing"},{"key":"e_1_3_2_20_2","doi-asserted-by":"crossref","unstructured":"Li B. Xue K. Liu B. and Lai Y. BBDM: Image-to-image translation with Brownian bridge diffusion models. In Proceedings of IEEE\/CVF Conf. Comput. Vis. Pattern Recognit. (2023) 1952\u20131961.","DOI":"10.1109\/CVPR52729.2023.00194"},{"key":"e_1_3_2_21_2","first-page":"110990","article-title":"F-DETR: Fusion detection transformer with heterogeneous scale multi-branch structure","volume":"147","author":"Liu Y.","year":"2024","unstructured":"Liu, Y., Wang, Z., and Wang, Y. F-DETR: Fusion detection transformer with heterogeneous scale multi-branch structure. Applied Soft Computing 147, (2024), 110990.","journal-title":"Applied Soft Computing"},{"key":"e_1_3_2_22_2","doi-asserted-by":"crossref","unstructured":"Liu Z. et al. Swin transformer: Hierarchical vision transformer using shifted windows. arXiv preprint arXiv:2103.14030 (2021).","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"e_1_3_2_23_2","unstructured":"Nearmap. Aerial map coverage\u00a0(2023)."},{"key":"e_1_3_2_24_2","doi-asserted-by":"publisher","DOI":"10.1145\/3502220"},{"key":"e_1_3_2_25_2","unstructured":"Nowak D. et al. The urban forest of New York City.\u00a0U.S. Department of Agriculture Forest Service Northern Research Station\u00a0(2018)."},{"key":"e_1_3_2_26_2","unstructured":"NYC Parks and Recreation Project. Street tree census (2017)."},{"key":"e_1_3_2_27_2","unstructured":"OpenStreetMap contributors and OpenStreetMap; https:\/\/www.openstreetmap.org"},{"key":"e_1_3_2_28_2","unstructured":"Planet. Planet explorer (2023)."},{"key":"e_1_3_2_29_2","unstructured":"Ravi N. et al. SAM 2: Segment anything in images and videos. arXiv preprint arXiv:2408.00714 (2024)."},{"key":"e_1_3_2_30_2","first-page":"234","article-title":"U-Net: Convolutional networks for biomedical image segmentation","author":"Ronneberger O.","year":"2015","unstructured":"Ronneberger, O. et al. U-Net: Convolutional networks for biomedical image segmentation. In Medical Image Computing and Computer-Assisted Intervention (2015), 234\u2013241.","journal-title":"Medical Image Computing and Computer-Assisted Intervention"},{"key":"e_1_3_2_31_2","article-title":"Live fast, die young: Accelerated growth, mortality, and turnover in street trees","volume":"14","author":"Smith I.","year":"2019","unstructured":"Smith, I. et al. Live fast, die young: Accelerated growth, mortality, and turnover in street trees. PLoS ONE 14\u00a0(2019).","journal-title":"PLoS ONE"},{"key":"e_1_3_2_32_2","doi-asserted-by":"publisher","DOI":"10.1145\/990680.990704"},{"key":"e_1_3_2_33_2","unstructured":"U.S. Census Bureau. City and town population totals: 2020\u20132022. (2023)."},{"key":"e_1_3_2_34_2","unstructured":"Walker K. and Herman M. Tidycensus: Load US census boundary and attribute data as \u2019tidyverse\u2019 and \u2019sf\u2019-ready data frames (2023); https:\/\/walker-data.com\/tidycensus\/"},{"key":"e_1_3_2_35_2","doi-asserted-by":"publisher","DOI":"10.1126\/science.aam9724"},{"key":"e_1_3_2_36_2","doi-asserted-by":"publisher","DOI":"10.3390\/ijerph17124371"},{"key":"e_1_3_2_37_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.uclim.2019.100460"},{"key":"e_1_3_2_38_2","doi-asserted-by":"publisher","DOI":"10.3389\/fenvs.2021.755587"}],"container-title":["Communications of the ACM"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dl.acm.org\/doi\/full\/10.1145\/3762636","content-type":"text\/html","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3762636","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3762636","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,4]],"date-time":"2026-05-04T15:05:20Z","timestamp":1777907120000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3762636"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,3,31]]},"references-count":37,"journal-issue":{"issue":"4","published-print":{"date-parts":[[2026,4,1]]}},"alternative-id":["10.1145\/3762636"],"URL":"https:\/\/doi.org\/10.1145\/3762636","relation":{},"ISSN":["0001-0782","1557-7317"],"issn-type":[{"value":"0001-0782","type":"print"},{"value":"1557-7317","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,3,31]]},"assertion":[{"value":"2024-08-09","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2026-03-31","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}