{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,23]],"date-time":"2026-06-23T13:50:31Z","timestamp":1782222631449,"version":"3.54.5"},"reference-count":48,"publisher":"Wiley","issue":"2","license":[{"start":{"date-parts":[[2026,3,8]],"date-time":"2026-03-08T00:00:00Z","timestamp":1772928000000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0\/"},{"start":{"date-parts":[[2026,3,8]],"date-time":"2026-03-08T00:00:00Z","timestamp":1772928000000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/doi.wiley.com\/10.1002\/tdm_license_1.1"}],"content-domain":{"domain":["onlinelibrary.wiley.com"],"crossmark-restriction":true},"short-container-title":["Transactions in GIS"],"published-print":{"date-parts":[[2026,4]]},"abstract":"<jats:title>ABSTRACT<\/jats:title>\n                  <jats:p>\n                    The proliferation of AI\u2010generated building footprints in OpenStreetMap (OSM) has transformed crowdsourced mapping, yet the geometric characteristics associated with different digitization methods remain poorly understood. This study presents a comprehensive morphometric analysis of more than 9\u2009million building footprints across 15 geographically diverse cities spanning six continents. To investigate whether buildings labeled with AI source tags exhibit distinct geometric patterns, machine learning classifiers were trained on a regionally balanced dataset of approximately 1\u2009million buildings. Thirty\u2010two shape\u2010based features encompassing size metrics, shape regularity, complexity measures, and anomaly detection indicators were extracted, and three gradient boosting classifiers were evaluated to distinguish these contributions. The best\u2010performing model (LightGBM with class weighting) was used to achieve 74.5% balanced accuracy, 82.9% recall, and 0.819 AUC, providing evidence that buildings labeled with AI source tags exhibit geometric patterns that differ systematically from other buildings in the dataset. Feature importance analysis revealed that orthogonality measurements, vertex density patterns, and shape regularity indices were the strongest discriminators, with orthogonality\n                    <jats:italic>z<\/jats:italic>\n                    \u2010scores alone accounting for 18.2% of model importance. AI\u2010generated buildings showed significantly higher orthogonality (angles within 5\u00b0 of 90\u00b0), greater rectangularity, and more consistent vertex spacing compared to human\u2010digitized footprints. Geographic analysis revealed substantial variation in both AI adoption (0.15% in Berlin to 15.7% in Cairo) and model performance across regions, with balanced accuracy ranging from 67.5% (Asia) to 79.9% (Oceania). However, 34% of human\u2010mapped buildings exhibited AI\u2010like geometric patterns: an overlap reflecting multiple competing factors including methodological convergence, label uncertainty from hybrid workflows, OSM's version\u2010history limitations, and natural variation in human digitization practices, none of which can be definitively separated without independent ground truth validation. These findings provide exploratory evidence that geometric analysis might complement other approaches to understanding data provenance in crowdsourced platforms, though substantial overlap between categories limits the utility of morphometric features for definitive source attribution.\n                  <\/jats:p>","DOI":"10.1111\/tgis.70227","type":"journal-article","created":{"date-parts":[[2026,3,9]],"date-time":"2026-03-09T06:11:13Z","timestamp":1773036673000},"update-policy":"https:\/\/doi.org\/10.1002\/crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Machine Learning Classification of\n                    <scp>AI<\/scp>\n                    \u2010Generated and Human\u2010Mapped Buildings in\n                    <scp>OpenStreetMap<\/scp>\n                    Using Morphometric Analysis"],"prefix":"10.1111","volume":"30","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-9072-869X","authenticated-orcid":false,"given":"Abdulkadir","family":"Memduho\u011flu","sequence":"first","affiliation":[{"name":"Department of Geomatic Engineering, Faculty of Engineering Harran University  \u015eanl\u0131urfa T\u00fcrkiye"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"311","published-online":{"date-parts":[[2026,3,8]]},"reference":[{"key":"e_1_2_10_2_1","doi-asserted-by":"publisher","DOI":"10.3390\/ijgi8050232"},{"key":"e_1_2_10_3_1","doi-asserted-by":"publisher","DOI":"10.1080\/24694452.2025.2589286"},{"key":"e_1_2_10_4_1","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0180698"},{"key":"e_1_2_10_5_1","doi-asserted-by":"publisher","DOI":"10.1080\/13658816.2017.1346257"},{"key":"e_1_2_10_6_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.compenvurbsys.2022.101809"},{"key":"e_1_2_10_7_1","doi-asserted-by":"crossref","unstructured":"Brasebin M. J.Perret S.Musti\u00e8re andC.Weber.2012.\u201cMeasuring the Impact of 3D Data Geometric Modeling on Spatial Analysis: Illustrations With Skyview Factor.\u201dUsage Usability and Utility of 3D City Models\u2013European COST Action TU0801 02001.https:\/\/doi.org\/10.1051\/3u3d\/201202001.","DOI":"10.1051\/3u3d\/201202001"},{"key":"e_1_2_10_8_1","doi-asserted-by":"publisher","DOI":"10.1023\/A:1010933404324"},{"key":"e_1_2_10_9_1","doi-asserted-by":"publisher","DOI":"10.3390\/ijgi7080289"},{"key":"e_1_2_10_10_1","doi-asserted-by":"publisher","DOI":"10.1613\/jair.953"},{"key":"e_1_2_10_11_1","doi-asserted-by":"publisher","DOI":"10.1145\/2939672.2939785"},{"key":"e_1_2_10_12_1","doi-asserted-by":"publisher","DOI":"10.1038\/s41598\u2010024\u201064231\u20100"},{"key":"e_1_2_10_13_1","doi-asserted-by":"publisher","DOI":"10.3390\/ijgi4031657"},{"key":"e_1_2_10_14_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.camwa.2010.07.043"},{"key":"e_1_2_10_15_1","doi-asserted-by":"publisher","DOI":"10.5194\/isprs\u2010annals\u2010X\u20105\u2010W2\u20102025\u2010165\u20102025"},{"key":"e_1_2_10_16_1","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0299713"},{"key":"e_1_2_10_17_1","doi-asserted-by":"publisher","DOI":"10.1080\/17538947.2025.2473637"},{"key":"e_1_2_10_18_1","doi-asserted-by":"publisher","DOI":"10.21105\/joss.01807"},{"key":"e_1_2_10_19_1","doi-asserted-by":"publisher","DOI":"10.1109\/IGARSS.2018.8518116"},{"key":"e_1_2_10_20_1","doi-asserted-by":"publisher","DOI":"10.1111\/j.1467\u20109671.2010.01203.x"},{"key":"e_1_2_10_21_1","doi-asserted-by":"publisher","DOI":"10.1109\/MPRV.2008.80"},{"key":"e_1_2_10_22_1","doi-asserted-by":"publisher","DOI":"10.3390\/ijgi2041066"},{"key":"e_1_2_10_23_1","doi-asserted-by":"publisher","DOI":"10.1038\/s41467\u2010023\u201039698\u20106"},{"key":"e_1_2_10_24_1","doi-asserted-by":"crossref","unstructured":"Huang X. Z.Tu X.Ye andM.Goodchild.2025.\u201cThe Role of Open\u2010Source LLMs in Shaping the Future of GeoAI.\u201darXiv.https:\/\/doi.org\/10.48550\/arXiv.2504.17833.","DOI":"10.1080\/19475683.2026.2630753"},{"key":"e_1_2_10_25_1","unstructured":"Humanitarian OpenStreetMap Team.2024a.\u201cGaza Building Footprints Pre\u2010Conflict Update 2024.\u201dhttps:\/\/www.hotosm.org\/projects\/gaza\u2010building\u2010footprints\u2010pre\u2010conflict\u2010update\u20102024\/."},{"key":"e_1_2_10_26_1","unstructured":"Humanitarian OpenStreetMap Team.2024b.\u201cOSM Building Dataset Complete for Conflict Affected Districts in Southern Lebanon.\u201dhttps:\/\/www.hotosm.org\/updates\/osm\u2010building\u2010dataset\u2010complete\u2010for\u2010conflict\u2010affected\u2010districts\u2010in\u2010southern\u2010lebanon\/."},{"key":"e_1_2_10_27_1","unstructured":"Humanitarian OpenStreetMap Team.2024c.\u201cfAIr: Free and Open Source AI for Resilient Mapping.\u201dhttps:\/\/www.hotosm.org\/tech\u2010suite\/fair\/."},{"key":"e_1_2_10_28_1","unstructured":"Humanitarian OpenStreetMap Team.2024d.\u201cfAIr in Production is Available for Everyone.\u201dhttps:\/\/www.hotosm.org\/updates\/fair\u2010in\u2010production\u2010is\u2010available\u2010for\u2010everyone\/."},{"key":"e_1_2_10_29_1","doi-asserted-by":"publisher","DOI":"10.1080\/01431161.2018.1528024"},{"key":"e_1_2_10_30_1","first-page":"3146","article-title":"LightGBM: A Fast, Distributed, Gradient Boosting Framework","volume":"30","author":"Ke G.","year":"2017","journal-title":"Advances in Neural Information Processing Systems (NIPS)"},{"key":"e_1_2_10_31_1","doi-asserted-by":"publisher","DOI":"10.1080\/13658816.2022.2103818"},{"key":"e_1_2_10_32_1","doi-asserted-by":"publisher","DOI":"10.1126\/science.156.3775.636"},{"key":"e_1_2_10_33_1","volume-title":"The Fractal Geometry of Nature\/Revised and Enlarged Edition","author":"Mandelbrot B. B.","year":"1983"},{"key":"e_1_2_10_34_1","doi-asserted-by":"publisher","DOI":"10.1007\/s12145\u2010024\u201001463\u20108"},{"key":"e_1_2_10_35_1","doi-asserted-by":"publisher","DOI":"10.1186\/s40965\u2010019\u20100067\u2010x"},{"key":"e_1_2_10_36_1","doi-asserted-by":"publisher","DOI":"10.1109\/JSTARS.2025.3581499"},{"key":"e_1_2_10_37_1","doi-asserted-by":"publisher","DOI":"10.3390\/land14101978"},{"issue":"2","key":"e_1_2_10_38_1","first-page":"301","article-title":"The Third Criterion: Compactness as a Procedural Safeguard Against Partisan Gerrymandering","volume":"9","author":"Polsby D. D.","year":"1991","journal-title":"Yale Law & Policy Review"},{"key":"e_1_2_10_39_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.jag.2023.103300"},{"key":"e_1_2_10_40_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-540-72849-8_72"},{"key":"e_1_2_10_41_1","doi-asserted-by":"publisher","DOI":"10.1080\/13658816.2026.2613347"},{"key":"e_1_2_10_42_1","doi-asserted-by":"publisher","DOI":"10.3390\/ijgi8010035"},{"key":"e_1_2_10_43_1","doi-asserted-by":"publisher","DOI":"10.3390\/ijgi12040143"},{"key":"e_1_2_10_44_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.compenvurbsys.2024.102076"},{"key":"e_1_2_10_45_1","doi-asserted-by":"publisher","DOI":"10.1038\/s41598\u2010023\u201034379\u20102"},{"key":"e_1_2_10_46_1","doi-asserted-by":"publisher","DOI":"10.1080\/17538947.2024.2392832"},{"key":"e_1_2_10_47_1","doi-asserted-by":"publisher","DOI":"10.1080\/13658816.2021.2023158"},{"key":"e_1_2_10_48_1","doi-asserted-by":"publisher","DOI":"10.1080\/13658816.2017.1395883"},{"key":"e_1_2_10_49_1","doi-asserted-by":"publisher","DOI":"10.1080\/17538947.2022.2159550"}],"container-title":["Transactions in GIS"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/pdf\/10.1111\/tgis.70227","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/full-xml\/10.1111\/tgis.70227","content-type":"application\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/pdf\/10.1111\/tgis.70227","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,6,23]],"date-time":"2026-06-23T13:06:38Z","timestamp":1782219998000},"score":1,"resource":{"primary":{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/10.1111\/tgis.70227"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,3,8]]},"references-count":48,"journal-issue":{"issue":"2","published-print":{"date-parts":[[2026,4]]}},"alternative-id":["10.1111\/tgis.70227"],"URL":"https:\/\/doi.org\/10.1111\/tgis.70227","archive":["Portico"],"relation":{},"ISSN":["1361-1682","1467-9671"],"issn-type":[{"value":"1361-1682","type":"print"},{"value":"1467-9671","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,3,8]]},"assertion":[{"value":"2026-01-08","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2026-02-20","order":2,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2026-03-08","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}],"article-number":"e70227"}}