{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,16]],"date-time":"2026-07-16T07:03:56Z","timestamp":1784185436604,"version":"3.55.0"},"reference-count":37,"publisher":"Springer Science and Business Media LLC","issue":"2","license":[{"start":{"date-parts":[[2026,4,1]],"date-time":"2026-04-01T00:00:00Z","timestamp":1775001600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2026,5,4]],"date-time":"2026-05-04T00:00:00Z","timestamp":1777852800000},"content-version":"vor","delay-in-days":33,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"funder":[{"DOI":"10.13039\/100007397","name":"Charles University","doi-asserted-by":"crossref","id":[{"id":"10.13039\/100007397","id-type":"DOI","asserted-by":"crossref"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["J Geogr Syst"],"published-print":{"date-parts":[[2026,4]]},"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:p>This study evaluates geographically weighted (GW) machine-learning models and, for the first time, introduces and empirically assesses spatially multiscale geographically weighted (SM-GW) models, in which kernel bandwidths vary by location. We compare Linear Regression, Random Forest, Support Vector Machines, and Extreme Gradient Boosting in global form, with single-bandwidth GW variants and SM-GW extensions, using 135 synthetic datasets that systematically vary spatial autocorrelation, relationship complexity, and the magnitude and form of spatial non-stationarity. Results show that single-bandwidth GW models consistently outperform global baselines when spatial dependence and non-stationarity are pronounced, with the largest gains observed for Linear Regression under moderate nonlinearity and high autocorrelation. Random Forest, Support Vector Machines, and Extreme Gradient Boosting also benefit from spatial weighting, though their inherent flexibility limits improvement. Adding geographic coordinates to global models proves unreliable and often degrades accuracy. SM-GW models do not consistently exceed single bandwidth formulations due to instability from isotropic neighborhoods, local bandwidth variance, and interpolation effects. However, SM-GW bandwidth surfaces provide valuable diagnostic insight into spatial variation in interaction scales. Overall, single-bandwidth GW models offer the most robust balance between accuracy and stability, while SM-GW models extend the methodological toolkit by making spatial scale variation explicit.<\/jats:p>","DOI":"10.1007\/s10109-026-00493-8","type":"journal-article","created":{"date-parts":[[2026,5,4]],"date-time":"2026-05-04T06:40:49Z","timestamp":1777876849000},"page":"243-279","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Efficiency of spatially multiscale machine learning models in addressing spatial non-stationarity and enhancing predictive accuracy"],"prefix":"10.1007","volume":"28","author":[{"given":"Daniel","family":"Bic\u00e1k","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Luk\u00e1\u0161","family":"Brodsk\u00fd","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,5,4]]},"reference":[{"issue":"12","key":"493_CR1","doi-asserted-by":"publisher","first-page":"6999","DOI":"10.1021\/acs.est.7b00891","volume":"51","author":"J Apte","year":"2017","unstructured":"Apte J, Messier K, Gani S, Brauer M, Kirchstetter T, Lunden M, Marshall J, Portier C, Vermeulen R, Hamburg S (2017) High-resolution air pollution mapping with google street view cars: exploiting big data. Environ Sci Technol 51(12):6999\u20137008","journal-title":"Environ Sci Technol"},{"issue":"4","key":"493_CR5","doi-asserted-by":"publisher","first-page":"281","DOI":"10.1111\/j.1538-4632.1996.tb00936.x","volume":"28","author":"C Brunsdon","year":"1996","unstructured":"Brunsdon C, Fotheringham AS, Charlton ME (1996) Geographically weighted regression: a method for exploring spatial nonstationarity. Geogr Anal 28(4):281\u2013298. https:\/\/doi.org\/10.1111\/j.1538-4632.1996.tb00936.x","journal-title":"Geogr Anal"},{"issue":"3","key":"493_CR6","doi-asserted-by":"publisher","first-page":"497","DOI":"10.1111\/0022-4146.00146","volume":"39","author":"C Brunsdon","year":"1999","unstructured":"Brunsdon C, Fotheringham AS, Charlton M (1999) Some notes on parametric significance tests for geographically weighted regression. J Reg Sci 39(3):497\u2013524. https:\/\/doi.org\/10.1111\/0022-4146.00146","journal-title":"J Reg Sci"},{"key":"493_CR7","unstructured":"Camnugent 2017. California housing prices. Kaggle. https:\/\/www.kaggle.com\/datasets\/camnugent\/california-housing-prices"},{"key":"493_CR8","doi-asserted-by":"publisher","DOI":"10.1007\/s10109-024-00452-1","author":"K Credit","year":"2024","unstructured":"Credit K (2024) Introduction to the special issue on spatial machine learning. J Geogr Syst. https:\/\/doi.org\/10.1007\/s10109-024-00452-1","journal-title":"J Geogr Syst"},{"key":"493_CR10","doi-asserted-by":"publisher","first-page":"74","DOI":"10.1590\/0037-8682-0307-2015","volume":"49","author":"M Duarte-Cunha","year":"2016","unstructured":"Duarte-Cunha M, Almeida ASD, Cunha GMD, Souza-Santos R (2016) Geographic weighted regression: applicability to epidemiological studies of leprosy. Rev Soc Bras Med Trop 49:74\u201382. https:\/\/doi.org\/10.1590\/0037-8682-0307-2015","journal-title":"Rev Soc Bras Med Trop"},{"key":"493_CR11","volume-title":"Geographically weighted regression: the analysis of spatially varying relationships","author":"AS Fotheringham","year":"2002","unstructured":"Fotheringham AS, Brunsdon C, Charlton M (2002) Geographically weighted regression: the analysis of spatially varying relationships. John Wiley & Sons"},{"issue":"4","key":"493_CR12","doi-asserted-by":"publisher","first-page":"431","DOI":"10.1111\/gean.12071","volume":"47","author":"AS Fotheringham","year":"2015","unstructured":"Fotheringham AS, Crespo R, Yao J (2015) Geographical and temporal weighted regression (GTWR). Geogr Anal 47(4):431\u2013452. https:\/\/doi.org\/10.1111\/gean.12071","journal-title":"Geogr Anal"},{"issue":"6","key":"493_CR13","doi-asserted-by":"publisher","first-page":"1247","DOI":"10.1080\/24694452.2017.1352480","volume":"107","author":"AS Fotheringham","year":"2017","unstructured":"Fotheringham AS, Yang W, Kang W (2017) Multiscale geographically weighted regression (MGWR). Ann Am Assoc Geogr 107(6):1247\u20131265. https:\/\/doi.org\/10.1080\/24694452.2017.1352480","journal-title":"Ann Am Assoc Geogr"},{"key":"493_CR14","doi-asserted-by":"publisher","DOI":"10.1201\/9781003435464","volume-title":"Multiscale geographically weighted regression: theory and practice","author":"AS Fotheringham","year":"2024","unstructured":"Fotheringham AS, Oshan TM, Li Z (2024) Multiscale geographically weighted regression: theory and practice. CRC Press. https:\/\/doi.org\/10.1201\/9781003435464"},{"issue":"2","key":"493_CR15","doi-asserted-by":"publisher","first-page":"113","DOI":"10.1111\/j.1538-4632.2000.tb00420.x","volume":"32","author":"M Gahegan","year":"2000","unstructured":"Gahegan M (2000) On the application of inductive machine learning tools to geographical analysis. Geogr Anal 32(2):113\u2013139. https:\/\/doi.org\/10.1111\/j.1538-4632.2000.tb00420.x","journal-title":"Geogr Anal"},{"issue":"9","key":"493_CR16","doi-asserted-by":"publisher","DOI":"10.3390\/ijgi11090471","volume":"11","author":"S Georganos","year":"2022","unstructured":"Georganos S, Kalogirou S (2022) A forest of forests: a spatially weighted and computationally efficient formulation of geographical random forests. ISPRS Int J Geo-Inf 11(9):471. https:\/\/doi.org\/10.3390\/ijgi11090471","journal-title":"ISPRS Int J Geo-Inf"},{"issue":"2","key":"493_CR17","doi-asserted-by":"publisher","first-page":"121","DOI":"10.1080\/10106049.2019.1595177","volume":"36","author":"S Georganos","year":"2021","unstructured":"Georganos S, Grippa T, Niang Gadiaga A, Linard C, Lennert M, Vanhuysse S, Kalogirou S (2021) Geographical random forests: a spatial extension of the random forest algorithm to address spatial heterogeneity in remote sensing and population modelling. Geocarto Int 36(2):121\u2013136. https:\/\/doi.org\/10.1080\/10106049.2019.1595177","journal-title":"Geocarto Int"},{"key":"493_CR18","doi-asserted-by":"publisher","first-page":"244","DOI":"10.1016\/j.compenvurbsys.2018.10.008","volume":"74","author":"G Grekousis","year":"2019","unstructured":"Grekousis G (2019) Artificial neural networks and deep learning in urban geography: a systematic review and meta-analysis. Comput Environ Urban Syst 74:244\u2013256. https:\/\/doi.org\/10.1016\/j.compenvurbsys.2018.10.008","journal-title":"Comput Environ Urban Syst"},{"key":"493_CR19","doi-asserted-by":"publisher","first-page":"169","DOI":"10.1007\/s10109-025-00465-4","volume":"27","author":"G Grekousis","year":"2025","unstructured":"Grekousis G (2025) Geographical-XGBoost: a new ensemble model for spatially local regression based on gradient-boosted trees. J Geogr Syst 27:169\u2013195. https:\/\/doi.org\/10.1007\/s10109-025-00465-4","journal-title":"J Geogr Syst"},{"key":"493_CR20","doi-asserted-by":"publisher","DOI":"10.1016\/j.healthplace.2022.102744","volume":"74","author":"G Grekousis","year":"2022","unstructured":"Grekousis G, Feng Z, Marakakis I, Lu Y, Wang R (2022) Ranking the importance of demographic, socioeconomic, and underlying health factors on US COVID-19 deaths: a geographical random forest approach. Health Place 74:102744. https:\/\/doi.org\/10.1016\/j.healthplace.2022.102744","journal-title":"Health Place"},{"issue":"2","key":"493_CR21","doi-asserted-by":"publisher","first-page":"215","DOI":"10.1080\/13658816.2021.1871618","volume":"36","author":"J Hagenauer","year":"2022","unstructured":"Hagenauer J, Helbich M (2022) A geographically weighted artificial neural network. Int J Geogr Inf Sci 36(2):215\u2013235. https:\/\/doi.org\/10.1080\/13658816.2021.1871618","journal-title":"Int J Geogr Inf Sci"},{"key":"493_CR22","doi-asserted-by":"publisher","DOI":"10.7717\/peerj.5518","volume":"6","author":"T Hengl","year":"2018","unstructured":"Hengl T, Nussbaum M, Wright MN, Heuvelink GB, Gr\u00e4ler B (2018) Random forest as a generic framework for predictive modeling of spatial and spatio-temporal variables. PeerJ 6:e5518. https:\/\/doi.org\/10.7717\/peerj.5518","journal-title":"PeerJ"},{"key":"493_CR23","doi-asserted-by":"publisher","first-page":"356","DOI":"10.14311\/CEJ.2023.03.0027","volume":"33","author":"S Ibrahim","year":"2023","unstructured":"Ibrahim S, Halounov\u00e1 L, Matou\u0161kov\u00e1 E, Brodsk\u00fd L, Landa M (2023) PM2.5 Estimation in the Czech republic using extremely randomized trees: a comprehensive data analysis. Stavebn\u00ed Obzor - Civil Eng J 33:356\u2013369. https:\/\/doi.org\/10.14311\/CEJ.2023.03.0027","journal-title":"Stavebn\u00ed Obzor - Civil Eng J"},{"issue":"4","key":"493_CR24","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3337798","volume":"10","author":"Z Jiang","year":"2019","unstructured":"Jiang Z, Sainju AM, Li Y, Shekhar S, Knight J (2019) Spatial ensemble learning for heterogeneous geographic data with class ambiguity. ACM Trans Intell Syst Technol 10(4):1\u201325. https:\/\/doi.org\/10.1145\/3337798","journal-title":"ACM Trans Intell Syst Technol"},{"key":"493_CR25","doi-asserted-by":"publisher","first-page":"399","DOI":"10.1007\/s10109-025-00468-1","volume":"27","author":"W Kang","year":"2025","unstructured":"Kang W, Oshan MT (2025) Scale and correlation in multiscale geographically weighted regression (MGWR). J Geogr Syst 27:399\u2013424. https:\/\/doi.org\/10.1007\/s10109-025-00468-1","journal-title":"J Geogr Syst"},{"issue":"5","key":"493_CR26","doi-asserted-by":"publisher","DOI":"10.1111\/gec3.12563","volume":"15","author":"A Lavallin","year":"2021","unstructured":"Lavallin A, Downs JA (2021) Machine learning in geography\u2013past, present, and future. Geogr Compass 15(5):e12563. https:\/\/doi.org\/10.1111\/gec3.12563","journal-title":"Geogr Compass"},{"issue":"7","key":"493_CR27","doi-asserted-by":"publisher","DOI":"10.3390\/ijgi11070385","volume":"11","author":"W Li","year":"2022","unstructured":"Li W, Hsu CY (2022) GeoAI for large-scale image analysis and machine vision: Recent progress of artificial intelligence in geography. ISPRS Int J Geo-Inf 11(7):385. https:\/\/doi.org\/10.3390\/ijgi11070385","journal-title":"ISPRS Int J Geo-Inf"},{"key":"493_CR28","doi-asserted-by":"publisher","DOI":"10.1016\/j.scitotenv.2020.141549","volume":"748","author":"G Li","year":"2020","unstructured":"Li G, Fang C, He S (2020a) The influence of environmental efficiency on PM2.5 pollution: evidence from 283 Chinese prefecture-level cities. Sci Total Environ 748:141549. https:\/\/doi.org\/10.1016\/j.scitotenv.2020.141549","journal-title":"Sci Total Environ"},{"issue":"3","key":"493_CR29","doi-asserted-by":"publisher","DOI":"10.3390\/app10031107","volume":"10","author":"Y Li","year":"2020","unstructured":"Li Y, Liu X, Han Z, Dou J (2020b) Spatial proximity-based geographically weighted regression model for landslide susceptibility assessment: a case study of Qingchuan area, China. Appl Sci Basel 10(3):1107. https:\/\/doi.org\/10.3390\/app10031107","journal-title":"Appl Sci Basel"},{"issue":"2","key":"493_CR30","doi-asserted-by":"publisher","first-page":"131","DOI":"10.2747\/1548-1603.45.2.131","volume":"45","author":"CP Lo","year":"2008","unstructured":"Lo CP (2008) Population estimation using geographically weighted regression. Gisci Remote Sens 45(2):131\u2013148","journal-title":"Gisci Remote Sens"},{"key":"493_CR31","doi-asserted-by":"publisher","first-page":"142","DOI":"10.1007\/978-3-319-92099-3_17","volume-title":"New metropolitan perspectives: local knowledge and innovation dynamics towards territory attractiveness through the implementation of Horizon\/E2020\/Agenda2030","author":"DE Massimo","year":"2019","unstructured":"Massimo DE, Del Giudice V, De Paola P, Forte F, Musolino M, Malerba A (2019) Geographically weighted regression for the post carbon city and real estate market analysis: a case study. New metropolitan perspectives: local knowledge and innovation dynamics towards territory attractiveness through the implementation of Horizon\/E2020\/Agenda2030. Springer International Publishing, pp 142\u2013149. https:\/\/doi.org\/10.1007\/978-3-319-92099-3_17"},{"issue":"8","key":"493_CR32","doi-asserted-by":"publisher","first-page":"1246","DOI":"10.2113\/gsecongeo.58.8.1246","volume":"58","author":"G Matheron","year":"1963","unstructured":"Matheron G (1963) Principles of geostatistics. Econ Geol 58(8):1246\u20131266","journal-title":"Econ Geol"},{"key":"493_CR33","doi-asserted-by":"publisher","DOI":"10.1016\/j.scitotenv.2020.138884","author":"A Mollalo","year":"2020","unstructured":"Mollalo A, Vahedi B, Rivera MK (2020) GIS-based spatial modeling of COVID-19 incidence rate in the continental United States. Sci Total Environ. https:\/\/doi.org\/10.1016\/j.scitotenv.2020.138884","journal-title":"Sci Total Environ"},{"issue":"3","key":"493_CR34","doi-asserted-by":"publisher","first-page":"294","DOI":"10.1080\/24751839.2019.1565653","volume":"3","author":"F Muharemi","year":"2019","unstructured":"Muharemi F, Logof\u0103tu D, Leon F (2019) Machine learning approaches for anomaly detection of water quality on a real-world data set. J Inf Telecommun 3(3):294\u2013307. https:\/\/doi.org\/10.1080\/24751839.2019.1565653","journal-title":"J Inf Telecommun"},{"key":"493_CR35","doi-asserted-by":"publisher","first-page":"82","DOI":"10.1016\/j.jag.2011.12.013","volume":"18","author":"P Propastin","year":"2012","unstructured":"Propastin P (2012) Modifying geographically weighted regression for estimating aboveground biomass in tropical rainforests by multispectral remote sensing data. Int J Appl Earth Obs Geoinf 18:82\u201390. https:\/\/doi.org\/10.1016\/j.jag.2011.12.013","journal-title":"Int J Appl Earth Obs Geoinf"},{"key":"493_CR37","doi-asserted-by":"publisher","first-page":"351","DOI":"10.1007\/s10708-015-9626-6","volume":"81","author":"R Stein","year":"2016","unstructured":"Stein R, Conley JF, Davis C (2016) The differential impact of physical disorder and collective efficacy: A geographically weighted regression on violent crime. GeoJournal 81:351\u2013365. https:\/\/doi.org\/10.1007\/s10708-015-9626-6","journal-title":"GeoJournal"},{"key":"493_CR39","doi-asserted-by":"publisher","DOI":"10.1038\/s40494-025-01938-x","volume":"13","author":"F Wang","year":"2025","unstructured":"Wang F, Zhang T, Zhang S (2025) MGWR reveals scale heterogeneity shaping intangible cultural heritage distribution in China. Npj Herit Sci 13:367. https:\/\/doi.org\/10.1038\/s40494-025-01938-x","journal-title":"Npj Herit Sci"},{"issue":"2","key":"493_CR40","doi-asserted-by":"publisher","first-page":"213","DOI":"10.1007\/s10109-022-00387-5","volume":"25","author":"W Yang","year":"2023","unstructured":"Yang W, Deng M, Tang J, Luo L (2023) Geographically weighted regression with the integration of machine learning for spatial prediction. J Geogr Syst 25(2):213\u2013236. https:\/\/doi.org\/10.1007\/s10109-022-00387-5","journal-title":"J Geogr Syst"},{"key":"493_CR41","doi-asserted-by":"publisher","first-page":"181302","DOI":"10.1109\/ACCESS.2020.3028420","volume":"8","author":"X Zhang","year":"2020","unstructured":"Zhang X, Liu L, Xiao L, Ji J (2020) Comparison of machine learning algorithms for predicting crime hotspots. IEEE Access 8:181302\u2013181310. https:\/\/doi.org\/10.1109\/ACCESS.2020.3028420","journal-title":"IEEE Access"},{"issue":"2","key":"493_CR42","doi-asserted-by":"publisher","first-page":"1703","DOI":"10.3390\/su15021703","volume":"15","author":"C Zhao","year":"2023","unstructured":"Zhao C, Wu Y, Chen Y, Chen G (2023) Multiscale effects of hedonic attributes on Airbnb listing prices based on MGWR: a case study of Beijing. China Sustain 15(2):1703. https:\/\/doi.org\/10.3390\/su15021703","journal-title":"China Sustain"},{"key":"493_CR43","doi-asserted-by":"publisher","first-page":"012006","DOI":"10.1088\/1742-6596\/2646\/1\/012006","volume-title":"Journal of physics: conference series (Vol. 2646, No. 1)","author":"T Zhou","year":"2023","unstructured":"Zhou T (2023) Application of artificial intelligence in geography. Journal of physics: conference series (Vol. 2646, No. 1). IOP Publishing, p 012006. https:\/\/doi.org\/10.1088\/1742-6596\/2646\/1\/012006"}],"container-title":["Journal of Geographical Systems"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10109-026-00493-8.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s10109-026-00493-8","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10109-026-00493-8.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,7,16]],"date-time":"2026-07-16T06:11:43Z","timestamp":1784182303000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s10109-026-00493-8"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,4]]},"references-count":37,"journal-issue":{"issue":"2","published-print":{"date-parts":[[2026,4]]}},"alternative-id":["493"],"URL":"https:\/\/doi.org\/10.1007\/s10109-026-00493-8","relation":{},"ISSN":["1435-5930","1435-5949"],"issn-type":[{"value":"1435-5930","type":"print"},{"value":"1435-5949","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,4]]},"assertion":[{"value":"26 March 2025","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"20 March 2026","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"4 May 2026","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"ChatGPT 5 was used in the writing of this article for stylistic and grammar correction purposes only.","order":1,"name":"Ethics","label":"Generative artificial intelligence (AI)","group":{"name":"EthicsHeading","label":"Declarations"}}]}}