[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-seo-290832-105":3,"detail-sidebar-cat-0-en-105":81,"doc-detail-290832-en":130},{"code":4,"msg":5,"data":6},0,"ok",{"site_id":7,"language":8,"slug":9,"title":10,"keywords":11,"description":12,"schema_data":13,"social_meta":74,"head_meta":76,"extra_data":78,"updated_unix":80},105,"en","traffic-noise-assessment-in-urban-bulgaria-using-explainable-machine-learning","Traffic noise assessment in urban Bulgaria using explainable machine learning","","Fine-grained noise maps are vital for epidemiological studies on traffic noise, yet detailed data are often limited, especially in Eastern Europe. This work compares supervised machine-learning models to predict traffic noise levels across Bulgaria’s five largest cities using in situ A-weighted equivalent continuous sound levels from 232 fixed-site monitors. Transport- and land-use predictors were built with 50–1,000 m buffers. Extreme gradient boosting achieved the best cross-validated fit (R²=0.680) and lowest RMSE (4.739), with Shapley explanations identifying key non-linear drivers and revealing that 96.8% of the urban population experiences harmful noise.",{"@graph":14,"@context":73},[15,34,56],{"@type":16,"itemListElement":17},"BreadcrumbList",[18,23,27,31],{"item":19,"name":20,"@type":21,"position":22},"https://docshare.wps.com","Home","ListItem",1,{"item":24,"name":25,"@type":21,"position":26},"https://docshare.wps.com/document/","Document",2,{"item":28,"name":29,"@type":21,"position":30},"https://docshare.wps.com/document/research-report/","Research & Report",3,{"item":32,"name":10,"@type":21,"position":33},"https://docshare.wps.com/document/traffic-noise-assessment-in-urban-bulgaria-using-explainable-machine-learning/290832/",4,{"url":32,"name":10,"@type":35,"image":36,"author":41,"headline":10,"publisher":44,"fileFormat":47,"inLanguage":8,"description":12,"dateModified":48,"datePublished":49,"encodingFormat":47,"isAccessibleForFree":50,"interactionStatistic":51},"DigitalDocument",{"url":37,"@type":38,"width":39,"height":40},"https://docshare.wps.com/thumbnails/traffic-noise-assessment-in-urban-bulgaria-using-explainable-machine-learning/290832.png","ImageObject",300,407,{"name":42,"@type":43},"Skyler","Person",{"url":19,"name":45,"@type":46},"DocShare","Organization","application/pdf","2026-10-24","2026-09-17",true,{"@type":52,"interactionType":53,"userInteractionCount":55},"InteractionCounter",{"@type":54},"ViewAction",9,{"@type":57,"mainEntity":58},"FAQPage",[59,65,69],{"name":60,"@type":61,"acceptedAnswer":62},"Which supervised machine-learning models were compared for traffic noise prediction?","Question",{"text":63,"@type":64},"The study compared extreme gradient boosting (XGB), random forest, support vector regression, elastic net, and linear regression models for predicting traffic noise levels.","Answer",{"name":66,"@type":61,"acceptedAnswer":67},"How was the noise data collected and what was the geographic scope?",{"text":68,"@type":64},"A-weighted equivalent continuous sound levels were measured in situ using 232 fixed-site monitors across the five largest Bulgarian cities.",{"name":70,"@type":61,"acceptedAnswer":71},"What did the Shapley values for XGB reveal about important predictors?",{"text":72,"@type":64},"Shapley values indicated that major road length within 100 m buffers, footways within 50 m buffers, residential roads within 50 m buffers, and the number of buildings within 50 m buffers were important non-linear predictors.","https://schema.org",{"og:url":32,"og:type":75,"og:title":10,"og:site_name":45,"og:description":12},"article",{"robots":77,"canonical":32},"index,follow",{"doc_id":79,"site_id":7},290832,1789642698,{"code":4,"msg":82,"data":83},"success",[84,88,92,96,101,106,111,115,119,122,126],{"id":22,"doc_module":4,"doc_module_name":25,"category_name":85,"show_sort_weight":86,"slug":87},"Story & Novel",90,"story-novel",{"id":26,"doc_module":4,"doc_module_name":25,"category_name":89,"show_sort_weight":90,"slug":91},"Literature",80,"literature",{"id":33,"doc_module":4,"doc_module_name":25,"category_name":93,"show_sort_weight":94,"slug":95},"Exam",70,"exam",{"id":97,"doc_module":4,"doc_module_name":25,"category_name":98,"show_sort_weight":99,"slug":100},5,"Comic",60,"comic",{"id":102,"doc_module":4,"doc_module_name":25,"category_name":103,"show_sort_weight":104,"slug":105},6,"Technology",50,"technology",{"id":107,"doc_module":4,"doc_module_name":25,"category_name":108,"show_sort_weight":109,"slug":110},7,"Healthcare",40,"healthcare",{"id":112,"doc_module":4,"doc_module_name":25,"category_name":29,"show_sort_weight":113,"slug":114},8,30,"research-report",{"id":55,"doc_module":4,"doc_module_name":25,"category_name":116,"show_sort_weight":117,"slug":118},"Religion & Spirituality",20,"religion-spirituality",{"id":117,"doc_module":4,"doc_module_name":25,"category_name":120,"show_sort_weight":117,"slug":121},"World Cup","world-cup",{"id":123,"doc_module":4,"doc_module_name":25,"category_name":124,"show_sort_weight":123,"slug":125},10,"Lifestyle","lifestyle",{"id":127,"doc_module":4,"doc_module_name":25,"category_name":128,"show_sort_weight":97,"slug":129},19,"General","general",{"code":4,"msg":82,"data":131},{"doc_id":79,"user_id":132,"nickname":42,"user_avatar":133,"doc_module":4,"category_id":112,"category_name":29,"doc_title":10,"doc_description":12,"doc_content":134,"file_id":135,"file_url":136,"file_type":137,"file_size":138,"view_count":55,"is_deleted":4,"is_public":22,"is_downloadable":22,"audit_status":22,"page_count":139,"language":140,"language_code":8,"site_id":7,"html_lang":8,"table_of_contents":141,"faqs":142,"seo_title":143,"seo_description":12,"update_tm":80,"read_time":144,"preview_page_count":4},2336464648746,"https://ap-avatar.wpscdn.com/davatar_276721f389ce27ea32af1340a28f341c","Traffic noise assessment in urban Bulgaria using explainable machine learning  \nMarco Helbich1,2,3,\\#,$, Julian Hagenauer1,2,3,$, Angel Burov2,3,4, Angel M. Dzhambov2,3  \n1 Department of Human Geography and Spatial Planning, Faculty of Geosciences, Utrecht University, Utrecht, The Netherlands  \n2 Health and Quality of Life in a Green and Sustainable Environment Research Group, Strategic Research and Innovation Program for the Development of MU – Plovdiv, Medical University of Plovdiv, Plovdiv, Bulgaria  \n3 Environmental Health Division, Research Institute at Medical University of Plovdiv, Medical University of Plovdiv, Plovdiv, Bulgaria  \n4 Department of Urban Planning, Faculty of Architecture, University of Architecture, Civil Engineering and Geodesy, Sofia, Bulgaria  \n\\# Corresponding author, Princetonlaan 8a, 3584 CB Utrecht, The Netherlands, Tel.: (0031) 30 253 2017, [Email:](Email: m.helbich@uu.nl)[ ](Email: m.helbich@uu.nl)[m.helbich@uu.nl](Email: m.helbich@uu.nl)  \n$ Both authors contributed equally  \nAbstract  \nFine-grained noise maps are vital for epidemiological studies on traffic noise. However, detailed information on traffic noise is often limited, especially in Eastern Europe. Rigid linear noise land-use regressions are typically employed to estimate noise levels; however, machine learning likely offers more accurate noise predictions. We innovated by comparing the predictive accuracies of supervised machine  \nlearning models to estimate traffic noise levels across the five largest Bulgarian cities. In situ A-weighted equivalent continuous sound levels were obtained from 232 fixed-site monitors across these cities. We included transport-and land-use-related predictors using 50-1,000 m buffers. Extreme gradient boosting (XGB) had the highest ten-fold cross-validated fit (R²=0 . 680) and the lowest root mean square error (RMSE=4 . 739), insignificantly besting the random forest-based model (R ²=0 .667, RMSE=4 . 895) . Support vector regression (R ²=0 . 633, RMSE=5 . 358), elastic net (R ²=0 .568, RMSE=5 . 625), and linear regression (R ²=0 . 548, RMSE=5 .569) performed significantly worse. Shapley values for the XGB showed that the length of major roads within 100 m buffers, footways within 50 m buffers, residential roads within 50 m buffers, and the number of buildings within 50 m buffers were important non-linear predictors. Our spatially resolved noise maps revealed striking geographic noise variations and that, on average, 96.8% of the urban population experiences harmful noise levels.  \nKeywords: Traffic noise pollution; exposure assessment; land-use regression; machine learning; Shapley additive explanations; environmental monitoring  \n1 Introduction  \nTransport noise is a primary source of noise pollution (Mann and Singh, 2022) and an environmental stressor detrimental to human health (Welch et al., 2023; World Health Organization, 2018) . Meta-analyses have substantiated that excessive traffic noise exposure puts people at risk for non-auditory adverse health outcomes, including elevated annoyance (Guski et al., 2017), blood pressure (Chen et al., 2023), mental illness (Lan et al., 2020), and sleep disturbance (Smith et al., 2022) . Furthermore, urban noise is unevenly distributed (European Environment Agency, 2019), with some areas experiencing disproportionate burdens (Hayward and Helbich, 2024; Peris and Arguelles, 2023) . Approximately 20% of Europeans, predominantly in urban areas, are exposed to unhealthy noise concentrations of more than 55 decibels (dB) during the day-evening-night period (European Environment Agency, 2021) . In Bulgaria, the proportion is substantially worse, with 76% of urban inhabitants exposed to harmful road noise (European Environment Agency, 2024) .  \nMonitoring traffic noise across cities comprehensively is often infeasible because measurements are timeconsuming, expensive, and labor-intensive (Mann and Singh, 2022) . However, the European Environmental Noise Directive 2002/49/EC obligates countries ","cbCaiiyZq6FB8j9v","https://ap.wps.com/l/cbCaiiyZq6FB8j9v","pdf",1004367,35,"English","# Abstract\n## Models and data collection\n## Findings and explanations\n# 1 Introduction\n## Health impacts and population exposure\n## Monitoring constraints and directive requirements\n## Mapping approaches and limitations","[{\"question\":\"Which supervised machine-learning models were compared for traffic noise prediction?\",\"answer\":\"The study compared extreme gradient boosting (XGB), random forest, support vector regression, elastic net, and linear regression models for predicting traffic noise levels.\"},{\"question\":\"How was the noise data collected and what was the geographic scope?\",\"answer\":\"A-weighted equivalent continuous sound levels were measured in situ using 232 fixed-site monitors across the five largest Bulgarian cities.\"},{\"question\":\"What did the Shapley values for XGB reveal about important predictors?\",\"answer\":\"Shapley values indicated that major road length within 100 m buffers, footways within 50 m buffers, residential roads within 50 m buffers, and the number of buildings within 50 m buffers were important non-linear predictors.\"}]","Traffic noise assessment in urban Bulgaria using explainable machine learning | PDF",88]