[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-123194-en":3,"doc-seo-123194-105":30,"detail-sidebar-cat-0-en-105":91},{"code":4,"msg":5,"data":6},0,"success",{"doc_id":7,"user_id":8,"nickname":9,"user_avatar":10,"doc_module":4,"category_id":11,"category_name":12,"doc_title":13,"doc_description":14,"doc_content":15,"file_id":16,"file_url":17,"file_type":18,"file_size":19,"view_count":4,"is_deleted":4,"is_public":20,"is_downloadable":20,"audit_status":20,"page_count":21,"language":22,"language_code":23,"site_id":24,"html_lang":23,"table_of_contents":25,"faqs":26,"seo_title":27,"seo_description":14,"update_tm":28,"read_time":29},123194,13056703019404,"Miles","https://ap-avatar.wpscdn.com/davatar_29158cc5080c5b710cf443261637dec0",8,"Research & Report","Indoor radon interval prediction in the Swedish building stock using machine learning","Indoor radon poses a health hazard to building occupants, yet Sweden has a low indoor radon measurement rate due to limited mandatory requirements. Large-scale assessment is challenging, so data-driven machine learning is used to estimate indoor radon exposure across the Swedish building stock. XGBoost and deep neural network models are trained using indoor radon measurements, property registers, and geogenic information, then evaluated via macro-F1 and transferred to metropolitan building registers.","Building and Environment 245 (2023) 110879  \nContents lists available at ScienceDirect Building and Environment  \njournal [homepage: www.elsevier.com/locate/buildenv](homepage: www.elsevier.com/locate/buildenv)  \n| Indoor radon interval prediction in the Swedish building stock using machine learning |  |  |  |\n| --- | --- | --- | --- |\n| Pei-Yu Wu a, b, *, Tim Johansson a, Claes Sandels a, Mikael Mangold a, Kristina Mj¨ornell a, b\u003Cbr>a RISE Research Institutes of Sweden, 412 58, Gothenburg, Sweden\u003Cbr>b Department of Building and Environmental Technology, Faculty of Engineering, Lund University, 221 00, Lund, Sweden |  |  |  |\n| A R T I C L E I N F O |  | A B S T R A C T |  |\n| Keywords:\u003Cbr>Indoor radon\u003Cbr>Predictive modeling XGBoost\u003Cbr>Deep learning\u003Cbr>Radon exposure estimation Regional building stock |  | Indoor radon represents a health hazard for occupants. However, the indoor radon measurement rate is low in Sweden because of no mandatory requirements. Measuring indoor radon on an urban scale is complicated, machine learning exploiting existing data for pattern identification provides a cost-efficient approach to estimate indoor radon exposure in the building stock. Extreme gradient boosting (XGBoost) models and deep neural network (DNN) models were developed based on indoor radon measurement records, property registers, and geogenic information. The XGBoost models showed promising results in predicting indoor radon intervals for different types of buildings with macro-F1 between 0.93 and 0.96, whereas the DNN models attained macro-F1 between 0.64 and 0.74. After that, the XGBoost models trained on the national indoor radon dataset were transferred to fit building registers in metropolitan regions to estimate the indoor radon intervals in nonmeasured and measured buildings by regions and building classes. By comparing the prediction results and the statistical summary of indoor radon intervals in measured buildings, the model uncertainty and validity were determined. The study ascertains the prediction performance of machine learning models in classifying indoor radon intervals and discusses the benefits and limitations of the data-driven approach. The research outcomes can assist preliminary large-scale indoor radon distribution estimation for relevant authorities and guide onsite measurements for prioritized building stock prone to indoor radon exposure. |  |\n\n1. Introduction  \nIndoor radon is a universal health hazard and the second leading cause of lung cancer worldwide. Approximately 15% of lung cancers in Sweden are induced by indoor radon in dwelling buildings, corresponding to 500 lung cancer cases every year [1,2]. The exposure to residential radon is particularly severe in cold climates, given the longtime spent indoors in buildings with insufficient ventilation. To address the health risk of indoor radon and monitor its exposure in the indoor environment, most European countries adopt three indoor radon reference thresholds: (i) 200 Bq/m3 for residential and public buildings and as the highest acceptable level for new buildings, (ii) 400 Bq/m3 for existing buildings, (iii) above 1,000 Bq/m3 for immediate decontamination [3]. From available measurement records, it is estimated that around 16% of single-family houses and 19% of workplaces exceed the indoor radon reference level in the Swedish building stock [2]. No requirements on the measured frequency have been put in place  \nnowadays; measurements are, however, recommended every ten years or after an extensive renovation that may affect the indoor radon concentration. For buildings whose indoor radon concentrations exceed the reference limit of 200 Bq/m3, their indoor radon sources must be identified before decontamination. The indoor radon measurements andremediation are the responsibility of property owners and are supervised by the county’s and municipality’s environmental and health protection committees.  \nIn light of the new Swedish National Action Plan [","cbCaiugUrOE6Tbmx","https://ap.wps.com/l/cbCaiugUrOE6Tbmx","pdf",7168817,1,13,"English","en",105,"# Introduction\n## Health impact and reference thresholds\n## Measurement practices and data sources\n## Prior studies on radon concentrations","[{\"question\":\"Why is estimating indoor radon exposure across the Swedish building stock difficult?\",\"answer\":\"Indoor radon measurement frequency in Sweden is low because mandatory requirements are limited, and urban-scale measurement is complicated.\"},{\"question\":\"What machine learning models are used for indoor radon interval prediction?\",\"answer\":\"The study develops Extreme Gradient Boosting (XGBoost) models and deep neural network (DNN) models using measurement records, property registers, and geogenic information.\"},{\"question\":\"How were the models evaluated and applied beyond the national dataset?\",\"answer\":\"XGBoost performance is assessed using macro-F1 for different building types, and models trained on the national dataset are transferred to metropolitan building registers to estimate radon intervals for measured and nonmeasured buildings by region and building class.\"}]","Indoor radon interval prediction in the Swedish building stock using machine learning | PDF",1785815142,33,{"code":4,"msg":31,"data":32},"ok",{"site_id":24,"language":23,"slug":33,"title":13,"keywords":34,"description":14,"schema_data":35,"social_meta":86,"head_meta":88,"extra_data":90,"updated_unix":28},"indoor-radon-interval-prediction-in-the-swedish-building-stock-using-machine-learning","",{"@graph":36,"@context":85},[37,54,68],{"@type":38,"itemListElement":39},"BreadcrumbList",[40,44,48,51],{"item":41,"name":42,"@type":43,"position":20},"https://docshare.wps.com","Home","ListItem",{"item":45,"name":46,"@type":43,"position":47},"https://docshare.wps.com/document/","Document",2,{"item":49,"name":12,"@type":43,"position":50},"https://docshare.wps.com/document/research-report/",3,{"item":52,"name":13,"@type":43,"position":53},"https://docshare.wps.com/document/indoor-radon-interval-prediction-in-the-swedish-building-stock-using-machine-learning/123194/",4,{"url":52,"name":13,"@type":55,"author":56,"headline":13,"publisher":58,"fileFormat":61,"inLanguage":23,"description":14,"dateModified":62,"datePublished":62,"encodingFormat":61,"isAccessibleForFree":63,"interactionStatistic":64},"DigitalDocument",{"name":9,"@type":57},"Person",{"url":41,"name":59,"@type":60},"DocShare","Organization","application/pdf","2026-08-04",true,{"@type":65,"interactionType":66,"userInteractionCount":4},"InteractionCounter",{"@type":67},"ViewAction",{"@type":69,"mainEntity":70},"FAQPage",[71,77,81],{"name":72,"@type":73,"acceptedAnswer":74},"Why is estimating indoor radon exposure across the Swedish building stock difficult?","Question",{"text":75,"@type":76},"Indoor radon measurement frequency in Sweden is low because mandatory requirements are limited, and urban-scale measurement is complicated.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"What machine learning models are used for indoor radon interval prediction?",{"text":80,"@type":76},"The study develops Extreme Gradient Boosting (XGBoost) models and deep neural network (DNN) models using measurement records, property registers, and geogenic information.",{"name":82,"@type":73,"acceptedAnswer":83},"How were the models evaluated and applied beyond the national dataset?",{"text":84,"@type":76},"XGBoost performance is assessed using macro-F1 for different building types, and models trained on the national dataset are transferred to metropolitan building registers to estimate radon intervals for measured and nonmeasured buildings by region and building class.","https://schema.org",{"og:url":52,"og:type":87,"og:title":13,"og:site_name":59,"og:description":14},"article",{"robots":89,"canonical":52},"index,follow",{"doc_id":7,"site_id":24},{"code":4,"msg":5,"data":92},[93,97,101,105,110,115,120,123,128,131,135],{"id":20,"doc_module":4,"doc_module_name":46,"category_name":94,"show_sort_weight":95,"slug":96},"Story & Novel",90,"story-novel",{"id":47,"doc_module":4,"doc_module_name":46,"category_name":98,"show_sort_weight":99,"slug":100},"Literature",80,"literature",{"id":53,"doc_module":4,"doc_module_name":46,"category_name":102,"show_sort_weight":103,"slug":104},"Exam",70,"exam",{"id":106,"doc_module":4,"doc_module_name":46,"category_name":107,"show_sort_weight":108,"slug":109},5,"Comic",60,"comic",{"id":111,"doc_module":4,"doc_module_name":46,"category_name":112,"show_sort_weight":113,"slug":114},6,"Technology",50,"technology",{"id":116,"doc_module":4,"doc_module_name":46,"category_name":117,"show_sort_weight":118,"slug":119},7,"Healthcare",40,"healthcare",{"id":11,"doc_module":4,"doc_module_name":46,"category_name":12,"show_sort_weight":121,"slug":122},30,"research-report",{"id":124,"doc_module":4,"doc_module_name":46,"category_name":125,"show_sort_weight":126,"slug":127},9,"Religion & Spirituality",20,"religion-spirituality",{"id":126,"doc_module":4,"doc_module_name":46,"category_name":129,"show_sort_weight":126,"slug":130},"World Cup","world-cup",{"id":132,"doc_module":4,"doc_module_name":46,"category_name":133,"show_sort_weight":132,"slug":134},10,"Lifestyle","lifestyle",{"id":136,"doc_module":4,"doc_module_name":46,"category_name":137,"show_sort_weight":106,"slug":138},19,"General","general"]