[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-122157-en":3,"doc-seo-122157-105":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},122157,7971461740886,"Theodore","https://ap-avatar.wpscdn.com/davatar_3d24733baf745e90a7e4bdd5f77d97b2",8,"Research & Report","Machine Learning Techniques for the Prediction of Indoor Gamma-ray Dose Rates - Strengths, Weaknesses and implications for Epidemiology","We investigate machine-learning methods for estimating indoor gamma-ray dose rates at locations where measurements are unavailable. The approach extends earlier work by using broader modelling techniques and a larger set of explanatory variables, including detailed dwelling characteristics. Three machine-learning model types are applied alongside geostatistical, nearest-neighbour, and other traditional models. Predictions show significantly improved performance with consistent variable-class tendencies, though model outputs remain noisy and relative variable importance exhibits some instability. Predicted dose-range is narrower than measured values, implying reduced statistical power for epidemiological studies compared with direct measurements.","1 Machine Learning Techniques for the Prediction of Indoor Gamma-ray Dose Rates –  \n2 Strengths, Weaknesses and implications for Epidemiology  \n3  \n4 Word count: abstract 176 words, main text (excluding references, Tables, Figures) 10,141 words  \n5 67 references  \n6 7 Tables, 3 Figures  \n7 GM Kendalla, JD Appletonb, P Chernyavskiyc, A Arshamd, MP Littlee, f  \n8 aCancer Epidemiology Unit, NDPH, University of Oxford, Richard Doll Building, Old Road  \n9 Campus, Headington, Oxford OX3 7LF, UK  \n10 bBritish Geological Survey, Kingsley Dunham Centre, Nicker Hill, Keyworth, Nottingham NG12  \n11 5GG, UK  \n12 cDepartment of Public Health Sciences, University of Virginia School of Medicine, 13 Charlottesville VA 22908-0717, USA  \n14 dCenter for Data, Mathematical & Computational Sciences, Goucher College, Baltimore, 15 Maryland, USA  \n16 eRadiation Epidemiology Branch, Division of Cancer Epidemiology and Genetics, National  \n17 Cancer Institute, DHHS, NIH, Bethesda, MD 20892-9778, USA  \n18 fFaculty of Health and Life Sciences, Oxford Brookes University, Headington Campus, Oxford, 19 OX3 0BP, UK  \n20  \n21 Word count: abstract 176 words, main text (excluding references, Tables, Figures) 10,141 words  \n22 67 references  \n23 7 Tables, 3 Figures  \n24 Author roles  \n25 Conceptualization, Methodology: Mark Little, Gerald Kendall; Software: Mark Little; Data  \n26 curation: Gerald Kendall; Writing - Original draft preparation: Gerald Kendall, Mark Little;  \n27 Supervision: Gerald Kendall; Software, Validation: Mark Little; Writing - Reviewing and  \n28 Editing: all authors.  \n29 Acknowledgements  \n30 The authors are grateful to Dr Richard Wakeford and the two referees for detailed and helpful  \n31 comments. The work of MPL was supported by the Intramural Research Program of the National  \n32 Institutes of Health, National Cancer Institute, Division of Cancer Epidemiology and Genetics.  \n33 Abstract  \n34 We investigate methods that improve the estimation of indoor gamma ray dose rates at locations  \n35 where measurements had not been made. These new predictions use a greater range of modelling  \n36 techniques and larger variety of explanatory variables than our previous examinations of this  \n37 subject. Specifically, we now employ three types of machine learning models in addition to the  \n38 geostatistical, nearest neighbour and other earlier models. A large number of parameters, mostly  \n39 describing the characteristics of dwellings in the area in question, have been added to the set of  \n40 explanatory variables. The use of machine learning methods results in significantly improved  \n41 predictions over earlier models. The machine learning models are noisy and there is some  \n42 instability in the relative importance of particular explanatory variables although there are  \n43 general and consistent tendencies supporting the importance of certain classes of variable.  \n44 However, the range of predicted indoor gamma ray dose rates is much smaller than that of the  \n45 measurements. It is probable that epidemiological studies using such predictions will have lower  \n46 statistical power than those based on direct measurements.  \n47 Keywords: machine learning; natural background; gamma radiation; geostatistcs; neural  \n48 networks; random forests  \n49 Highlights  \n50 􀀁 Direct estimates of background γ-ray doses are expensive and liable to bias.  \n51 􀀁 Machine learning and more standard models were fitted to γ data in Great Britain.  \n52 􀀁 Machine learning results in significantly improved predictions over other models.  \n53 􀀁 All machine learning models performed well, with boosting models performing best.  \n54 􀀁 Machine learning models are noisy, and may result in loss of power.  \n55 1. Introduction  \n56 Natural background gamma radiation from terrestrial sources produces a globally averaged  \n57 annual effective dose of 0.48 mSv with a range of 0.3 to 1.0 mSv (United Nations Scientific  \n58 Committee on the Effects of Atomic Radiation (UNSCEAR","cbCaihOEt9tqkX92","https://ap.wps.com/l/cbCaihOEt9tqkX92","pdf",878574,1,48,"English","en",105,"# Abstract\n# Keywords\n# Highlights\n# 1. Introduction\n## Natural background gamma radiation and epidemiological context\n## Components of external radiation and measurement basis","[{\"question\":\"What problem does the study address for epidemiology?\",\"answer\":\"The study targets improved estimation of indoor gamma-ray dose rates at places without direct measurements, enabling more usable exposure estimates for epidemiological research.\"},{\"question\":\"How do the proposed machine-learning methods differ from earlier models?\",\"answer\":\"They use a wider range of modelling techniques and a larger set of explanatory variables, and they incorporate three machine-learning model types in addition to earlier geostatistical and nearest-neighbour approaches.\"},{\"question\":\"What are the main limitations of the machine-learning predictions?\",\"answer\":\"Predictions show noise and some instability in variable importance, and the predicted range of indoor gamma-ray dose rates is much smaller than the measured range, which may reduce statistical power versus direct measurements.\"}]","Machine Learning Techniques for the Prediction of Indoor Gamma-ray Dose Rates - Strengths, Weaknesses and implications for Epidemiology | PDF",1785809112,121,{"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},"machine-learning-techniques-for-the-prediction-of-indoor-gamma-ray-dose-rates-strengths-weaknesses-and-implications-for-epidemiology","",{"@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/machine-learning-techniques-for-the-prediction-of-indoor-gamma-ray-dose-rates-strengths-weaknesses-and-implications-for-epidemiology/122157/",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},"What problem does the study address for epidemiology?","Question",{"text":75,"@type":76},"The study targets improved estimation of indoor gamma-ray dose rates at places without direct measurements, enabling more usable exposure estimates for epidemiological research.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"How do the proposed machine-learning methods differ from earlier models?",{"text":80,"@type":76},"They use a wider range of modelling techniques and a larger set of explanatory variables, and they incorporate three machine-learning model types in addition to earlier geostatistical and nearest-neighbour approaches.",{"name":82,"@type":73,"acceptedAnswer":83},"What are the main limitations of the machine-learning predictions?",{"text":84,"@type":76},"Predictions show noise and some instability in variable importance, and the predicted range of indoor gamma-ray dose rates is much smaller than the measured range, which may reduce statistical power versus direct measurements.","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"]