[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-123267-en":3,"doc-seo-123267-105":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},123267,1099514067438,"River Wang","https://ap-avatar.wpscdn.com/avatar/100002539ee87300030?x-image-process=image/resize,m_fixed,w_180,h_180&k=1780474512215547542",8,"Research & Report","How to better predict the effect of urban traffic and weather on air pollution - Norwegian evidence from machine learning approaches","This paper uses machine learning approaches to predict the association between traffic volume, air pollution, and meteorological conditions, emphasizing interactions among these factors. Using hourly data for Oslo, Norway, it models traffic and pollution with NOx and PM2.5 together with weather variables. Evaluation across six datasets from the full 2019 year shows that autoregressive integrated moving average with exogenous inputs and an autoregressive moving average dynamic linear model outperform machine learning benchmarks. The study also tests how sampling weather subsets affects accuracy and derives policy recommendations for reducing traffic-related air pollution.","Journal of Economic Behavior and Organization 221 (2024) 544–569  \nContents lists available at ScienceDirect  \nJournal of Economic Behavior and Organization  \njournal [homepage: www.elsevier.com/locate/jebo](homepage: www.elsevier.com/locate/jebo)  \n| Research Paper\u003Cbr>How to better predict the effect of urban traffic and weather on air pollution? Norwegian evidence from machine learning approaches |  |  |  |\n| --- | --- | --- | --- |\n| Cong Cao a, b, *\u003Cbr>a Center for Science, Society, and Public Policy, Division of the Humanities and Social Sciences, California Institute of Technology, 1200 E California Blvd, Pasadena, CA 91125, USA\u003Cbr>b Department of Economics, Norwegian University of Science and Technology, Høgskoleringen 1, 7491 Trondheim, Norway |  |  |  |\n| A R T I C L E I N F O |  | A B S T R A C T |  |\n| JEL Classification:\u003Cbr>C53 C52 Q5\u003Cbr>R4\u003Cbr>Keywords:\u003Cbr>Machine Learning Urban Traffic Air Pollution Transportation Policy |  | This paper uses machine learning approaches to predict the association between traffic volume, air pollution, and meteorological conditions. A key focus is on the interaction between these factors. The paper does this using hourly traffic volume, NOx , PM2.5 , and weather data for Oslo, Norway. I considered a total of six datasets of the 2019 whole-year data to verify the prediction accuracy of the models. I find that the autoregressive integrated moving average model with exogenous input variables, and the autoregressive moving average dynamic linear model outperform the machine learning models in predicting air pollution. At the same time, I also explored the effect of sampling weather subsets on prediction accuracy. Finally, my study makes optimal policy recommendations for reducing air pollution from traffic volume, after considering the interaction and lagged effects of meteorology, time variables, traffic, and air pollution. |  |\n\n1. Introduction  \nAir pollution caused by traffic, and its resulting health effects, have become increasingly recognized as a source of public concern (Currie et al., 2005 & 2009; Pasquier and Andr´e, 2017; Kendrick et al., 2015). Poor urban air quality poses a significant risk to the environment and human health: It increases the incidence of respiratory diseases, especially among those living near major traffic routes and highways (Font & Fuller, 2016; Moretti et al., 2011; Bai et al., 2018). Across the globe, more than 5.5 million people die prematurely every year because of air pollution (Amos, 2016). In addition, traffic-related air pollution drains more public hospital care resource usage as well as personal health costs. It also influences people’s behavior. As an example, the extreme air pollution experienced in Beijing has led to the demand for air filtration equipment, air freshening equipment, and regular precautionary hospital visits for respiratory and lung examinations, which increases the cost of personal medical care. At the same time, residents need to wear PM2.5 disposable masks outside as a protective measure during winter in Beijing; here the PM2.5 represents particulate matter with a diameter of less than, or equal to, 2.5 microns. Sustainable transport is one of the sustainable development goals of the UN 2030 Agenda (Kurz et al., 2014), and many policies have been suggested and implemented aimed at improving urban transportation and curbing air pollution (Parry et al., 2007). These include low-emission zones, restrictions on urban vehicle use, and congestion pricing (Bjørgen & Ryghaug, 2022; Green et al., 2016, 2020; Green & Krehic, 2022).  \nEffective policies to address these externalities rely on a clear understanding of the links between traffic volume and air pollution. One problem is that the mechanism between traffic volume and air pollution is complicated due to confounders such as meteorological  \n* Corresponding author.  \nE-mail address: [ccao4541@gmail.com](ccao4541@gmail.com).  \n[https://doi.org/10.1016/j.jebo.2024.03.018](htt","cbCaims3HcqGc1Ho","https://ap.wps.com/l/cbCaims3HcqGc1Ho","pdf",8643956,1,26,"English","en",105,"# Introduction\n## Policy context and public health relevance\n## Key challenge: confounding and meteorological interactions\n## Modeling approaches and research motivation","[{\"question\":\"What variables does the study use to predict air pollution in Oslo?\",\"answer\":\"It uses hourly traffic volume, NOx, PM2.5, and meteorological data, focusing on interactions among these factors.\"},{\"question\":\"Which modeling approaches perform best for air-pollution prediction?\",\"answer\":\"The autoregressive integrated moving average model with exogenous inputs and the autoregressive moving average dynamic linear model outperform the machine learning models in the paper’s evaluations.\"},{\"question\":\"How does the study incorporate weather into prediction and policy implications?\",\"answer\":\"It examines interaction and lagged effects of meteorology and tests whether sampling subsets of weather affects accuracy, then uses the results to propose optimal traffic-volume-related policy recommendations.\"}]","How to better predict the effect of urban traffic and weather on air pollution - Norwegian evidence from machine learning approaches | PDF",1785815594,66,{"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},"how-to-better-predict-the-effect-of-urban-traffic-and-weather-on-air-pollution-norwegian-evidence-from-machine-learning-approaches","",{"@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/how-to-better-predict-the-effect-of-urban-traffic-and-weather-on-air-pollution-norwegian-evidence-from-machine-learning-approaches/123267/",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 variables does the study use to predict air pollution in Oslo?","Question",{"text":75,"@type":76},"It uses hourly traffic volume, NOx, PM2.5, and meteorological data, focusing on interactions among these factors.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"Which modeling approaches perform best for air-pollution prediction?",{"text":80,"@type":76},"The autoregressive integrated moving average model with exogenous inputs and the autoregressive moving average dynamic linear model outperform the machine learning models in the paper’s evaluations.",{"name":82,"@type":73,"acceptedAnswer":83},"How does the study incorporate weather into prediction and policy implications?",{"text":84,"@type":76},"It examines interaction and lagged effects of meteorology and tests whether sampling subsets of weather affects accuracy, then uses the results to propose optimal traffic-volume-related policy recommendations.","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"]