[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-126729-en":3,"doc-seo-126729-105":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},126729,962084925782,"Ava Thompson","https://ap-avatar.wpscdn.com/davatar_9964176cb1d06d4a9deccf72a44ae3dc",8,"Research & Report","DATA-DRIVEN CHIMNEY FIRE RISK PREDICTION USING MACHINE LEARNING AND POINT PROCESS TOOLS - Research Report","Chimney fires are a frequent fire type whose impacts require precise prediction and rapid prevention. This study presents a combined machine-learning and statistical modelling pipeline for fire-risk prediction. Informative drivers are selected using random forests with permutation importance. A Poisson point process model is then fitted with logistic-regression estimation, and the Poisson assumption is checked via second-order summary statistics and residual diagnostics. The pipeline is validated on Twente Fire Brigade data, producing credible spatiotemporal risk predictions.","The Annals of Applied Statistics  \n2023, Vol. 17, No. 4, 3088–3111  \n[https://doi.org/10.1214/23-AOAS1752](https://doi.org/10.1214/23-AOAS1752)  \n© Institute of Mathematical Statistics, 2023  \nDATA-DRIVEN CHIMNEY FIRE RISK PREDICTION USING MACHINE LEARNING AND POINT PROCESS TOOLS  \nBY CHANGQING LU1, a , MARIE-COLETTE VAN LIESHOUT2, b , MAURITS DE GRAAF3, c  \nAND PAUL VISSCHER4, d  \n1 Department of Applied Mathematics, University of Twente, [a](ac.lu@utwente.nl)[c.lu@utwente.nl](ac.lu@utwente.nl)[ ](ac.lu@utwente.nl)2 Stochastics, Centrum Wiskunde & Informatica, [b](b marie-colette.van.lieshout@cwi.nl)[ marie-colette.van.lieshout@cwi.nl](b marie-colette.van.lieshout@cwi.nl)[ ](b marie-colette.van.lieshout@cwi.nl)3 Innovation Research & Technology, Thales Nederland B. V., [c](c maurits.de.graaf@cwi.nl)[ maurits.de.graaf@cwi.nl](c maurits.de.graaf@cwi.nl)[ ](c maurits.de.graaf@cwi.nl)4 Sector Strategy & Support, Brandweer Twente, [d](dp.visscher@brandweertwente.nl)[p.visscher@brandweertwente.nl](dp.visscher@brandweertwente.nl)  \nChimney fires constitute one of the most commonly occurring fire types.  \nPrecise prediction and prompt prevention are crucial in reducing the harm they cause. In this paper we develop a combined machine learning and statistical modelling process to predict fire risk. First, we use random forests and permutation importance techniques to identify the most informative explanatory variables. Second, we design a Poisson point process model and employ logistic regression estimation to estimate the parameters. Moreover, we validate the Poisson model assumption using second-order summary statistics and residuals. We implement the modelling process on data collected by the Twente Fire Brigade and obtain plausible predictions. Compared to similar studies, our approach has two advantages: (i) with random forests, we can select explanatory variables nonparametrically considering variable dependence; (ii) using logistic regression estimation, we can fit our statistical model efficiently by tuning it to focus on regions and times that are salient for fire  \nrisk.  \n1. Introduction. During the last decade, the Dutch fire and rescue services have been developing an interest in applying business intelligence to improve their strategy of fire prediction and prevention (NVBR (2010)) . To prepare for risk reducing measures, such as essential public awareness campaigns and proper fire staffing and equipment arrangements, accurate predictions are required. In this study we focus on chimney fires, as they occur frequently, rely heavily on environmental factors and impact people’s daily life. Collaborating with the Twente Fire Brigade, we conduct a complete risk prediction study for chimney fires. We define fire risk prediction as an occurrence modelling problem, analyze underlying patterns and design appropriate prediction models. Our approach for chimney fire prediction is general and can be transferred to similar fire types, such as kitchen fires.  \nThe literature for fire risk prediction is mostly concerned with wildfires. Overall, the prediction approaches can be divided into two categories: machine learning based approaches (e.g., Rodrigues and de la Riva (2014), Jain et al. (2020), Malik et al. (2021)) and statistical approaches (e.g., Turner (2009), Møller and Díaz-Avalos (2010), Xu and Schoenberg (2011)) . Usually, machine learning based approaches do not require prior knowledge but can detect the dependence between fire risk and a large number of environmental variables automatically using specialised learning algorithms, such as logistic regression (Preisler et al.(2004)), support vector machine (Sakr et al. (2010)), decision tree (Stojanova et al. (2012)), random forest (Rodrigues and de la Riva (2014)) and neural network (Satir, Berberoglu and Donmez (2016)) . Most machine learning algorithms are applicable for discrete data, whereas hazard maps of fire risk are continuous. Moreover, fire occurrences are usually recorded as  \nReceived O","cbCaidqevPZ9DqPD","https://ap.wps.com/l/cbCaidqevPZ9DqPD","pdf",1969758,1,24,"English","en",105,"# Introduction\n## Problem formulation for chimney fire risk prediction\n## Related approaches: machine learning vs statistical models\n# Key modelling components\n## Variable selection with random forests and permutation importance\n## Poisson point process modelling with logistic regression estimation\n## Model validation using second-order summary statistics and residuals","[{\"question\":\"What modelling approach does the study use to predict chimney fire risk?\",\"answer\":\"It combines random-forest-based variable selection with a Poisson point process model, estimated using logistic regression techniques.\"},{\"question\":\"How are explanatory variables chosen in the proposed framework?\",\"answer\":\"Random forests together with permutation importance identify the most informative variables while accounting for variable dependence.\"},{\"question\":\"How is the Poisson point process assumption validated?\",\"answer\":\"The paper validates the Poisson assumption using second-order summary statistics and residual diagnostics from the fitted model.\"}]","DATA-DRIVEN CHIMNEY FIRE RISK PREDICTION USING MACHINE LEARNING AND POINT PROCESS TOOLS - Research Report | PDF",1785934457,60,{"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},"data-driven-chimney-fire-risk-prediction-using-machine-learning-and-point-process-tools-research-report","",{"@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/data-driven-chimney-fire-risk-prediction-using-machine-learning-and-point-process-tools-research-report/126729/",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","2026-08-05",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 modelling approach does the study use to predict chimney fire risk?","Question",{"text":75,"@type":76},"It combines random-forest-based variable selection with a Poisson point process model, estimated using logistic regression techniques.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"How are explanatory variables chosen in the proposed framework?",{"text":80,"@type":76},"Random forests together with permutation importance identify the most informative variables while accounting for variable dependence.",{"name":82,"@type":73,"acceptedAnswer":83},"How is the Poisson point process assumption validated?",{"text":84,"@type":76},"The paper validates the Poisson assumption using second-order summary statistics and residual diagnostics from the fitted model.","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},[93,97,101,105,109,114,119,122,127,130,134],{"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":29,"slug":108},5,"Comic","comic",{"id":110,"doc_module":4,"doc_module_name":46,"category_name":111,"show_sort_weight":112,"slug":113},6,"Technology",50,"technology",{"id":115,"doc_module":4,"doc_module_name":46,"category_name":116,"show_sort_weight":117,"slug":118},7,"Healthcare",40,"healthcare",{"id":11,"doc_module":4,"doc_module_name":46,"category_name":12,"show_sort_weight":120,"slug":121},30,"research-report",{"id":123,"doc_module":4,"doc_module_name":46,"category_name":124,"show_sort_weight":125,"slug":126},9,"Religion & Spirituality",20,"religion-spirituality",{"id":125,"doc_module":4,"doc_module_name":46,"category_name":128,"show_sort_weight":125,"slug":129},"World Cup","world-cup",{"id":131,"doc_module":4,"doc_module_name":46,"category_name":132,"show_sort_weight":131,"slug":133},10,"Lifestyle","lifestyle",{"id":135,"doc_module":4,"doc_module_name":46,"category_name":136,"show_sort_weight":106,"slug":137},19,"General","general"]