[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-118374-en":3,"doc-seo-118374-105":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},118374,1099514067415,"Rowan","https://ap-avatar.wpscdn.com/avatar/100002539d78ffe74a7?x-image-process=image/resize,m_fixed,w_180,h_180&k=1779092875211072502",8,"Research & Report","Sensitivity and feature importance of climate factors for predicting fire hotspots using machine learning methods - Research article","Indonesia faces recurrent forest-fire crises, with vast losses and heavy health impacts driven by fire hotspots that enable rapid monitoring over large areas. This study evaluates and compares machine learning approaches to predict hotspots in Kalimantan using local and global climate factors from 2001–2020. The most accurate Bayesian linear regression model is assessed with sensitivity and feature-importance measures, including variance/density/distribution-based indices and permutation/Shapley methods. Results show dry days as the most influential predictor, while tree-based models indicate potential overfitting and inferior generalization.","IAES International Journal of Artificial Intelligence (IJ-AI)  \nVol. 13, No. 2, June 2024, pp. 2212∼2225  \nISSN: 2252-8938, DOI: 10.11591/ijai.v13.i2.pp2212-2225 ❒ 2212  \n\n| Sensitivity and feature importance of climate factors for predicting fire hotspots using machine learning methods\u003Cbr>Endar Hasafah Nugrahani, Sri Nurdiati, Fahren Bukhari, Mohamad Khoirun Najib, Denny Muliawan\u003Cbr>Sebastian, Putri Afia Nur Fallahi\u003Cbr>Department of Mathematics, Faculty of Mathematics and Natural Sciences, IPB University, Bogor, Indonesia |  |  |\n| --- | --- | --- |\n| Article Info\u003Cbr>Article history:\u003Cbr>Received Jul 29, 2023 Revised Oct 29, 2023 Accepted Jan 6, 2024\u003Cbr>Keywords:\u003Cbr>Bayesian regression Feature importance Machine learning Sensitivity analysis Wildfire |  | ABSTRACT\u003Cbr>Every year, Indonesia experiences a national crisis due to forest fires because the resulting impacts and losses are enormous. Hotspots as indicators of forest fires capable of quickly monitoring large areas are often predicted using various machine learning methods. However, there is still few research that analyzes the sensitivity and feature importance of each predictor that forms a machine learning prediction model. This study evaluates and compares machine learning methods to predict hotspots in Kalimantan based on local and global climate factors in 2001-2020 . Using the most accurate machine learning model, each climate factor used as a predictor is analyzed for its sensitivity and feature importance. Four methods used include random forest, gradient boosting, Bayesian regression, and artificial neural networks. Meanwhile, measures of sensitivity and feature importance used are variance, density, and distributionbased sensitivity indices, as well as permutation and Shapley feature importance. Evaluation of the machine learning model concluded that the Bayesian linear regression model outperformed other models with an RMSE of 750 hotspots and an explained variance score of 68.96% on testing data. Meanwhile, tree-based models show signs of overfitting, including gradient boosting and random forest. Based on the results of sensitivity analysis and feature importance of the Bayesian linear regression model, the number of dry days is the most important feature in predicting fire hotspots in Kalimantan.\u003Cbr>This is an open access article under the CC BY-SA license. |\n| Corresponding Author: |  |  |\n| Sri Nurdiati\u003Cbr>Department of Mathematics, Faculty of Mathematics and Natural Sciences, IPB University Meranti Kampus Road, Babakan, Dramaga, Bogor Regency, West Java 16680, Indonesia Email: [nurdiati@apps.ipb.ac.id](nurdiati@apps.ipb.ac.id) |  |  |\n\n1. INTRODUCTION  \nIn the last three decades, Indonesia is heavily affected by land and forest fires. There have been three remarkable land and forest fires reported in 1997–1998, 2015, and 2019 . Nonetheless, Indonesia always experiences land and forest fires, particularly in Sumatra and Kalimantan [1] . Forest fires are a major environmental problem with significant impacts on the atmosphere, carbon cycle, and various ecosystem benefits. The haze caused by forest fires causes short to long-term health problems, as well as causing economic losses, and even affects neighboring countries [2] . Therefore, it is vital to know the indications of forest fires in order to reduce their impact.  \nOne of the factors causing forest fires is climatic conditions such as temperature, humidity, and rainfall, which can affect surface dryness [1] . Climate is the average condition of temperature, rainfall, pressure,  \nhumidity, wind direction, and other climate parameters over a long period. Meanwhile, climate change is the term used to describe shifts in the climate that are caused, either directly or indirectly, by human activity, causing changes in the composition of the atmosphere and increasing climate variability over a long period. Indonesia is included in the category of countries that are very vulnerable to climate change can be ","cbCaiekIiLK4eIvL","https://ap.wps.com/l/cbCaiekIiLK4eIvL","pdf",2160754,1,14,"English","en",105,"# Introduction\n## Climate drivers of forest fires\n## Previous prediction models and research gap\n# Methodology and model evaluation\n## Machine learning methods used\n## Sensitivity and feature-importance measures\n# Results\n## Model comparison and performance\n## Sensitivity analysis and key predictors\n# Conclusion","[{\"question\":\"Why are fire hotspots important in predicting forest fires?\",\"answer\":\"Hotspots serve as indicators of forest fires and can be used to monitor large areas quickly. Their prediction helps reduce environmental, health, and economic impacts.\"},{\"question\":\"Which machine learning methods are evaluated for hotspot prediction?\",\"answer\":\"The study compares random forest, gradient boosting, Bayesian regression (Bayesian linear regression), and artificial neural networks.\"},{\"question\":\"What is the most important climate feature for predicting fire hotspots in Kalimantan?\",\"answer\":\"Sensitivity and feature-importance results from the Bayesian linear regression model identify the number of dry days as the most important feature.\"}]","Sensitivity and feature importance of climate factors for predicting fire hotspots using machine learning methods - Research article | PDF",1785683325,35,{"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},"sensitivity-and-feature-importance-of-climate-factors-for-predicting-fire-hotspots-using-machine-learning-methods-research-article","",{"@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/sensitivity-and-feature-importance-of-climate-factors-for-predicting-fire-hotspots-using-machine-learning-methods-research-article/118374/",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","2026-08-02",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 are fire hotspots important in predicting forest fires?","Question",{"text":75,"@type":76},"Hotspots serve as indicators of forest fires and can be used to monitor large areas quickly. Their prediction helps reduce environmental, health, and economic impacts.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"Which machine learning methods are evaluated for hotspot prediction?",{"text":80,"@type":76},"The study compares random forest, gradient boosting, Bayesian regression (Bayesian linear regression), and artificial neural networks.",{"name":82,"@type":73,"acceptedAnswer":83},"What is the most important climate feature for predicting fire hotspots in Kalimantan?",{"text":84,"@type":76},"Sensitivity and feature-importance results from the Bayesian linear regression model identify the number of dry days as the most important feature.","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"]