[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-126270-en":3,"doc-seo-126270-105":31,"detail-sidebar-cat-0-en-105":97},{"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":20,"is_deleted":4,"is_public":21,"is_downloadable":21,"audit_status":21,"page_count":22,"language":23,"language_code":24,"site_id":25,"html_lang":24,"table_of_contents":26,"faqs":27,"seo_title":28,"seo_description":14,"update_tm":29,"read_time":30},126270,2336475104362,"Eden","https://ap-avatar.wpscdn.com/avatar/22000c4c46a41b752dd?x-image-process=image/resize,m_fixed,w_180,h_180&k=1786595829695023868",8,"Research & Report","Forest and Land Fire Vulnerability Assessment and Mapping using Machine Learning Method in East Nusa Tenggara Province, Indonesia","Forest and land fires (FLF) can severely damage forest ecosystems and reduce their ecological functions, making accurate prediction a key requirement for prevention and land management. A study focuses on East Nusa Tenggara (NTT), Indonesia, where 2022 recorded the highest fire incidence nationwide. It evaluates seven machine learning models using a geospatial dataset built with ArcGIS, combining NTT fire data and fourteen fire-related factors. Information Gain Ratio selects twelve key features, and the XGB model achieves strong training AUC (0.959) and useful testing performance (0.743). The resulting vulnerability map highlights topographic, vegetation, meteorological, and human-related drivers, with recommendations for policy, land management, education, and infrastructure.","Forest and Land Fire Vulnerability Assessment and Mapping using Machine Learning Method in East Nusa Tenggara Province, Indonesia  \nHans Timothy Wijaya⁎ and Aniati MurniArymurthy† Faculty of Computer Science, Universitas Indonesia, Depok, Indonesia E-mail:⁎[hans.timothy@ui.ac.id](hans.timothy@ui.ac.id),†[aniati@cs.ui.ac.id](aniati@cs.ui.ac.id)  \nAbstract  \nForest and land fires (FLF) severely damage forest ecosystems and reduce their functionality. Predicting areas prone to fires is crucial for effective management and prevention. Machine learning (ML) has shown potential in this field. By 2022, East Nusa Tenggara (NTT) experienced the highest incidence of fires in Indonesia, with 70,637 hectares burned. This study evaluates NTT's FLF vulnerability using seven ML methods: Gaussian Naive Bayes, Support Vector Machine, Logistic Regression, Artificial Neural Network, Random Forest, Gradient Boosting Machine, and Extreme Gradient Boost (XGB). A geospatial dataset combining NTT's 2022 fire data and fourteen fire-related factors was developed with ArcGIS. Using the Information Gain Ratio for feature selection, twelve key features were identified: Elevation, Slope angle, Slope Aspect, Plan Curvature, Land Cover, NDVI, Distance to Road, Distance to Buildings, Annual Rainfall, Average Temperature, Wind Speed, and Relative Humidity. The XGB model performed best, with AUC values of 0.959 for training and 0.743 for testing. The resulting vulnerability map revealed key fire factors: low elevation, gentle slopes, curved terrain, forest cover, poor vegetation health, human activity, distant firefighting resources, low rainfall, high temperatures, high wind speeds, and low humidity. Recommendations include land management, fire-resistant vegetation, policy enforcement, community education, and infrastructure enhancement.  \nKeywords: East Nusa Tenggara, forest and landfires, feature selection, machine learning, mapping  \n1. Introduction  \nTerrestrial ecosystems such as forests play a fundamental role in ecological equilibrium, soil and water conservation, environmental enhancement, carbon sequestration, and oxygen production [1]. Nonetheless, the integrity of forests faces multifaceted threats, including urban expansion, deforestation, natural disasters such as landslides and storms, and forest fires [2]. Forest and land fires (FLF) pose significant hazards to forest ecosystems, often spiraling out of control and causing detrimental impacts on both natural resources and human welfare [3].  \nAs per data from the Ministry of Environment and Forestry [4], Indonesia undergoes a substantial area of FLF amounting to 204.9 thousand hectares in 2022. This area predominantly comprises mineral soil, covering approximately 92.96%, followed by peat soil, accounting for 7.04% . Notably, East Nusa  \nTenggara (NTT) Province emerged as the region most affected by fires, with 70,637 hectares burned, primarily encompassing savanna, shrublands, and dry agricultural areas intermixed with shrubs.  \nThe repercussions of FLF are profound, leading to the degradation of forest functions such as soil ecology, hydrology, land integrity, and erosion [4-5]. Furthermore, these fires precipitate biodiversity loss, often resulting in species extinction [3]. Given the substantial losses incurred, governmental efforts are continuously directed toward fire prevention and control through various policy frameworks and programs [4] .  \nAccurate prediction of FLF is pivotal for effective mitigation and prevention strategies [6]. Additionally, mapping the vulnerability of regions to FLF is essential for resource allocation and land use planning [7] . Machine learning (ML) methods have been extensively explored for  \nTable 1. FLF-causal factors [1-2],[5-11] .  \n\n| Category | Specific conditioning factor |\n| --- | --- |\n| Topography | Altitude, Slope Angle, Slope Aspect, Plan Curvature |\n| Hydrology | Distance to Rivers, Topographic Wetness Index (TWI) |\n| Land coverage | Normalized D","cbCaibnrwfQH84tG","https://ap.wps.com/l/cbCaibnrwfQH84tG","pdf",2451437,5,1,17,"English","en",105,"# Introduction\n## Forest fires and ecological impacts\n## National and regional fire context (Indonesia, NTT)\n## Role of prediction and vulnerability mapping\n## Machine learning approaches and variability across studies\n## Feature selection and conditioning factors\n## Research questions and study objectives","[{\"question\":\"Why is predicting forest and land fire (FLF) vulnerability important in NTT?\",\"answer\":\"Accurate prediction supports mitigation and prevention efforts, and vulnerability mapping helps allocate resources and guide land-use planning effectively in NTT.\"},{\"question\":\"Which machine learning models are evaluated for FLF vulnerability assessment?\",\"answer\":\"The study evaluates seven models: Gaussian Naive Bayes, Support Vector Machine, Logistic Regression, Artificial Neural Network, Random Forest, Gradient Boosting Machine, and Extreme Gradient Boost (XGB).\"},{\"question\":\"How are key input features selected for the machine learning models?\",\"answer\":\"A geospatial dataset is built in ArcGIS, then Information Gain Ratio is applied for feature selection, resulting in twelve key features such as elevation, NDVI, rainfall, wind speed, and relative humidity.\"},{\"question\":\"What are the main drivers of FLF vulnerability revealed by the best-performing model?\",\"answer\":\"The vulnerability map indicates that low elevation, gentle slopes and curved terrain, forest cover with poor vegetation health, human activity, distant firefighting resources, low rainfall, high temperatures, high wind speeds, and low humidity increase fire susceptibility.\"}]","Forest and Land Fire Vulnerability Assessment and Mapping using Machine Learning Method in East Nusa Tenggara Province, Indonesia | PDF",1785904169,43,{"code":4,"msg":32,"data":33},"ok",{"site_id":25,"language":24,"slug":34,"title":13,"keywords":35,"description":14,"schema_data":36,"social_meta":92,"head_meta":94,"extra_data":96,"updated_unix":29},"forest-and-land-fire-vulnerability-assessment-and-mapping-using-machine-learning-method-in-east-nusa-tenggara-province-indonesia","",{"@graph":37,"@context":91},[38,55,70],{"@type":39,"itemListElement":40},"BreadcrumbList",[41,45,49,52],{"item":42,"name":43,"@type":44,"position":21},"https://docshare.wps.com","Home","ListItem",{"item":46,"name":47,"@type":44,"position":48},"https://docshare.wps.com/document/","Document",2,{"item":50,"name":12,"@type":44,"position":51},"https://docshare.wps.com/document/research-report/",3,{"item":53,"name":13,"@type":44,"position":54},"https://docshare.wps.com/document/forest-and-land-fire-vulnerability-assessment-and-mapping-using-machine-learning-method-in-east-nusa-tenggara-province-indonesia/126270/",4,{"url":53,"name":13,"@type":56,"author":57,"headline":13,"publisher":59,"fileFormat":62,"inLanguage":24,"description":14,"dateModified":63,"datePublished":64,"encodingFormat":62,"isAccessibleForFree":65,"interactionStatistic":66},"DigitalDocument",{"name":9,"@type":58},"Person",{"url":42,"name":60,"@type":61},"DocShare","Organization","application/pdf","2026-08-23","2026-08-05",true,{"@type":67,"interactionType":68,"userInteractionCount":20},"InteractionCounter",{"@type":69},"ViewAction",{"@type":71,"mainEntity":72},"FAQPage",[73,79,83,87],{"name":74,"@type":75,"acceptedAnswer":76},"Why is predicting forest and land fire (FLF) vulnerability important in NTT?","Question",{"text":77,"@type":78},"Accurate prediction supports mitigation and prevention efforts, and vulnerability mapping helps allocate resources and guide land-use planning effectively in NTT.","Answer",{"name":80,"@type":75,"acceptedAnswer":81},"Which machine learning models are evaluated for FLF vulnerability assessment?",{"text":82,"@type":78},"The study evaluates seven models: Gaussian Naive Bayes, Support Vector Machine, Logistic Regression, Artificial Neural Network, Random Forest, Gradient Boosting Machine, and Extreme Gradient Boost (XGB).",{"name":84,"@type":75,"acceptedAnswer":85},"How are key input features selected for the machine learning models?",{"text":86,"@type":78},"A geospatial dataset is built in ArcGIS, then Information Gain Ratio is applied for feature selection, resulting in twelve key features such as elevation, NDVI, rainfall, wind speed, and relative humidity.",{"name":88,"@type":75,"acceptedAnswer":89},"What are the main drivers of FLF vulnerability revealed by the best-performing model?",{"text":90,"@type":78},"The vulnerability map indicates that low elevation, gentle slopes and curved terrain, forest cover with poor vegetation health, human activity, distant firefighting resources, low rainfall, high temperatures, high wind speeds, and low humidity increase fire susceptibility.","https://schema.org",{"og:url":53,"og:type":93,"og:title":13,"og:site_name":60,"og:description":14},"article",{"robots":95,"canonical":53},"index,follow",{"doc_id":7,"site_id":25},{"code":4,"msg":5,"data":98},[99,103,107,111,115,120,125,128,133,136,140],{"id":21,"doc_module":4,"doc_module_name":47,"category_name":100,"show_sort_weight":101,"slug":102},"Story & Novel",90,"story-novel",{"id":48,"doc_module":4,"doc_module_name":47,"category_name":104,"show_sort_weight":105,"slug":106},"Literature",80,"literature",{"id":54,"doc_module":4,"doc_module_name":47,"category_name":108,"show_sort_weight":109,"slug":110},"Exam",70,"exam",{"id":20,"doc_module":4,"doc_module_name":47,"category_name":112,"show_sort_weight":113,"slug":114},"Comic",60,"comic",{"id":116,"doc_module":4,"doc_module_name":47,"category_name":117,"show_sort_weight":118,"slug":119},6,"Technology",50,"technology",{"id":121,"doc_module":4,"doc_module_name":47,"category_name":122,"show_sort_weight":123,"slug":124},7,"Healthcare",40,"healthcare",{"id":11,"doc_module":4,"doc_module_name":47,"category_name":12,"show_sort_weight":126,"slug":127},30,"research-report",{"id":129,"doc_module":4,"doc_module_name":47,"category_name":130,"show_sort_weight":131,"slug":132},9,"Religion & Spirituality",20,"religion-spirituality",{"id":131,"doc_module":4,"doc_module_name":47,"category_name":134,"show_sort_weight":131,"slug":135},"World Cup","world-cup",{"id":137,"doc_module":4,"doc_module_name":47,"category_name":138,"show_sort_weight":137,"slug":139},10,"Lifestyle","lifestyle",{"id":141,"doc_module":4,"doc_module_name":47,"category_name":142,"show_sort_weight":20,"slug":143},19,"General","general"]