[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-121726-en":3,"doc-seo-121726-105":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},121726,962075006959,"Anda","https://ap-avatar.wpscdn.com/avatar/e0002397efbe92a78e?_k=1776741047341049297",8,"Research & Report","Machine Learning-Enabled Regional Multi-Hazards Risk Assessment Considering Social Vulnerability","Regional multi-hazards risk assessment is challenging due to limited data access and the need to capture interactions among multiple hazards and social vulnerability. The study proposes a machine learning–enabled risk assessment framework to address distribution of multi-hazards risk in areas with high hazard levels and social vulnerability. It maps flooding, wildfires, and seismic hazards using multiple classifiers, evaluates social vulnerability via a tailored composite index and classification models, and quantifies spatial interaction mechanisms. The results show the Random Forest model performs best and provide a multi-hazards risk map to support prioritization and policy interventions.","Boise State University  \nScholarWorks  \n\n| Civil Engineering Faculty Publications and Presentations | Department of Civil Engineering |\n| --- | --- |\n| 8-17-2023\u003Cbr>Machine Learning-Enabled Regional Multi-Hazards Risk Assessment Considering Social Vulnerability\u003Cbr>Tianjie Zhang\u003Cbr>Boise State University\u003Cbr>Donglei Wang\u003Cbr>Boise State University\u003Cbr>Yang Lu\u003Cbr>Boise State University |  |\n\nPublication Information  \nZhang, Tianjie; Wang, Donglei; and Lu, Yang. (2023) . \"Machine Learning-Enabled Regional Multi-Hazards Risk Assessment Considering Social Vulnerability\" . Scientific Reports, 13, 13405. [https://doi.org/10.1038/](https://doi.org/10.1038/)[ ](https://doi.org/10.1038/)s41598-023-40159-9  \nThese authors contributed equally to this work: Tianjie Zhang and Donglei Wang.  \n[www. nature.com/scientificreports](www. nature.com/scientificreports)  \nOPEN  \nMachine learning‑enabled regional multi‑hazards risk assessment considering social vulnerability  \nTianjie Zhang1,4, Donglei Wang2,4 & Yang Lu3*  \nThe regional multi‑hazards risk assessment poses difficulties due to data access challenges, and the potential interactions between multi‑hazards and social vulnerability. For better natural hazards risk perception and preparedness, it is important to study the nature‑hazards risk distribution indifferent areas, specifically a major priority in the areas of high hazards level and social vulnerability. We propose a multi‑hazards risk assessment method which considers social vulnerability into the analyzing and utilize machine learning‑enabled models to solve this issue. The proposed methodology integrates three aspects as follows: (1) characterization and mapping of multi‑hazards (Flooding, Wildfires, and Seismic) using five machine learning methods including Naïve Bayes (NB), K‑Nearest Neighbors (KNN), Logistic Regression (LR), Random Forest (RF), and K‑Means (KM); (2) evaluation of social vulnerability with a composite index tailored for the case‑study area and using machine learning models for classification; (3) risk‑based quantification of spatial interaction mechanisms between multi‑hazards and social vulnerability. The results indicate that RF model performs best in both hazard‑related and social vulnerability datasets. The most cities at multi‑hazards risk account  \nfor 34.12% of total studied cities (covering 20.80% land). Additionally, high multi‑hazards level and socially vulnerable cities account for 15.88%(covering 4.92% land). This study generates a multi‑ hazards risk map which show a wide variety of spatial patterns and a corresponding understanding of where regional high hazards potential and vulnerable areas are. It emphasizes an urgent need to implement information‑based prioritization when natural hazards coming, and effective policy measures for reducing natural‑hazards risks in future.  \nIn recent years, natural hazards have become severe threats to society and continued to have a heavy toll on human being. Approximately 45,000 people globally (representing around 0.1% of global deaths) died yearly from natural disasters over the past decade1. The United States (US) had sustained 341 weather and climate disasters since 1980, where the total cost of these events exceeded $2.475 trillion, and overall damages/costs reached or exceeded $1 billion (reported by National Centers for Environmental Information, [www.ncei.noaa.gov/access/](www.ncei.noaa.gov/access/)[ ](www.ncei.noaa.gov/access/)[billions](billions)) . In addition, the previous study showed that over half (57%) of the US structures (office buildings, community houses, schools, hospitals, etc.) were built in hazard hotspots, and about 1.5 million structures were located in hotspots of two or more natural hazards2. There was growing awareness of the fact that different hazards could happen simultaneously or successively which would amplify their overall impact on communities3. Multi-hazards were defined based on this phenomenon4, which could result in a highe","cbCaivmohwRA1pvj","https://ap.wps.com/l/cbCaivmohwRA1pvj","pdf",2926429,1,15,"English","en",105,"# Background and Rationale\n## Multi-hazards and societal risk context\n## Hazard risk components: hazards, exposure, vulnerability\n# Proposed Methodology\n## Multi-hazards characterization and mapping\n## Social vulnerability evaluation\n## Spatial interaction risk quantification\n# Results and Implications\n## Model performance and risk distribution findings\n## Risk mapping and prioritization needs","[{\"question\":\"Why is regional multi-hazards risk assessment difficult?\",\"answer\":\"It is difficult because data access can be limited and because multi-hazards can interact with social vulnerability, requiring models that represent both dimensions jointly.\"},{\"question\":\"What machine learning methods are used to map multi-hazards?\",\"answer\":\"The framework uses five machine learning methods: Naïve Bayes, K-Nearest Neighbors, Logistic Regression, Random Forest, and K-Means to characterize and map flooding, wildfires, and seismic hazards.\"},{\"question\":\"How is social vulnerability assessed in the proposed approach?\",\"answer\":\"Social vulnerability is evaluated using a composite index tailored for the case-study area, and machine learning models are used for classification of vulnerability patterns.\"}]","Machine Learning-Enabled Regional Multi-Hazards Risk Assessment Considering Social Vulnerability | PDF",1785806505,38,{"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-enabled-regional-multi-hazards-risk-assessment-considering-social-vulnerability","",{"@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-enabled-regional-multi-hazards-risk-assessment-considering-social-vulnerability/121726/",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},"Why is regional multi-hazards risk assessment difficult?","Question",{"text":75,"@type":76},"It is difficult because data access can be limited and because multi-hazards can interact with social vulnerability, requiring models that represent both dimensions jointly.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"What machine learning methods are used to map multi-hazards?",{"text":80,"@type":76},"The framework uses five machine learning methods: Naïve Bayes, K-Nearest Neighbors, Logistic Regression, Random Forest, and K-Means to characterize and map flooding, wildfires, and seismic hazards.",{"name":82,"@type":73,"acceptedAnswer":83},"How is social vulnerability assessed in the proposed approach?",{"text":84,"@type":76},"Social vulnerability is evaluated using a composite index tailored for the case-study area, and machine learning models are used for classification of vulnerability patterns.","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"]