[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-120778-en":3,"doc-seo-120778-105":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},120778,34359740700684,"Finn","https://ap-avatar.wpscdn.com/avatar/1f400023980c374ae676?_k=1777273430885731487",8,"Research & Report","Testing machine learning models for heuristic building damage assessment applied to the Italian Database of Observed Damage (DaDO)","Seismic building damage assessment is critical for effective earthquake disaster management. This study evaluates six machine learning models for damage characterization using the Italian Database of Observed Damage (DaDO), training and testing with both complete DaDO structural features and a reduced set of reliable, easily collected features such as age, storeys, floor area, building height, and macroseismic intensity. Damage per building is derived using EMS-98 observed after seven Italian earthquakes, and results show extreme gradient boosting classification performs best with accurate traffic-light grouping, comparable to the RISK-UE method and revealing damage-dependent feature importance.","Nat. Hazards Earth Syst. Sci., 23, 3199–3218, 2023 [https://doi.org/10.5194/nhess-23-3199-2023](https://doi.org/10.5194/nhess-23-3199-2023)[ ](https://doi.org/10.5194/nhess-23-3199-2023)© Author(s) 2023 . This work is distributed under the Creative Commons Attribution 4 .0 License.  \nTesting machine learning models for heuristic building damage  \nassessment applied to the Italian Database of Observed Damage (DaDO)  \nSubash Ghimire 1 , Philippe Guéguen 1 , Adrien Pothon2 , and Danijel Schorlemmer3  \n1ISTerre, Université Grenoble Alpes/CNRS/IRD/Université Gustave Eiffel, Grenoble, CS40700 38058 Grenoble CEDEX 9, France  \n2AXA Group Risk Management, GIE AXA, 21 Avenue Matignon, 75008 Paris, France  \n3 German Research Centre for Geosciences, Telegrafenberg, 14473 Potsdam, Germany Correspondence: Subash Ghimire ([subash.ghimire@univ-grenoble-alpes.fr](subash.ghimire@univ-grenoble-alpes.fr))  \nReceived: 20 January 2023 – Discussion started: 7 February 2023  \nRevised: 27 June 2023 – Accepted: 23 August 2023 – Published: 5 October 2023  \nAbstract. Assessing or forecasting seismic damage to buildings is an essential issue for earthquake disaster management. In this study, we explore the efficacy of several machine learning models for damage characterization, trained and tested on the database of damage observed after Italian earthquakes (the Database of Observed Damage – DaDO) . Six models were considered: regression-and classificationbased machine learning models, each using random forest, gradient boosting, and extreme gradient boosting. The structural features considered were divided into two groups: all structural features provided by DaDO or only those considered to be the most reliable and easiest to collect (age, number of storeys, floor area, building height) . Macroseismic intensity was also included as an input feature. The seismic damage per building was determined according to the EMS-98 scale observed after seven significant earthquakes occurring in several Italian regions. The results showed that extreme gradient boosting classification is statistically the most efficient method, particularly when considering the basic structural features and grouping the damage according to the traffic-light-based system used; for example, during the post-disaster period (green, yellow, and red), 68 % of buildings were correctly classified. The results obtained by the machine-learning-based heuristic model for damage assessment are of the same order of accuracy (error values were less than 17 %) as those obtained by the traditional RISK-UE method. Finally, the machine learning analysis found that the  \nimportance of structural features with respect to damage was conditioned by the level of damage considered.  \n1 Introduction  \nPopulation growth worldwide increases exposure to natural hazards, increasing consequences in terms of global economic and human losses. For example, between 1985 and 2014, the world's population increased by 50 % and average annual losses due to natural disasters increased from USD 14 billion to over USD 140 billion (Silva et al., 2019) . Among other natural hazards, earthquakes represent one-fifthof total annual economic losses and cause more than 20 000 deaths per year (Daniell et al., 2017; Silva et al., 2019) . To develop effective seismic risk reduction policies, decisionmakers and stakeholders rely on a representation of consequences when earthquakes affect the built environment. Two main risk metrics generally considered at the global scale are associated with building damage: direct economic losses due to costs of repair/replacement and loss of life of inhabitants due to building damage. The damage is estimated by combining the seismic hazard, exposure models, and vulnerability/fragility functions (Silva et al., 2019) .  \nFor scenario-based risk assessment, damage and related consequences are computed for a single earthquake defined in terms of magnitude, location, and other seismological features. Many methods have","cbCaijKg3EiOY0FI","https://ap.wps.com/l/cbCaijKg3EiOY0FI","pdf",5301897,1,20,"English","en",105,"# Abstract\n# Introduction\n## Seismic risk and building damage metrics\n## Vulnerability and fragility functions\n## Data limitations and exposure modeling\n## Growth of AI in seismic risk assessment","[{\"question\":\"Which machine learning models are tested for building damage characterization in this study?\",\"answer\":\"Six models are considered, combining regression- and classification-based approaches using random forest, gradient boosting, and extreme gradient boosting.\"},{\"question\":\"What input features are used to predict seismic damage?\",\"answer\":\"Structural features are taken either from all DaDO-provided attributes or from a reduced set (age, number of storeys, floor area, building height), with macroseismic intensity added as an input feature.\"},{\"question\":\"How is seismic damage per building determined and what is the main performance outcome?\",\"answer\":\"Damage per building is computed according to the EMS-98 scale based on observations after seven significant Italian earthquakes. Extreme gradient boosting classification is identified as the most efficient method, especially for traffic-light-based grouping.\"}]","Testing machine learning models for heuristic building damage assessment applied to the Italian Database of Observed Damage (DaDO) | PDF",1785731998,50,{"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},"testing-machine-learning-models-for-heuristic-building-damage-assessment-applied-to-the-italian-database-of-observed-damage-dado","",{"@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/testing-machine-learning-models-for-heuristic-building-damage-assessment-applied-to-the-italian-database-of-observed-damage-dado/120778/",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","2026-08-03",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},"Which machine learning models are tested for building damage characterization in this study?","Question",{"text":75,"@type":76},"Six models are considered, combining regression- and classification-based approaches using random forest, gradient boosting, and extreme gradient boosting.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"What input features are used to predict seismic damage?",{"text":80,"@type":76},"Structural features are taken either from all DaDO-provided attributes or from a reduced set (age, number of storeys, floor area, building height), with macroseismic intensity added as an input feature.",{"name":82,"@type":73,"acceptedAnswer":83},"How is seismic damage per building determined and what is the main performance outcome?",{"text":84,"@type":76},"Damage per building is computed according to the EMS-98 scale based on observations after seven significant Italian earthquakes. Extreme gradient boosting classification is identified as the most efficient method, especially for traffic-light-based grouping.","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},[93,97,101,105,110,114,119,122,126,129,133],{"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":29,"slug":113},6,"Technology","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":21,"slug":125},9,"Religion & Spirituality","religion-spirituality",{"id":21,"doc_module":4,"doc_module_name":46,"category_name":127,"show_sort_weight":21,"slug":128},"World Cup","world-cup",{"id":130,"doc_module":4,"doc_module_name":46,"category_name":131,"show_sort_weight":130,"slug":132},10,"Lifestyle","lifestyle",{"id":134,"doc_module":4,"doc_module_name":46,"category_name":135,"show_sort_weight":106,"slug":136},19,"General","general"]