[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-122630-en":3,"doc-seo-122630-105":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},122630,1099513958762,"Logic","https://ap-avatar.wpscdn.com/avatar/1000023916a998db790?x-image-process=image/resize,m_fixed,w_180,h_180&k=1784791008015729253",8,"Research & Report","Probabilistic and machine learning methods for uncertainty quantification in power outage prediction due to extreme events","Strong hurricane winds can damage power grids and trigger cascading failures, making outage severity prediction critical for emergency planning. The work reviews existing statistical and machine learning outage models, noting limited generalization when trained on data from only a few utilities and regions. It re-trains and validates those models using multi-region, multi-event outage records from 1910 US cities across hurricanes Harvey (2017), Michael (2018), and Isaias (2020). Findings show bounded predictions, high-wind extrapolation, and physics-informed uncertainty handling remain inadequate, including overprediction and underestimated variance above ~70 m s−1.","Nat. Hazards Earth Syst. Sci., 23, 1665–1683, 2023 [https://doi.org/10.5194/nhess-23-1665-2023](https://doi.org/10.5194/nhess-23-1665-2023)[ ](https://doi.org/10.5194/nhess-23-1665-2023)© Author(s) 2023 . This work is distributed under the Creative Commons Attribution 4 .0 License.  \nProbabilistic and machine learning methods for uncertainty quantification in power outage prediction due to extreme events  \nPrateek Arora 1 and Luis Ceferino 1,2  \n1 Civil and Urban Engineering Department, New York University, Brooklyn, NY 11201, USA  \n2 Center for Urban Science and Progress, New York University, Brooklyn, NY 11201, USA Correspondence: Prateek Arora ([prateek40.a@gmail.com](prateek40.a@gmail.com))  \nReceived: 22 September 2022 – Discussion started: 10 October 2022  \nRevised: 27 March 2023 – Accepted: 31 March 2023 – Published: 3 May 2023  \nAbstract. Strong hurricane winds damage power grids and cause cascading power failures. Statistical and machine learning models have been proposed to predict the extent of power disruptions due to hurricanes. Existing outage models use inputs including power system information, environmental parameters, and demographic parameters. This paper reviews the existing power outage models, highlighting their strengths and limitations. Existing models were developed and validated with data from a few utility companies and regions, limiting the extent of their applicability across geographies and hurricane events. Instead, we train and validate these existing outage models using power outages from multiple regions and hurricanes, including hurricanes Harvey (2017), Michael (2018), and Isaias (2020), in 1910 US cities. The dataset includes outages from 39 utility companies in Texas, 5 in Florida, 5 in New Jersey, and 11 in New York. We discuss the limited ability of state-of-the-art machine learning models to (1) make bounded outage predictions,(2) extrapolate predictions to high winds, and (3) account for physics-informed outage uncertainties at low and high winds. For example, we observe that existing models can predict outages higher than the number of customers (in 19.8 % of cities with an average overprediction ratio of 5.2) and cannot capture well the outage variance for high winds, especially above 70 m s􀀀1 . Our findings suggest that further developments are needed for power outage models for proper representation of hurricane-induced outages.  \n1 Introduction  \nHurricanes can cause significant damage to the power distribution systems, resulting in large power failures and losses  \nof billions of US dollars (Smith, 2020) . Strong winds from hurricanes can destroy the exposed overhead distribution lines in a power grid and cause cascading power failures. For example, Hurricane Isaias (2020) damaged old power infrastructure and caused more than 2 million power outages across the US. More than a million outages occurred in New Jersey ([https://www.nytimes.com/2020/08/](https://www.nytimes.com/2020/08/)[ ](https://www.nytimes.com/2020/08/)[04/nyregion/isaias-ny.html](04/nyregion/isaias-ny.html), [last access: 21 September 2022](last access: 21 September 2022)) even though Hurricane Isaias had transitioned to a tropical storm when it hit New Jersey, reducing its sustained winds to 25 m s􀀀1 (Latto et al., 2021) . To address this issue, the US Department of Energy (DOE) has prioritized investing in enhancing power infrastructure resilience (National Academies of Sciences, Engineering, and Medicine, 2017) . The Senate of the US passed the Grid Research Security Research and Development Act (2020) with a budget of 573 million US dollars to be spent from 2020–2025 to improve grid security to withstand shocks and rapidly recover from disruptions ([Congress.gov](Congress.gov), 2020).  \nHurricane-induced power interruptions can cause billions of dollars in losses and long-lasting impacts on vulnerable communities. The power outages caused by storms can last for several hours to weeks and even months ([https://ww","cbCaiuIgfkOyMor7","https://ap.wps.com/l/cbCaiuIgfkOyMor7","pdf",4601526,1,19,"English","en",105,"# Abstract\n# Introduction\n## Motivation: hurricane-driven cascading power failures\n## Need for improved outage prediction models","[{\"question\":\"What limitation of existing outage models is highlighted in the paper?\",\"answer\":\"Existing models are often trained and validated using data from only a few utilities and regions, which restricts applicability across different geographies and hurricane events.\"},{\"question\":\"How does the paper improve evaluation of outage prediction models?\",\"answer\":\"It trains and validates existing outage models using outage data from multiple regions and multiple hurricanes, covering 1910 US cities.\"},{\"question\":\"What problems do the authors observe for machine learning models at high winds?\",\"answer\":\"The study reports limited ability to extrapolate to high winds and to capture outage variance, with evidence such as overprediction (and inability to represent variance well above about 70 m s−1).\"}]","Probabilistic and machine learning methods for uncertainty quantification in power outage prediction due to extreme events | PDF",1785811818,48,{"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},"probabilistic-and-machine-learning-methods-for-uncertainty-quantification-in-power-outage-prediction-due-to-extreme-events","",{"@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/probabilistic-and-machine-learning-methods-for-uncertainty-quantification-in-power-outage-prediction-due-to-extreme-events/122630/",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},"What limitation of existing outage models is highlighted in the paper?","Question",{"text":75,"@type":76},"Existing models are often trained and validated using data from only a few utilities and regions, which restricts applicability across different geographies and hurricane events.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"How does the paper improve evaluation of outage prediction models?",{"text":80,"@type":76},"It trains and validates existing outage models using outage data from multiple regions and multiple hurricanes, covering 1910 US cities.",{"name":82,"@type":73,"acceptedAnswer":83},"What problems do the authors observe for machine learning models at high winds?",{"text":84,"@type":76},"The study reports limited ability to extrapolate to high winds and to capture outage variance, with evidence such as overprediction (and inability to represent variance well above about 70 m s−1).","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":21,"doc_module":4,"doc_module_name":46,"category_name":136,"show_sort_weight":106,"slug":137},"General","general"]