{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,30]],"date-time":"2026-09-30T00:58:11Z","timestamp":1790729891879,"version":"4.1.0"},"reference-count":54,"publisher":"Wiley","issue":"6","license":[{"start":{"date-parts":[[2026,5,26]],"date-time":"2026-05-26T00:00:00Z","timestamp":1779753600000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/onlinelibrary.wiley.com\/termsAndConditions#vor"},{"start":{"date-parts":[[2026,5,26]],"date-time":"2026-05-26T00:00:00Z","timestamp":1779753600000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/doi.wiley.com\/10.1002\/tdm_license_1.1"}],"content-domain":{"domain":["onlinelibrary.wiley.com"],"crossmark-restriction":true},"short-container-title":["Risk Analysis"],"published-print":{"date-parts":[[2026,6]]},"abstract":"<jats:title>ABSTRACT<\/jats:title>\n                  <jats:p>Power outages caused by tropical cyclones (TCs) pose serious risks to electric power systems and the communities they serve. Accurate, high\u2010resolution outage forecasting is therefore critical for both proactive mitigation planning and real\u2010time emergency response. Most existing outage prediction models operate in open\u2010loop or event\u2010level settings and cannot update forecasts as storm conditions and system states evolve. To address this limitation, we propose the SpatioTemporal Outage ForeCAST (STO\u2010CAST) model, a spatiotemporal deep learning framework that performs state\u2010dependent, observation\u2010updated rolling inference throughout TC events. STO\u2010CAST enables outage forecasts to evolve in response to updated meteorological projections and newly observed outage information during runtime. The model integrates static environmental and infrastructure attributes with dynamic meteorological and outage sequences and produces hourly outage forecasts at a 4\u00a0km by 4\u00a0km resolution. STO\u2010CAST supports dual\u2010horizon forecasting, providing short\u2010term nowcasting with a 6\u2010hour lead time for real\u2010time situational awareness and long\u2010term forecasting with a 60\u2010hour lead time to inform proactive planning and resource staging. A case study of Typhoon Muifa (2022), evaluated under a Leave\u2010One\u2010Storm\u2010Out framework, demonstrates the model's operational value, including its ability to track evolving outage hotspots and to provide diagnostic insight through error decomposition that distinguishes the effects of model limitations, meteorological uncertainty, and observation gaps. Overall, STO\u2010CAST offers a scalable and interpretable framework to support risk\u2010informed emergency response and enhance power system resilience under intensifying TC threats.<\/jats:p>","DOI":"10.1111\/risa.70275","type":"journal-article","created":{"date-parts":[[2026,5,26]],"date-time":"2026-05-26T10:04:16Z","timestamp":1779789856000},"update-policy":"https:\/\/doi.org\/10.1002\/crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["From Forecast to Action: A Deep Learning Model for Predicting Power Outages During Tropical Cyclones"],"prefix":"10.1111","volume":"46","author":[{"given":"Yongchuan","family":"Yang","sequence":"first","affiliation":[{"name":"College of Civil Engineering and Architecture Zhejiang University  Hangzhou China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4167-1084","authenticated-orcid":false,"given":"Naiyu","family":"Wang","sequence":"additional","affiliation":[{"name":"College of Civil Engineering and Architecture Zhejiang University  Hangzhou China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhenguo","family":"Wang","sequence":"additional","affiliation":[{"name":"State Grid Zhejiang Electric Power Co., Ltd., Electric Power Research Institute  Hangzhou China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Min","family":"Ouyang","sequence":"additional","affiliation":[{"name":"School of Artificial Intelligence and Automation Huazhong University of Science and Technology  Wuhan China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Can","family":"Wan","sequence":"additional","affiliation":[{"name":"College of Electrical Engineering Zhejiang University  Hangzhou China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"311","published-online":{"date-parts":[[2026,5,26]]},"reference":[{"key":"e_1_2_9_2_1","doi-asserted-by":"crossref","unstructured":"Abaas M. R. A.Lee andP.Singh.2022. \u201cLong Short\u2010Term Memory Customer\u2010Centric Power Outage Prediction Models for Weather\u2010Related Power Outages.\u201d 2022 IEEE Green Energy and Smart Systems (IGESSC).","DOI":"10.1109\/IGESSC55810.2022.9955338"},{"key":"e_1_2_9_3_1","doi-asserted-by":"publisher","DOI":"10.3390\/rs12071156"},{"key":"e_1_2_9_4_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-82435-7_26"},{"key":"e_1_2_9_5_1","doi-asserted-by":"publisher","DOI":"10.3390\/forecast2020008"},{"key":"e_1_2_9_6_1","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2019.2902558"},{"key":"e_1_2_9_7_1","unstructured":"Chung J. \u00c7.G\u00fcl\u00e7ehre K.Cho andY.Bengio.2014. \u201cEmpirical Evaluation of Gated Recurrent Neural Networks on Sequence Modeling.\u201d ArXiv.https:\/\/doi.org\/10.48550\/arXiv.1412.3555."},{"key":"e_1_2_9_8_1","unstructured":"Dai X.2023. \u201cFujian Power Sector Undertakes Emergency Repairs in Response to Typhoon \u2018Doksuri\u2019; Over 80% of Affected Users Have Regained Power Supply.\u201dXinHuaNet. Accessed May 23 2026.http:\/\/www.news.cn\/2023\u201007\/30\/c_1129776514.htm."},{"key":"e_1_2_9_9_1","doi-asserted-by":"publisher","DOI":"10.1061\/(ASCE)1527\u20106988(2003)4:1(36)"},{"key":"e_1_2_9_10_1","unstructured":"Donald J. B. andC.James.1994. \u201cUsing Dynamic Time Warping to Find Patterns in Time Series.\u201d InProceedings of the 3rd International Conference on Knowledge Discovery and Data Mining (AAAIWS'94) 359\u2013370.AAAI Press."},{"key":"e_1_2_9_11_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11263\u2010009\u20100275\u20104"},{"key":"e_1_2_9_12_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.engappai.2024.108056"},{"key":"e_1_2_9_13_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.scib.2019.03.002"},{"key":"e_1_2_9_14_1","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2014.2365716"},{"key":"e_1_2_9_15_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.ress.2011.10.012"},{"key":"e_1_2_9_16_1","doi-asserted-by":"publisher","DOI":"10.1111\/j.1539\u20106924.2009.01280.x"},{"key":"e_1_2_9_17_1","unstructured":"Holcombe M. H.Yan andE.Levenson.2021. \u201cIda Left More Than 1 Million Without Power Possibly for Weeks. And Now Comes the Scorching Heat.\u201dCable News Network. Accessed May 23 2026.https:\/\/edition.cnn.com\/2021\/08\/31\/weather\/tropical\u2010depression\u2010ida\u2010tuesday\/index.html."},{"key":"e_1_2_9_18_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.ress.2023.109398"},{"key":"e_1_2_9_19_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.epsr.2022.108098"},{"key":"e_1_2_9_20_1","unstructured":"Hu J.2022. \u201cPower Supply Has Been Restored in Zhejiang After Typhoon Muifa.\u201dHangzhou News.https:\/\/news.hangzhou.com.cn\/zjnews\/content\/2022\u201009\/15\/content_8354393.htm."},{"key":"e_1_2_9_21_1","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2024.3355484"},{"key":"e_1_2_9_22_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.ress.2023.109731"},{"key":"e_1_2_9_23_1","doi-asserted-by":"publisher","DOI":"10.1214\/aoms\/1177703732"},{"key":"e_1_2_9_24_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.ress.2022.108628"},{"key":"e_1_2_9_25_1","doi-asserted-by":"publisher","DOI":"10.1111\/risa.14211"},{"key":"e_1_2_9_26_1","unstructured":"Kingma D. P. andJ.Ba.2014. \u201cAdam: A Method for Stochastic Optimization.\u201dArXiv.https:\/\/doi.org\/10.48550\/arXiv.1412.6980."},{"key":"e_1_2_9_27_1","doi-asserted-by":"publisher","DOI":"10.1145\/3065386"},{"key":"e_1_2_9_28_1","doi-asserted-by":"publisher","DOI":"10.1061\/(ASCE)1076\u20100342(2005)11:4(258)"},{"key":"e_1_2_9_29_1","unstructured":"Lundberg S. M. andS.\u2010I.Lee.2017.A Unified Approach to Interpreting Model Predictions Proceedings of the 31st International Conference on Neural Information Processing Systems Long Beach California USA."},{"key":"e_1_2_9_30_1","doi-asserted-by":"publisher","DOI":"10.1109\/TSG.2016.2591885"},{"key":"e_1_2_9_31_1","doi-asserted-by":"publisher","DOI":"10.1111\/risa.12728"},{"key":"e_1_2_9_32_1","unstructured":"Micek K. J. R.Corey Paul andR.Turner.2024. \u201cHurricane Helene Causes Over 4.7 Million Power Outages Across Southeast US.\u201dS&P Global. Accessed May 23 2026.https:\/\/www.spglobal.com\/commodityinsights\/en\/market\u2010insights\/latest\u2010news\/electric\u2010power\/092724\u2010hurricane\u2010helene\u2010causes\u2010over\u201047\u2010million\u2010power\u2010outages\u2010across\u2010southeast\u2010us#:~:text=Hurricane%20Helene%20causes%20over%204.7%20million%20power%20outages%20across%20Southeast%20US \u2010Author%20Kassia%20Micek&text=Nearly%204.7%20million%20customers%20were%20without%20power%20across%20the%20Southeastern%20US%20Sept."},{"key":"e_1_2_9_33_1","doi-asserted-by":"publisher","DOI":"10.1175\/WAF\u2010D\u201012\u201000050.1"},{"key":"e_1_2_9_34_1","volume-title":"The Equivalence of Logistic Regression and Maximum Entropymodels","author":"Mount J.","year":"2011"},{"key":"e_1_2_9_35_1","doi-asserted-by":"publisher","DOI":"10.1111\/risa.12131"},{"issue":"24","key":"e_1_2_9_36_1","first-page":"7735","article-title":"Keeping the Country Running: Natural Hazards and Infrastructure: A Guide to Improving the Resilience of Critical Infrastructure and Essential Services","volume":"79","author":"Office G. B. C.","year":"2011","journal-title":"Applied & Environmental Microbiology"},{"key":"e_1_2_9_37_1","doi-asserted-by":"publisher","DOI":"10.1109\/JPROC.2017.2691357"},{"key":"e_1_2_9_38_1","first-page":"13","article-title":"Electricity Consumption in Rural vs. Urban Areas","volume":"7","author":"Petersen H. C.","year":"1982","journal-title":"Western Journal of Agricultural Economics"},{"key":"e_1_2_9_39_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.ijepes.2025.110811"},{"key":"e_1_2_9_40_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11069\u2010010\u20109672\u20109"},{"key":"e_1_2_9_41_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.ress.2015.07.028"},{"key":"e_1_2_9_42_1","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2018.2877078"},{"key":"e_1_2_9_43_1","first-page":"802","volume-title":"Neural Information Processing Systems","author":"Shi X.","year":"2015"},{"key":"e_1_2_9_44_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.ijepes.2021.107545"},{"key":"e_1_2_9_45_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.ijepes.2022.108296"},{"key":"e_1_2_9_46_1","doi-asserted-by":"publisher","DOI":"10.1016\/B978-0-12-821204-2.00077-5"},{"key":"e_1_2_9_47_1","doi-asserted-by":"publisher","DOI":"10.1111\/risa.12552"},{"key":"e_1_2_9_48_1","doi-asserted-by":"crossref","unstructured":"Udeh K. D. W.Wanik D.Cerrai D.Aguiar andE.Anagnostou.2022. \u201cAutoregressive Modeling of Utility Customer Outages With Deep Neural Networks.\u201d2022 IEEE 12th Annual Computing and Communication Workshop and Conference (CCWC).","DOI":"10.1109\/CCWC54503.2022.9720799"},{"key":"e_1_2_9_49_1","unstructured":"Wang Y.2024. \u201cA Dataset of Typhoon Tracks in Offshore China (1945\u20132023).\u201dIOCAS.https:\/\/doi.org\/10.12157\/IOCAS.20210804.001."},{"key":"e_1_2_9_50_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11069-015-1908-2"},{"key":"e_1_2_9_51_1","doi-asserted-by":"publisher","DOI":"10.1049\/joe.2019.1274"},{"key":"e_1_2_9_52_1","doi-asserted-by":"publisher","DOI":"10.3390\/forecast3030031"},{"key":"e_1_2_9_53_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.ijepes.2019.105711"},{"key":"e_1_2_9_54_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.ress.2020.107348"},{"key":"e_1_2_9_55_1","doi-asserted-by":"publisher","DOI":"10.1049\/rpg2.12996"}],"container-title":["Risk Analysis"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/pdf\/10.1111\/risa.70275","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/full-xml\/10.1111\/risa.70275","content-type":"application\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/pdf\/10.1111\/risa.70275","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,6,29]],"date-time":"2026-06-29T06:39:01Z","timestamp":1782715141000},"score":1,"resource":{"primary":{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/10.1111\/risa.70275"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,5,26]]},"references-count":54,"journal-issue":{"issue":"6","published-print":{"date-parts":[[2026,6]]}},"alternative-id":["10.1111\/risa.70275"],"URL":"https:\/\/doi.org\/10.1111\/risa.70275","archive":["Portico"],"relation":{},"ISSN":["0272-4332","1539-6924"],"issn-type":[{"value":"0272-4332","type":"print"},{"value":"1539-6924","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,5,26]]},"assertion":[{"value":"2025-02-28","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2026-05-19","order":2,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2026-05-26","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}],"article-number":"e70275"}}