[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-124582-en":3,"doc-seo-124582-105":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},124582,1099513958762,"Logic","https://ap-avatar.wpscdn.com/avatar/1000023916a998db790?x-image-process=image/resize,m_fixed,w_180,h_180&k=1784791008015729253",8,"Research & Report","Improved extended-range prediction of persistent stratospheric perturbations using machine learning","Sudden stratospheric warmings (SSWs) produce extreme perturbations of the polar vortex roughly every two years, and their influence extends beyond the stratosphere to affect surface weather for up to three months, especially when recovery is prolonged. The study introduces a fully data-driven workflow to enhance long-range stratospheric forecasts around extended-recovery SSWs. It uses unsupervised machine learning to extract spatio-temporal dynamics, builds a continuous scale index for persistence, identifies statistically significant early signals through 3D spatial pattern correlations, and compares two ML forecasting models with the ECMWF S2S numerical system, including post-processing that improves ensemble skill by up to 20%.","Weather Clim. Dynam., 4, 287–307, 2023 [https://doi.org/10.5194/wcd-4-287-2023](https://doi.org/10.5194/wcd-4-287-2023)[ ](https://doi.org/10.5194/wcd-4-287-2023)© Author(s) 2023 . This work is distributed under the Creative Commons Attribution 4 .0 License.  \nImproved extended-range prediction of persistent stratospheric perturbations using machine learning  \nRaphaël de Fondeville 1 , Zheng Wu2 , Enik Székely 1 , Guillaume Obozinski 1 , and Daniela I. V. Domeisen3,2  \n1 Swiss Data Science Center, ETH Zurich and EPFL, Lausanne, Switzerland  \n2Institute for Atmospheric and Climate Science, ETH Zurich, Zurich, Switzerland  \n3Institute of Earth Surface Dynamics, Université de Lausanne, Lausanne, Switzerland Correspondence: Raphaël de Fondeville ([raphael.de-fondeville@ep](raphael.de-fondeville@ep)fl.ch)  \nReceived: 4 October 2022 – Discussion started: 6 October 2022  \nRevised: 16 February 2023 – Accepted: 4 March 2023 – Published: 4 April 2023  \nAbstract. On average every 2 years, the stratospheric polar vortex exhibits extreme perturbations known as sudden stratospheric warmings (SSWs) . The impact of these events is not limited to the stratosphere: but they can also influence the weather at the surface of the Earth for up to 3 months after their occurrence. This downward effect is observed in particular for SSW events with extended recovery timescales. This long-lasting stratospheric impact on surface weather can be leveraged to significantly improve the performance of weather forecasts on timescales of weeks to months. In this paper, we present a fully data-driven procedure to improve the performance of long-range forecasts of the stratosphere around SSW events with an extended recovery. We first use unsupervised machine learning algorithms to capture the spatio-temporal dynamics of SSWs and to create a continuous scale index measuring both the frequency and the strength of persistent stratospheric perturbations. We then uncover three-dimensional spatial patterns maximizing the correlation with positive index values, allowing us to assess when and where statistically significant early signals of SSW occurrence can be found. Finally, we propose two machine learning (ML) forecasting models as competitors for the state-of-the-art sub-seasonal European Centre for MediumRange Weather Forecasts (ECMWF) numerical prediction model S2S (sub-seasonal to seasonal): while the numerical model performs better for lead times of up to 25 d, the ML models offer better predictive performance for greater lead times. We leverage our best-performing ML forecasting model to successfully post-process numerical ensemble forecasts and increase their performance by up to 20 % .  \n1 Introduction  \nIn both hemispheres and during winter, the atmosphere above the polar regions is characterized by eastward winds centered around the poles with a mid-winter peak in wind intensity, the so-called “polar vortex”. On average once every 2 years, in the Northern Hemisphere, upwardly propagating Rossby waves can disturb the polar vortex and induce a sudden warming of the polar stratosphere. Known as sudden stratospheric warmings (SSWs; Baldwin et al., 2021), these events not only impact the stratosphere but also strongly influence the weather at the Earth's surface for up to 3 months after their occurrence (Baldwin and Dunkerton, 2001) . Therefore, SSW events are considered an important source of predictability of surface weather on sub-seasonal timescales ranging from 2 weeks to 2 months. Improving the prediction of SSW events may therefore help enhance the forecast performance of surface weather (Sigmond et al., 2013 ; Domeisen et al., 2020a) .  \nThe dynamics behind SSWs are not yet fully understood (Baldwin et al., 2021), and hundreds of contributions have been made on the topic, including for instance a classification of stratospheric perturbations based on their influenceon the troposphere to uncover common dynamical precursors (Runde et al., 2016) or the quantification","cbCaia7M0cjSsB70","https://ap.wps.com/l/cbCaia7M0cjSsB70","pdf",16337113,1,21,"English","en",105,"# Introduction\n## Polar vortex and sudden stratospheric warmings\n## Predictability limits and motivation\n## Persistent events and their surface impact\n## Data-driven approach and forecasting framework","[{\"question\":\"What problem does the paper address for weather forecasting?\",\"answer\":\"It targets improved prediction of long-range surface and stratospheric impacts associated with SSW events that have extended recovery timescales, where predictability can last weeks to months.\"},{\"question\":\"How does the method detect persistent stratospheric perturbations?\",\"answer\":\"It uses unsupervised machine learning to learn spatio-temporal dynamics of SSWs and constructs a continuous scale index capturing both the frequency and the strength of persistent perturbations.\"},{\"question\":\"How do the machine learning models compare with the ECMWF S2S numerical model?\",\"answer\":\"For lead times up to about 25 days, the numerical model performs better, while the ML models provide better predictive performance for longer lead times; the best ML model also post-processes numerical ensembles and increases performance by up to 20%.\"}]","Improved extended-range prediction of persistent stratospheric perturbations using machine learning | PDF",1785893144,53,{"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},"improved-extended-range-prediction-of-persistent-stratospheric-perturbations-using-machine-learning","",{"@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/improved-extended-range-prediction-of-persistent-stratospheric-perturbations-using-machine-learning/124582/",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","2026-08-05",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 problem does the paper address for weather forecasting?","Question",{"text":75,"@type":76},"It targets improved prediction of long-range surface and stratospheric impacts associated with SSW events that have extended recovery timescales, where predictability can last weeks to months.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"How does the method detect persistent stratospheric perturbations?",{"text":80,"@type":76},"It uses unsupervised machine learning to learn spatio-temporal dynamics of SSWs and constructs a continuous scale index capturing both the frequency and the strength of persistent perturbations.",{"name":82,"@type":73,"acceptedAnswer":83},"How do the machine learning models compare with the ECMWF S2S numerical model?",{"text":84,"@type":76},"For lead times up to about 25 days, the numerical model performs better, while the ML models provide better predictive performance for longer lead times; the best ML model also post-processes numerical ensembles and increases performance by up to 20%.","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"]