[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-119045-en":3,"doc-seo-119045-105":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},119045,137441390410,"Hazel","https://ap-avatar.wpscdn.com/avatar/2000252f4ab5702993?_k=1776741390130283984",8,"Research & Report","Machine Learning Estimation of Maximum Vertical Velocity from Radar - Estimating storm updrafts from 3D radar reflectivity using U-Nets","Quantifying storm updrafts remains unavailable for operational forecasting despite their central role in convection and severe weather hazards. Proxies such as overshooting top area capture only part of the total updraft. This study tests whether U-Net based machine learning can retrieve maximum vertical velocity and its areal extent from 3D gridded radar reflectivity alone. Models are trained on simulated radar using WoFS convection-permitting outputs and adapted with sinh-arcsinh-normal regression for deterministic and probabilistic predictions, then evaluated against independent WoFS tests and real dual-Doppler cases.","arXiv :2310 .09392v2 [ cs .LG] 25 Jan 2024  \nGenerated using the official AMS LATEX template v6.1 two-column layout. This work has been submitted for publication. Copyright in this work may be transferred without further notice, and this version may no longer be accessible.  \nMachine Learning Estimation of Maximum Vertical Velocity from Radar  \nRandy J. Chase a,b,c , Amy McGoverna,b,c , Cameron R. Homeyerb , Peter J. Marinescud , Corey K. Potvinb,c,e  \na School of Computer Science, University of Oklahoma, Norman OK USA  \nb School of Meteorology, University of Oklahoma, Norman OK USA  \nc NSFAI Institute for Research on Trustworthy AI in Weather, Climate, and Coastal Oceanography, University of Oklahoma, Norman OK  \nUSA  \nd Department of Atmospheric Science, Colorado State University, Fort Collins CO USA  \ne National Severe Storms Laboratory, Norman, Oklahoma  \nABSTRACT: The quantification of storm updrafts remains unavailable for operational forecasting despite their inherent importance to convection and its associated severe weather hazards. Updraft proxies, like overshooting top area from satellite images, have been linked to severe weather hazards but only relate to a limited portion of the total storm updraft. This study investigates if a machine learning model, namely U-Nets, can skillfully retrieve maximum vertical velocity and its areal extent from 3-dimensional gridded radar reflectivity alone. The machine learning model is trained using simulated radar reflectivity and vertical velocity from the National Severe Storm Laboratory’s convection permitting Warn on Forecast System (WoFS) . A parametric regression technique using the sinh-arcsinh-normal distribution is adapted to run with U-Nets, allowing for both deterministic and probabilistic predictions of maximum vertical velocity. The best models after hyperparameter search provided less than 50% root mean squared error, a coefficient of determination greater than 0.65 and an intersection over union (IoU) of more than 0.45 on the independent test set composed of WoFS data. Beyond the WoFS analysis, a case study was conducted using real radar data and corresponding dual-Doppler analyses of vertical velocity within a supercell. The U-Net consistently underestimates the dual-Doppler updraft speed estimates by 50% . Meanwhile, the area of the 5 and 10 m s−1 updraft cores show an IoU of 0.25 . While the above statistics are not exceptional, the machine learning model enables quick distillation of 3D radar data that is related to the maximum vertical velocity which could be useful in assessing a storm’s severe potential.  \nSIGNIFICANCE STATEMENT: All convective storm hazards (tornadoes, hail, heavy rain, straight line winds) can be related to a storm’s updraft. Yet, there is no direct measurement of updraft speed or area available for forecasters to make their warning decisions off of. This paper addresses the lack of observational data by providing a machine learning solution that skillfully estimates the maximum updraft speed within storms from only the radar reflectivity 3D structure. After further vetting the machine learning solutions on additional real world examples, the estimated storm updrafts will hopefully provide forecasters with an added tool to help diagnose a storms hazard potential more accurately.  \nCorresponding author: Randy J. Chase, [randy.chase@colostate.edu](randy.chase@colostate.edu)  \n2  \n1. Introduction  \nWeather hazards in the United States cost billions of dollars annually (NCEI 2023) . A majority of the billiondollar disaster events involve hazards directly created by convective storms (e.g., hail, tornadoes, floods, straightline winds) . Convective weather hazards are ultimately connected to the fast current of upward moving air, also known as an updraft. Despite the updraft’s importance in convective storms, an updraft’s intensity or area is not something that is reliably quantified in real time to be used as a forecasting tool for assessing sto","cbCaip7ZUEf1x0z6","https://ap.wps.com/l/cbCaip7ZUEf1x0z6","pdf",5795994,1,19,"English","en",105,"# Abstract\n# Significance Statement\n# 1. Introduction\n## Updrafts and operational limitations\n## Multi-Doppler radar retrieval challenges\n## Existing updraft proxy methods\n# 2. Method Overview\n## U-Net based retrieval from 3D reflectivity\n## Training with WoFS simulated data\n## Deterministic and probabilistic regression","[{\"question\":\"Why are direct measurements of storm updraft speed difficult for forecasters?\",\"answer\":\"Operational systems do not provide reliable real-time quantification of updraft intensity or area. Multi-Doppler retrievals require favorable radar coverage and are sensitive to artifacts, often demanding expert quality control.\"},{\"question\":\"How does the study estimate maximum vertical velocity from radar data?\",\"answer\":\"A U-Net machine learning model is trained to retrieve maximum vertical velocity and its areal extent using only 3D gridded radar reflectivity structure. The approach uses simulated training data from WoFS and a regression adaptation to support deterministic and probabilistic outputs.\"},{\"question\":\"How were the model results evaluated?\",\"answer\":\"Performance was assessed on an independent WoFS test set using metrics such as root mean squared error, coefficient of determination, and intersection over union. A real-data case study using dual-Doppler vertical velocity analysis further examined errors and overlap for updraft cores.\"}]","Machine Learning Estimation of Maximum Vertical Velocity from Radar - Estimating storm updrafts from 3D radar reflectivity using U-Nets | PDF",1785722074,48,{"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},"machine-learning-estimation-of-maximum-vertical-velocity-from-radar-estimating-storm-updrafts-from-3d-radar-reflectivity-using-u-nets","",{"@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-estimation-of-maximum-vertical-velocity-from-radar-estimating-storm-updrafts-from-3d-radar-reflectivity-using-u-nets/119045/",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},"Why are direct measurements of storm updraft speed difficult for forecasters?","Question",{"text":75,"@type":76},"Operational systems do not provide reliable real-time quantification of updraft intensity or area. Multi-Doppler retrievals require favorable radar coverage and are sensitive to artifacts, often demanding expert quality control.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"How does the study estimate maximum vertical velocity from radar data?",{"text":80,"@type":76},"A U-Net machine learning model is trained to retrieve maximum vertical velocity and its areal extent using only 3D gridded radar reflectivity structure. The approach uses simulated training data from WoFS and a regression adaptation to support deterministic and probabilistic outputs.",{"name":82,"@type":73,"acceptedAnswer":83},"How were the model results evaluated?",{"text":84,"@type":76},"Performance was assessed on an independent WoFS test set using metrics such as root mean squared error, coefficient of determination, and intersection over union. A real-data case study using dual-Doppler vertical velocity analysis further examined errors and overlap for updraft cores.","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"]