[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-128023-en":3,"doc-seo-128023-105":30,"detail-sidebar-cat-0-en-105":92},{"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":20,"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},128023,962084931830,"Theodore","https://ap-avatar.wpscdn.com/davatar_a8503ba1806abce46bf441b54a3ca4cd",8,"Research & Report","Identifying Ocean Submesoscale Activity From Vertical Density Profiles Using Machine Learning - research article","Submesoscale eddies play a key role in the upper ocean by mediating air-sea exchanges, transporting heat and tracers downward, and enhancing biological production. Their small horizontal scales and brief lifetimes make field observations difficult with standard survey resolutions. Submesoscales modify the upper-ocean vertical density stratification and shape the vertical density profile. This work introduces an unsupervised machine-learning approach that identifies submesoscale activity from vertical density profiles alone, using a PCM-based profile-classification model trained on two distinct model data sets.","RESEARCH ARTICLE  \n10.1029/2022EA002618  \nKey Points:  \n• A machine learning algorithm is used to identify the signature of submesoscale eddies in the ocean  \n• The method is applied to two model data set and shown to be a good predictor of submesoscale activity  \n• The advantage of the method is that it can be applied to vertical density profiles without needing information about horizontal variation  \nCorrespondence to:  \nJ. R. Taylor,  \n[j.r.taylor@damtp.cam.ac.uk](j.r.taylor@damtp.cam.ac.uk)  \nCitation:  \nYao, L., Taylor, J. R., Jones, D. C., & Bachman, S. D. (2025) . Identifying ocean submesoscale activity from vertical density profiles using machine learning. Earth and Space Science, 12, e2022EA002618. [https://doi.org/10.1029/](https://doi.org/10.1029/)[ ](https://doi.org/10.1029/)2022EA002618  \nReceived 24 FEB 2023 Accepted 2 JAN 2025  \nAuthor Contributions:  \nConceptualization: Leyu Yao, John  \nR. Taylor  \nData curation: Scott D. Bachman  \nFormal analysis: John R. Taylor  \nInvestigation: Leyu Yao  \nMethodology: Leyu Yao  \nSupervision: John R. Taylor, Dani  \nC. Jones  \nVisualization: Leyu Yao  \nWriting – original draft: Leyu Yao, John R. Taylor  \nWriting – review & editing: Leyu Yao, John R. Taylor, Dani C. Jones, Scott  \nD. Bachman  \n© 2025. The Author(s) .  \nThis is an open access article under the terms of the Creative Commons Attribution License, which permits use, distribution and reproduction in any medium, provided the original work is properly cited.  \nIdentifying Ocean Submesoscale Activity From Vertical Density Profiles Using Machine Learning  \nLeyu Yao1, John R. Taylor1 , Dani C. Jones2,3, and Scott D. Bachman4   \n1Department of Applied Mathematics and Theoretical Physics, University of Cambridge, Cambridge, UK, 2Cooperative Institute for Great Lakes Research (CIGLR), University of Michigan, Ann Arbor, MI, USA, 3British Antarctic Survey, NERC, UKRI, Cambridge, UK, 4National Center for Atmospheric Research, Boulder, CO, USA  \nAbstract Submesoscale eddies are important features in the upper ocean where they mediate air‐sea exchanges, convey heat and tracer fluxes into ocean interior, and enhance biological production. However, due to their small size (0.1–10 km) and short lifetime (hours to days), directly observing submesoscales in the field generally requires targeted high resolution surveys. Submesoscales increase the vertical density stratification of the upper ocean and qualitatively modify the vertical density profile. In this paper, we propose an unsupervised machine learning algorithm to identify submesoscale activity using vertical density profiles. The algorithm, based on the profile classification model (PCM) approach, is trained and tested on two model‐based data sets with vastly different resolutions. One data set is extracted from a large‐eddy simulation (LES) in a 4 km by 4 km domain and the other from a regional model for a sector in the Southern Ocean. We show that the adapted PCM can identify regions with high submesoscale activity, as characterized by the vorticity field (i.e., where surface vertical vorticity ζ is similar to Coriolis frequency f and Rossby number Ro = ζ/f ∼ O(1)), using solely the vertical density profiles, without any additional information on the velocity, the profile location, or horizontal density gradients. The results of this paper show that the adapted PCM can be applied to data sets from different sources and provides a method to study submesoscale eddies using global data sets (e.g., CTD profiles collected from ships, gliders, and Argo floats) .  \nPlain Language Summary In this paper we describe a new method based on Machine Learning techniques for identifying the tell‐tale signatures of submesoscale (1–10 km) eddies from individual density profiles. Our method is based on the hypothesis that submesoscale eddies alter the shape of the buoyancy profile within the surface mixed layer. We start by re‐scaling (normalizing) buoyancy and depth within the mixed layer so t","cbCaimZ2Yk2LXi0Y","https://ap.wps.com/l/cbCaimZ2Yk2LXi0Y","pdf",6021792,1,18,"English","en",105,"# Key Points\n# Abstract\n# Plain Language Summary\n# Introduction","[{\"question\":\"Why are submesoscale eddies difficult to observe directly in the field?\",\"answer\":\"They are small-scale features (about 0.1–10 km) with short lifetimes (hours to days), which typically requires targeted high-resolution surveys to capture them.\"},{\"question\":\"What data does the proposed method use to detect submesoscale activity?\",\"answer\":\"It uses only vertical density profiles, with the algorithm trained to classify the normalized buoyancy-profile shape within the mixed layer.\"},{\"question\":\"How does the method relate its classifications to physical submesoscale dynamics?\",\"answer\":\"The detected regions of high submesoscale activity are characterized by vorticity behavior where surface vertical vorticity ζ is comparable to the Coriolis frequency f (Rossby number Ro = ζ/f ~ O(1)).\"}]","Identifying Ocean Submesoscale Activity From Vertical Density Profiles Using Machine Learning - research article | PDF",1785944018,45,{"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":87,"head_meta":89,"extra_data":91,"updated_unix":28},"identifying-ocean-submesoscale-activity-from-vertical-density-profiles-using-machine-learning-research-article","",{"@graph":36,"@context":86},[37,54,69],{"@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/identifying-ocean-submesoscale-activity-from-vertical-density-profiles-using-machine-learning-research-article/128023/",4,{"url":52,"name":13,"@type":55,"author":56,"headline":13,"publisher":58,"fileFormat":61,"inLanguage":23,"description":14,"dateModified":62,"datePublished":63,"encodingFormat":61,"isAccessibleForFree":64,"interactionStatistic":65},"DigitalDocument",{"name":9,"@type":57},"Person",{"url":41,"name":59,"@type":60},"DocShare","Organization","application/pdf","2026-08-24","2026-08-05",true,{"@type":66,"interactionType":67,"userInteractionCount":20},"InteractionCounter",{"@type":68},"ViewAction",{"@type":70,"mainEntity":71},"FAQPage",[72,78,82],{"name":73,"@type":74,"acceptedAnswer":75},"Why are submesoscale eddies difficult to observe directly in the field?","Question",{"text":76,"@type":77},"They are small-scale features (about 0.1–10 km) with short lifetimes (hours to days), which typically requires targeted high-resolution surveys to capture them.","Answer",{"name":79,"@type":74,"acceptedAnswer":80},"What data does the proposed method use to detect submesoscale activity?",{"text":81,"@type":77},"It uses only vertical density profiles, with the algorithm trained to classify the normalized buoyancy-profile shape within the mixed layer.",{"name":83,"@type":74,"acceptedAnswer":84},"How does the method relate its classifications to physical submesoscale dynamics?",{"text":85,"@type":77},"The detected regions of high submesoscale activity are characterized by vorticity behavior where surface vertical vorticity ζ is comparable to the Coriolis frequency f (Rossby number Ro = ζ/f ~ O(1)).","https://schema.org",{"og:url":52,"og:type":88,"og:title":13,"og:site_name":59,"og:description":14},"article",{"robots":90,"canonical":52},"index,follow",{"doc_id":7,"site_id":24},{"code":4,"msg":5,"data":93},[94,98,102,106,111,116,121,124,129,132,136],{"id":20,"doc_module":4,"doc_module_name":46,"category_name":95,"show_sort_weight":96,"slug":97},"Story & Novel",90,"story-novel",{"id":47,"doc_module":4,"doc_module_name":46,"category_name":99,"show_sort_weight":100,"slug":101},"Literature",80,"literature",{"id":53,"doc_module":4,"doc_module_name":46,"category_name":103,"show_sort_weight":104,"slug":105},"Exam",70,"exam",{"id":107,"doc_module":4,"doc_module_name":46,"category_name":108,"show_sort_weight":109,"slug":110},5,"Comic",60,"comic",{"id":112,"doc_module":4,"doc_module_name":46,"category_name":113,"show_sort_weight":114,"slug":115},6,"Technology",50,"technology",{"id":117,"doc_module":4,"doc_module_name":46,"category_name":118,"show_sort_weight":119,"slug":120},7,"Healthcare",40,"healthcare",{"id":11,"doc_module":4,"doc_module_name":46,"category_name":12,"show_sort_weight":122,"slug":123},30,"research-report",{"id":125,"doc_module":4,"doc_module_name":46,"category_name":126,"show_sort_weight":127,"slug":128},9,"Religion & Spirituality",20,"religion-spirituality",{"id":127,"doc_module":4,"doc_module_name":46,"category_name":130,"show_sort_weight":127,"slug":131},"World Cup","world-cup",{"id":133,"doc_module":4,"doc_module_name":46,"category_name":134,"show_sort_weight":133,"slug":135},10,"Lifestyle","lifestyle",{"id":137,"doc_module":4,"doc_module_name":46,"category_name":138,"show_sort_weight":107,"slug":139},19,"General","general"]