[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-127752-en":3,"doc-seo-127752-105":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},127752,962084926284,"Aurora","https://ap-avatar.wpscdn.com/davatar_29158cc5080c5b710cf443261637dec0",8,"Research & Report","Surface Turbulent Fluxes From the MOSAiC Campaign Predicted by Machine Learning - Research Letter","Reliable boundary-layer turbulence parametrizations for polar conditions are required to reduce uncertainty in projections of Arctic sea ice melting and its broader impacts. Surface turbulent sensible and latent heat fluxes are commonly represented in weather and climate models using bulk formulas based on Monin-Obukhov Similarity Theory, sometimes tailored to high stability and sea-ice presence. Here, neural networks trained on observations from earlier Arctic campaigns predict MOSAiC sea-ice fluxes, outperforming the bulk scheme with up to 70% RMSE reductions, and are provided as a plug-in Fortran implementation.","RESEARCH LETTER  \n10.1029/2023GL105698  \nKey Points:  \n• Neural networks trained on previous Arctic campaigns predict surface turbulent fluxes from MOSAiC more accurately than bulk methods  \n• Updated parametrizations using the MOSAiC data have been developed and implemented in Fortran for deployment in weather/climate models  \n• Modest performance gains (up to +7% R2) from recalibration on MOSAiC indicate good generalizability to the pan-Arctic sea ice domain  \nCorrespondence to:  \nD. P. Cummins,  \n[donald.cummins@meteo.fr](donald.cummins@meteo.fr)  \n[Citation:](Citation:)  \nCummins, D. P., Guemas, V., Cox, C.  \nJ., Gallagher, M. R., & Shupe, M. D.(2023) . Surface turbulent fluxes from the MOSAiC campaign predicted by machine learning. Geophysical Research Letters, 50, e2023GL105698. [https://doi](https://doi). org/10.1029/2023GL105698  \nReceived 2 AUG 2023 Accepted 26 OCT 2023  \n© 2023. The Authors.  \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.  \nSurface Turbulent Fluxes From the MOSAiC Campaign Predicted by Machine Learning  \nDonald P. Cummins1 , Virginie Guemas1 , Christopher J. Cox2 , Michael R. Gallagher2,3 , and Matthew D. Shupe2,3   \n1CNRM, Météo-France, CNRS, Université de Toulouse, Toulouse, France, 2Physical Sciences Laboratory, National Oceanic and Atmospheric Administration, Boulder, CO, USA, 3Cooperative Institute for Research in Environmental Sciences, University of Colorado, Boulder, CO, USA  \nAbstract Reliable boundary-layer turbulence parametrizations for polar conditions are needed to reduce uncertainty in projections of Arctic sea ice melting rate and its potential global repercussions. Surface turbulent fluxes of sensible and latent heat are typically represented in weather/climate models using bulk formulae based on the Monin-Obukhov Similarity Theory, sometimes finely tuned to high stability conditions and the potential presence of sea ice. In this study, we test the performance of new, machine-learning (ML) flux parametrizations, using an advanced polar-specific bulk algorithm as a baseline. Neural networks, trained on observations from previous Arctic campaigns, are used to predict surface turbulent fluxes measured over sea ice as part of the recent MOSAiC expedition. The ML parametrizations outperform the bulk at the MOSAiC sites, with RMSE reductions of up to 70 percent. We provide a plug-in Fortran implementation of the neural networks for use in models.  \nPlain Language Summary Heat can make its way into or out of sea ice via unpredictable air movements, known as turbulence, near the sea surface. In order to predict how quickly Arctic sea ice will melt in the future, we need to know how much heat the turbulence can transport in different weather conditions. Traditionally, turbulence calculations have been performed using sophisticated mathematical formulae from physics. In this study, we test an alternative method for predicting turbulent heat exchange: a computer algorithm known as an artificial neural network. By showing turbulence data, measured in the Arctic during previous scientific expeditions, to the network, it can be “trained” to make predictions in a process known as machine learning. We compare turbulence measurements, taken above sea ice in the recent MOSAiC expedition, with predictions from trained neural networks. We find that the neural networks are better than the traditional physics at predicting what the scientists at MOSAiC observed. The trained neural networks have been made publicly available so that they can be used by scientists for predicting climate change.  \n1. Introduction  \nThe polar regions, in particular the Arctic, are on the front line of the climate crisis. In recent decades, the rate of surface warming in the Arctic has been two to four times higher than the global mean (Rantanen et al., 2022), a phenomenon k","cbCaigbPmSZjXz0u","https://ap.wps.com/l/cbCaigbPmSZjXz0u","pdf",550217,1,11,"English","en",105,"# Abstract\n# Introduction\n## Arctic amplification and sea ice change\n## Turbulence parametrizations and Monin-Obukhov Similarity Theory\n# Methods\n## Neural-network flux parametrizations\n## Baseline bulk algorithm\n# Results\n## Performance at MOSAiC sites\n# Implementation\n## Plug-in Fortran deployment","[{\"question\":\"Why are improved turbulence parametrizations needed for Arctic sea ice projections?\",\"answer\":\"They reduce uncertainty in how much heat is exchanged between the atmosphere and sea ice, which controls sea ice melting rates and therefore affects future climate projections.\"},{\"question\":\"What approach does the study use to predict surface turbulent heat fluxes?\",\"answer\":\"It trains neural networks on observations from previous Arctic campaigns and uses them to predict sensible and latent heat fluxes measured over sea ice during MOSAiC.\"},{\"question\":\"How do the machine-learning parametrizations compare with traditional bulk methods at MOSAiC?\",\"answer\":\"The machine-learning parametrizations outperform the bulk scheme at MOSAiC sites, with RMSE reductions of up to 70%.\"}]","Surface Turbulent Fluxes From the MOSAiC Campaign Predicted by Machine Learning - Research Letter | PDF",1785941407,28,{"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},"surface-turbulent-fluxes-from-the-mosaic-campaign-predicted-by-machine-learning-research-letter","",{"@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/surface-turbulent-fluxes-from-the-mosaic-campaign-predicted-by-machine-learning-research-letter/127752/",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","2026-08-22","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 improved turbulence parametrizations needed for Arctic sea ice projections?","Question",{"text":76,"@type":77},"They reduce uncertainty in how much heat is exchanged between the atmosphere and sea ice, which controls sea ice melting rates and therefore affects future climate projections.","Answer",{"name":79,"@type":74,"acceptedAnswer":80},"What approach does the study use to predict surface turbulent heat fluxes?",{"text":81,"@type":77},"It trains neural networks on observations from previous Arctic campaigns and uses them to predict sensible and latent heat fluxes measured over sea ice during MOSAiC.",{"name":83,"@type":74,"acceptedAnswer":84},"How do the machine-learning parametrizations compare with traditional bulk methods at MOSAiC?",{"text":85,"@type":77},"The machine-learning parametrizations outperform the bulk scheme at MOSAiC sites, with RMSE reductions of up to 70%.","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"]