[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-120693-en":3,"doc-seo-120693-105":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":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},120693,1099513958762,"Logic","https://ap-avatar.wpscdn.com/avatar/1000023916a998db790?x-image-process=image/resize,m_fixed,w_180,h_180&k=1784791008015729253",8,"Research & Report","Future digital twins - emulating a highly complex marine biogeochemical model with machine learning to predict hypoxia","Machine learning models are increasingly used in oceanographic research, but emulation of marine biogeochemical models remains uncommon. This work develops novel ML emulators to reproduce a highly complex physical-biogeochemical model for predicting marine oxygen in shelf-sea environments. The emulators are designed to support future digital twins for hypoxia prediction relevant to aquaculture and fisheries and for oxygen extrapolation from marine observations.","TYPE Original Research PUBLISHED 17 April 2023  \nDOI 10.3389/fmars.2023.1058837  \nOPEN ACCESS  \nEDITED BY Wen Luo,  \nNanjing Normal University, China  \nREVIEWED BY  \nEmmanuel Hanert,  \nUniversite´ Catholique de Louvain, Belgium Jann Paul Mattern,  \nUniversity of California, Santa Cruz, United States  \n*CORRESPONDENCE Jozef Sk´akala  \n[jos@pml.ac.uk](jos@pml.ac.uk)  \nSPECIALTY SECTION  \nThis article was submitted to Marine Biogeochemistry, a section of the journal Frontiers in Marine Science  \nRECEIVED 30 September 2022  \nACCEPTED 22 March 2023  \nPUBLISHED 17 April 2023  \nCITATION  \nSk´akala J, Awty-Carroll K, Menon PP, Wang K and Lessin G (2023) Future digital twins: emulating a highly complex marine biogeochemical model with machine learning to predict hypoxia.  \nFront. Mar. Sci. 10:1058837 .  \ndoi: 10.3389/fmars.2023.1058837  \nCOPYRIGHT  \n© 2023 Sk´akala, Awty-Carroll, Menon, Wang and Lessin. This is an open-access article distributed under the terms of the Creative Commons Attribution License (CC BY) . The use, distribution or reproduction in other forums is permitted, provided the original author(s) and the copyright owner(s) are credited and that the original publication in this journal is cited, in accordance with accepted academic practice. No use, distribution or reproduction is permitted which does not comply with these terms.  \nFuture digital twins: emulating a highly complex marine biogeochemical model  \nwith machine learning to predict hypoxia  \nJozef Sk´akala 1,2*, Katie Awty-Carroll 1,2,3, Prathyush P. Menon 4, Ke Wang 4 and Gennadi Lessin 1  \n1 Plymouth Marine Laboratory, Plymouth, United Kingdom, 2 National Centre for Earth Observation, Plymouth, United Kingdom, 3Space Intelligence, Edinburgh, United Kingdom, 4 Faculty of Environment, Science and Economy, University of Exeter, Exeter, United Kingdom  \nThe Machine learning (ML) revolution is becoming established in oceanographic research, but its applications to emulate marine biogeochemical models are still rare. We pioneer a novel application of machine learning to emulate a highly complex physical-biogeochemical model to predict marine oxygen in the shelfsea environment. The emulators are developed with intention of supporting future digital twins for two key stakeholder applications: (i) prediction of hypoxia for aquaculture and fisheries, (ii) extrapolation of oxygen from marine observations. We identify the key drivers behind oxygen concentrations and determine the constrains on observational data for a skilled prediction of marine oxygen across the whole water column. Through this we demonstrate that ML models can be very useful in informing observation measurement arrays. We compare the performance of multiple different ML models, discuss the benefits of the used approaches and identify outstanding issues, such as limitations imposed by the spatio-temporal resolution of the training/validation data.  \nKEYWORDS  \ndigital twins, machine learning emulator, oxygen prediction, shelf seas, marine biogeochemical model  \n1 Introduction  \nOcean ecosystems play an essential role in many aspects of our lives: from providing essential sources of food, through producing half of the planet’s oxygen, to serving as an important sink of carbon dioxide (e.g., Pauly et al. (2002); Riebesell et al. (2009)) . Of particular relevance for this are the continental shelves, and coastal regions, which are highly biologically productive, containing 90% of the world’s fisheries (Pauly et al. (2002)) and providing resources for the aquaculture industry (Bostock et al. (2010)) . Despite its importance, our understanding of marine biogeochemistry suffers from it being extremely  \nFrontiers in Marine Science 01 [frontiersin.org](frontiersin.org)  \nundersampled (Davidson et al. (2019)), with robust observations limited to the ocean surface and to a few variables that can be reasonably estimated from the satellite optical measurements (such as the surface total chlorophyll-a) . More diverse","cbCail680XcdPtkt","https://ap.wps.com/l/cbCail680XcdPtkt","pdf",6452608,1,16,"English","en",105,"# Introduction\n## Marine biogeochemistry data gaps\n## Role of ecosystem models\n## Mapping observations to unobserved outputs","[{\"question\":\"What problem does the study address?\",\"answer\":\"It targets oxygen prediction in shelf-sea environments by emulating a highly complex physical-biogeochemical model with machine learning, enabling better hypoxia forecasts and oxygen extrapolation.\"},{\"question\":\"How do the machine learning emulators support digital twins?\",\"answer\":\"They are built to underpin future digital twins for stakeholder use cases such as hypoxia prediction for aquaculture and fisheries and extrapolating oxygen from marine observations.\"},{\"question\":\"What factors and data constraints does the study examine?\",\"answer\":\"It identifies key drivers of oxygen concentrations and discusses constraints imposed by the spatio-temporal resolution of the training and validation data, affecting prediction skill across the water column.\"}]","Future digital twins - emulating a highly complex marine biogeochemical model with machine learning to predict hypoxia | PDF",1785731570,40,{"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},"future-digital-twins-emulating-a-highly-complex-marine-biogeochemical-model-with-machine-learning-to-predict-hypoxia","",{"@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/future-digital-twins-emulating-a-highly-complex-marine-biogeochemical-model-with-machine-learning-to-predict-hypoxia/120693/",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":20},"InteractionCounter",{"@type":67},"ViewAction",{"@type":69,"mainEntity":70},"FAQPage",[71,77,81],{"name":72,"@type":73,"acceptedAnswer":74},"What problem does the study address?","Question",{"text":75,"@type":76},"It targets oxygen prediction in shelf-sea environments by emulating a highly complex physical-biogeochemical model with machine learning, enabling better hypoxia forecasts and oxygen extrapolation.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"How do the machine learning emulators support digital twins?",{"text":80,"@type":76},"They are built to underpin future digital twins for stakeholder use cases such as hypoxia prediction for aquaculture and fisheries and extrapolating oxygen from marine observations.",{"name":82,"@type":73,"acceptedAnswer":83},"What factors and data constraints does the study examine?",{"text":84,"@type":76},"It identifies key drivers of oxygen concentrations and discusses constraints imposed by the spatio-temporal resolution of the training and validation data, affecting prediction skill across the water column.","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},[93,97,101,105,110,115,119,122,127,130,134],{"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":29,"slug":118},7,"Healthcare","healthcare",{"id":11,"doc_module":4,"doc_module_name":46,"category_name":12,"show_sort_weight":120,"slug":121},30,"research-report",{"id":123,"doc_module":4,"doc_module_name":46,"category_name":124,"show_sort_weight":125,"slug":126},9,"Religion & Spirituality",20,"religion-spirituality",{"id":125,"doc_module":4,"doc_module_name":46,"category_name":128,"show_sort_weight":125,"slug":129},"World Cup","world-cup",{"id":131,"doc_module":4,"doc_module_name":46,"category_name":132,"show_sort_weight":131,"slug":133},10,"Lifestyle","lifestyle",{"id":135,"doc_module":4,"doc_module_name":46,"category_name":136,"show_sort_weight":106,"slug":137},19,"General","general"]