[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-123206-en":3,"doc-seo-123206-105":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},123206,1374391975076,"Riley","https://ap-avatar.wpscdn.com/avatar/14000253ca4ec9f6853?x-image-process=image/resize,m_fixed,w_180,h_180&k=1783305029341752051",8,"Research & Report","A Machine Learning-Based Dissolved Organic Carbon Climatology","Marine dissolved organic carbon (DOC) is a major carbon reservoir influencing climate, yet it remains poorly quantified, limiting climate-model validation and estimates of the modern ocean DOC inventory. This work applies boosted regression trees to link compiled DOC observations with environmental variables, then extrapolates inferred relationships across the entire ocean to produce annual, layer-wise DOC climatologies with uncertainties. Performance is reported as R2 between 0.6 and 0.8 across layers, with errors comparable to measurement variability, and the total DOC inventory estimated near 690 Pg C.","RESEARCH LETTER  \n10.1029/2024GL112792  \nKey Points:  \n• A machine learning model was fitted to relate DOC observations to other environmental variables (e.g., temperature, dissolved oxygen)  \n• Inferred relationships between environmental predictors and DOC were used to generate layer‐wise climatologies of DOC  \n• By integrating our predictions to the global ocean, we propose a refined estimate of the total DOC content of  \n690 Pg C  \nSupporting Information:  \nSupporting Information may be found in the online version of this article.  \nCorrespondence to:  \nT. Panaïotis,  \n[thelma.panaiotis@noc.ac.uk](thelma.panaiotis@noc.ac.uk)  \nCitation:  \nPanaïotis, T., Wilson, J., & Cael, B. (2025) . A machine learning‐based dissolved organic carbon climatology. Geophysical Research Letters, 52, e2024GL112792 .  \n[https://doi.org/10.1029/2024GL112792](https://doi.org/10.1029/2024GL112792)  \nReceived 30 SEP 2024  \nAccepted 17 FEB 2025  \nAuthor Contributions:  \nConceptualization: Thelma Panaïotis, Jamie Wilson, BB Cael  \nData curation: Thelma Panaïotis  \nFormal analysis: Thelma Panaïotis  \nFunding acquisition: BB Cael  \nSoftware: Thelma Panaïotis  \nSupervision: BB Cael  \nValidation: Thelma Panaïotis, Jamie Wilson  \nVisualization: Thelma Panaïotis Writing – original draft:  \nThelma Panaïotis, Jamie Wilson  \nWriting – review & editing:  \nThelma Panaïotis, Jamie Wilson, BB Cael  \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.  \nA Machine Learning‐Based Dissolved Organic Carbon Climatology  \nThelma Panaïotis1 , Jamie Wilson2 , and BB Cael1,3   \n1National Oceanography Centre, Southampton, UK, 2University of Liverpool, Liverpool, UK, 3Department of the Geophysical Sciences, University of Chicago, Chicago, Illinois, USA  \nAbstract Marine dissolved organic carbon (DOC) is a major carbon reservoir influencing climate, but is poorly quantified. The lack of a comprehensive DOC climatology hinders model validation, estimation of the modern DOC inventory, and understanding of DOC's role in the carbon cycle and climate. To address this problem, we used boosted regression trees to relate a compilation of DOC observations to different environmental climatologies, and extrapolated these inferred relationships to the entire ocean to compute annual layer‐wise DOC climatologies with uncertainties. Prediction performance was satisfactory, with R2 values within 0.6–0.8 for all layers and prediction error comparable to within‐pixel measurement variability. DOC was mainly predicted by dissolved oxygen in the bathypelagic layer, and by nutrients in other layers. We estimate the total oceanic DOC inventory to be around 690 Pg C. Our results exemplify that machine learning is a powerful tool for constructing climatologies from limited observations.  \nPlain Language Summary Marine dissolved organic carbon (DOC) is a large and important component of the Earth's carbon cycle that influences climate. However, we do not have a good understanding of how much DOC is in the oceans. This lack of information makes it difficult to improve climate models and fully understand how DOC affects the global carbon cycle. To address this, we used a machine learning technique (boosted regression trees) to relate available DOC data to environmental factors. We then applied this analysis to the entire ocean to produce annual estimates of DOC concentrations, along with the associated uncertainties. Our model performed well, explaining between 60% and 80% of the variance across different ocean layers. We found that dissolved oxygen seems to the main factor influencing DOC in deep waters, while nutrients were more important in the upper layers. We estimate that the total amount of DOC in the ocean isabout 690 billion tonnes of carbon. Our work shows that machine learning can be a useful tool to generate global est","cbCaid5D3xEtPQu6","https://ap.wps.com/l/cbCaid5D3xEtPQu6","pdf",1397921,1,10,"English","en",105,"# 1. Introduction\n## DOC as a major carbon reservoir\n## Drivers and uncertainties in DOC cycling\n# Abstract\n## Problem and modeling approach\n## Results and key predictors","[{\"question\":\"Why is a global DOC climatology important for climate science?\",\"answer\":\"A robust DOC climatology constrains how DOC impacts the climate system, supports validation of climate-relevant models, and improves estimates of the modern ocean DOC inventory.\"},{\"question\":\"What machine learning method is used to construct DOC climatologies?\",\"answer\":\"The study uses boosted regression trees to relate compiled DOC observations to environmental climatologies, then extrapolates those relationships to the entire ocean.\"},{\"question\":\"Which environmental variables most strongly predict DOC in different ocean layers?\",\"answer\":\"DOC is mainly predicted by dissolved oxygen in the bathypelagic layer, while nutrients are more important in other layers.\"}]","A Machine Learning-Based Dissolved Organic Carbon Climatology | PDF",1785815220,25,{"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},"a-machine-learning-based-dissolved-organic-carbon-climatology","",{"@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/a-machine-learning-based-dissolved-organic-carbon-climatology/123206/",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","2026-08-04",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},"Why is a global DOC climatology important for climate science?","Question",{"text":75,"@type":76},"A robust DOC climatology constrains how DOC impacts the climate system, supports validation of climate-relevant models, and improves estimates of the modern ocean DOC inventory.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"What machine learning method is used to construct DOC climatologies?",{"text":80,"@type":76},"The study uses boosted regression trees to relate compiled DOC observations to environmental climatologies, then extrapolates those relationships to the entire ocean.",{"name":82,"@type":73,"acceptedAnswer":83},"Which environmental variables most strongly predict DOC in different ocean layers?",{"text":84,"@type":76},"DOC is mainly predicted by dissolved oxygen in the bathypelagic layer, while nutrients are more important in other layers.","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},[93,97,101,105,110,115,120,123,128,131,134],{"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":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":21,"doc_module":4,"doc_module_name":46,"category_name":132,"show_sort_weight":21,"slug":133},"Lifestyle","lifestyle",{"id":135,"doc_module":4,"doc_module_name":46,"category_name":136,"show_sort_weight":106,"slug":137},19,"General","general"]