[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-123288-en":3,"doc-seo-123288-105":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},123288,687197207057,"Sage","https://ap-avatar.wpscdn.com/davatar_29158cc5080c5b710cf443261637dec0",8,"Research & Report","Process-Based Machine Learning Observationally Constrains Future Regional Warming Projections","A novel process-based machine learning method is introduced to constrain climate model uncertainty in future regional near-surface temperature projections. Ridge-ERA5, a ridge regression model, learns coefficients representing climate-invariant relationships that map observed daily temperature anomaly patterns to controlling predictors from ERA5. By combining historically constrained coefficients with CMIP6 future projection inputs, observational constraints on regional warming are derived. Constrained temperature ranges include the multi-model mean across tested regions, while models projecting extreme warming are more likely to be excluded; decomposition highlights predictor contribution patterns consistent with feedback error-cancellation in some regions.","RESEARCH ARTICLE  \n10.1029/2025JH000698  \nKey Points:  \n• We demonstrate a new approach to observationally constrain climate modeling uncertainty in future near‐ surface temperature projections  \n• The approach builds on climate‐ invariant relationships learned to reliably predict daily temperatures from a set of controlling factors  \n• The results of our observational constraint are in line with previous work suggesting warming in high sensitivity models may be too high  \nSupporting Information:  \nSupporting Information may be found in the online version of this article.  \nCorrespondence to:  \nS. Wilkinson,  \n[sophie.wilkinson@uea.ac.uk](sophie.wilkinson@uea.ac.uk)  \nCitation:  \nWilkinson, S., Nowack, P., & Joshi, M.(2025) . Process‐based machine learning observationally constrains future regional warming projections. Journal of Geophysical Research: Machine Learning and Computation, 2, e2025JH000698 .  \n[https://doi.org/10.1029/2025JH000698](https://doi.org/10.1029/2025JH000698)  \nReceived 20 MAR 2025 Accepted 27 MAY 2025  \n© 2025 The Author(s) . Journal of Geophysical Research: Machine Learning and Computation published by Wiley Periodicals LLC on behalf of American Geophysical Union.  \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.  \nProcess‐Based Machine Learning Observationally Constrains Future Regional Warming Projections  \nSophie Wilkinson1 , Peer Nowack2,3 , and Manoj Joshi1   \n1Climatic Research Unit, School of Environmental Sciences, University of East Anglia, Norwich, UK, 2Institute of Theoretical Informatics, Karlsruhe Institute of Technology, Karlsruhe, Germany, 3Institute of Meteorology and Climate Research (IMK‐ASF), Karlsruhe Institute of Technology, Karlsruhe, Germany  \nAbstract We present the results of a novel process‐based machine learning method to constrain climate model uncertainty in future regional temperature projections. Ridge‐ERA5—a ridge regression model—learns coefficients to represent observed relationships between daily near‐surface temperature anomalies and predictor variables from ERA5 reanalysis in Northern Hemisphere land regions. Combining the historically constrained Ridge‐ERA5 coefficients with inputs from CMIP6 future projections enables a derivation of observational constraints on regional warming. Although the multi‐model mean falls within the constrained range of temperatures in all tested regions, a subset of models which predict the greatest degree of warming tend to be excluded and decomposition of the constraint into predictor variable contributions suggests error‐cancellation of feedbacks in some models and regions.  \nPlain Language Summary Knowledge about future global and regional warming is essential for effective adaptation planning. Future temperature projections are based on the output of global climate models which simulate future warming under a range of possible future emissions pathways. Although climate models agree that there will be warming in the future, there are still significant discrepancies in the degree of warming projected under a given scenario. Here, we make use of a machine learning (ML)‐based method which learns relationships from daily observations‐based data to predict daily temperature anomalies in climate models. These observations‐based relationships are applied to future climate model projections to produce a constrained range of future temperature predictions. For regions across the Northern Hemisphere, we find that, the mean of models broadly falls within the observationally constrained range whilst those few models which predict the most extreme future warming are most likely to be excluded by the constraint.  \n1. Introduction  \nDespite improvements in resolution and modeling of physical processes between subsequent generations of CMIP models, constraining uncertainty in future projections of","cbCaim7xEZZlhG5y","https://ap.wps.com/l/cbCaim7xEZZlhG5y","pdf",2242600,1,15,"English","en",105,"# Key Points\n# 1. Introduction\n## Climate model uncertainty in CMIP5 vs CMIP6\n## Sources of future climate projection uncertainty\n## Approaches to constraining model uncertainty\n## Detection and attribution and Bayesian principles","[{\"question\":\"What problem does the paper address in climate projections?\",\"answer\":\"The paper addresses how to constrain uncertainty in future climate change projections, focusing on model uncertainty in regional surface temperature projections.\"},{\"question\":\"How does Ridge-ERA5 produce observational constraints?\",\"answer\":\"Ridge-ERA5 learns coefficients from observed daily near-surface temperature anomalies and ERA5 predictor variables, then applies these historically constrained relationships to CMIP6 future projection inputs to derive constrained warming ranges.\"},{\"question\":\"What are the main findings across Northern Hemisphere land regions?\",\"answer\":\"The multi-model mean generally falls within the observationally constrained temperature range, while a subset of models predicting the strongest extreme warming is more likely to be excluded by the constraint; contributor decomposition suggests error-cancellation of feedbacks in some models and regions.\"}]","Process-Based Machine Learning Observationally Constrains Future Regional Warming Projections | PDF",1785815767,38,{"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},"process-based-machine-learning-observationally-constrains-future-regional-warming-projections-123288","",{"@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/process-based-machine-learning-observationally-constrains-future-regional-warming-projections-123288/123288/",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":4},"InteractionCounter",{"@type":67},"ViewAction",{"@type":69,"mainEntity":70},"FAQPage",[71,77,81],{"name":72,"@type":73,"acceptedAnswer":74},"What problem does the paper address in climate projections?","Question",{"text":75,"@type":76},"The paper addresses how to constrain uncertainty in future climate change projections, focusing on model uncertainty in regional surface temperature projections.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"How does Ridge-ERA5 produce observational constraints?",{"text":80,"@type":76},"Ridge-ERA5 learns coefficients from observed daily near-surface temperature anomalies and ERA5 predictor variables, then applies these historically constrained relationships to CMIP6 future projection inputs to derive constrained warming ranges.",{"name":82,"@type":73,"acceptedAnswer":83},"What are the main findings across Northern Hemisphere land regions?",{"text":84,"@type":76},"The multi-model mean generally falls within the observationally constrained temperature range, while a subset of models predicting the strongest extreme warming is more likely to be excluded by the constraint; contributor decomposition suggests error-cancellation of feedbacks in some models and regions.","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":136,"doc_module":4,"doc_module_name":46,"category_name":137,"show_sort_weight":106,"slug":138},19,"General","general"]