[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-117760-en":3,"doc-seo-117760-105":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},117760,1099513958607,"Jiven","https://ap-avatar.wpscdn.com/avatar/100002390cf8733938c?x-image-process=image/resize,m_fixed,w_180,h_180&k=1778829742770036399",8,"Research & Report","Applications of unsupervised machine learning in climate research","Machine learning in climate science is expanding rapidly, with data-driven models offering improved accuracy and deeper insight into the physical climate system compared with conventional statistical approaches. This thesis investigates two core problems—climate mode extraction and bias correction of simulations—using unsupervised machine learning. It develops and tests mode-extraction frameworks on climate-like data, evaluates performance on reanalysis and model temperature, and examines risks from false modes. It also applies unsupervised deep neural networks for bias correcting multi-variable simulated fields, highlighting strengths and limitations.","This thesis has been submitted in fulfilment of the requirements for a postgraduate degree (e. g. PhD, MPhil, DClinPsychol) at the University of Edinburgh. Please note the following terms and conditions of use:  \n• This work is protected by copyright and other intellectual property rights, which are retained by the thesis author, unless otherwise stated.  \n• A copy can be downloaded for personal non-commercial research or study, without prior permission or charge.  \n• This thesis cannot be reproduced or quoted extensively from without first obtaining permission in writing from the author.  \n• The content must not be changed in any way or sold commercially in any format or medium without the formal permission of the author.  \n• When referring to this work, full bibliographic details including the author, title, awarding institution and date of the thesis must be given.  \nApplications of unsupervised machine learning in climate research  \nD. James Fulton School of GeoSciences  \nUniversity of Edinburgh  \nA thesis submitted for the degree of Doctor of Philosophy  \n2022  \nDeclaration  \nI declare that this thesis has been composed solely by myself and that it has not been submitted, in whole or in part, in any previous application for a degree. Except where stated otherwise by reference or acknowledgment, the work presented is entirely my own.  \nJames Fulton November 2022  \nAcknowledgements  \nFirst and foremost I would like to thank Gabi Hegerl for taking a chance on me, and for giving me the freedom and support to take this PhD where it wanted togo. Although the final destination of this thesis was far from the planned route I hope that it has found its way. I’d also like to thank Simon Tett for his support, for hitting me with the important questions along the way, and helping me to sure up my thinking. This thesis could not have come to be without both of them. I would also like to thank our research group for putting up with too much discussion on machine learning when none of them were particularly enthralled by it.  \nI couldn’t have gotten through this without the support of my PhD peersand friends. I have to especially acknowledge Ben Clarke. Years ago we were physics undergrads estimating the mass of Sagittarius A* together. During our PhDs we bias corrected climate data with machine learning methods. It’s been a pleasure. I also want to thank my flatmates, and especially Aaron Torrens for being an industrial strength vent.  \nDuring the course of the PhD I spent two summers working on different projects related to machine learning in climate. I have to thank Jack Kelly and those at Open Climate Fix for hosting me in the middle of a pandemic and always having time to chat to a grad student who really didn’t know very much about machine learning. I also want to thank the Frontier Development Lab (FDL) for keeping me motivated during a second summer of lockdowns. I also owe a lot to my research group at FDL, it was a pleasure working with you and I learned a lot.  \nI have Neale Gibson to thank for giving me my first taste of academic research, and Adam Povey to thank for my first foray into working with earth data.  \nMost of all I want to thank my parents for their steady and unwavering support throughout too many years of education. To my brother for keeping me grounded and realising there is more to this whole mess than work. And to Emily for everything else. If any of you are reading this, I am grateful, but please put it down and go do something more worthwhile. Life is far to precious than to read dusty esoterica.  \nAbstract  \nThe use of machine learning in climate science is expanding rapidly after its success in other fields. The more powerful data driven models of machine learning show promise to give us more accurate predictions of and potentially more insights into the physical climate system than conventional statistical models.  \nMany new applications for machine learning in climate science have been proposed in rec","cbCaimhSssBEH1K7","https://ap.wps.com/l/cbCaimhSssBEH1K7","pdf",16637045,1,175,"English","en",105,"# Abstract\n# Lay Summary\n# Declaration\n# Acknowledgements\n# Applications of unsupervised machine learning in climate research\n## Climate mode extraction framework\n## False mode extraction and modal mechanisms\n## Bias correction with unsupervised deep neural networks\n## Cross-variable and spatial correlation mapping\n## Limitations of unconstrained optimization","[{\"question\":\"What two problems does the thesis address using unsupervised machine learning?\",\"answer\":\"It addresses climate mode extraction and the bias correction of simulations.\"},{\"question\":\"How does the thesis evaluate climate mode extraction methods?\",\"answer\":\"It develops a framework using imitation climate-like data, then applies newer mode-extraction methods to reanalysis and model surface temperature to assess their ability to extract known modes and signals.\"},{\"question\":\"What are the main advantages and limitations of the unsupervised deep neural networks for bias correction?\",\"answer\":\"The networks enable more faithful bias correction of cross-variable and spatial correlations and can shift misplaced climate features, but lack of constraints during optimization can produce unexpected results and reveal method limitations.\"}]","Applications of unsupervised machine learning in climate research | PDF",1785679426,441,{"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},"applications-of-unsupervised-machine-learning-in-climate-research","",{"@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/applications-of-unsupervised-machine-learning-in-climate-research/117760/",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","2026-08-02",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 two problems does the thesis address using unsupervised machine learning?","Question",{"text":75,"@type":76},"It addresses climate mode extraction and the bias correction of simulations.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"How does the thesis evaluate climate mode extraction methods?",{"text":80,"@type":76},"It develops a framework using imitation climate-like data, then applies newer mode-extraction methods to reanalysis and model surface temperature to assess their ability to extract known modes and signals.",{"name":82,"@type":73,"acceptedAnswer":83},"What are the main advantages and limitations of the unsupervised deep neural networks for bias correction?",{"text":84,"@type":76},"The networks enable more faithful bias correction of cross-variable and spatial correlations and can shift misplaced climate features, but lack of constraints during optimization can produce unexpected results and reveal method limitations.","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"]