[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-121673-en":3,"doc-seo-121673-105":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},121673,687197100911,"Himbo","https://ap-avatar.wpscdn.com/avatar/a000239b6f1da00475?x-image-process=image/resize,m_fixed,w_180,h_180&k=1785132997149421697",8,"Research & Report","Investigating large-scale change in volcanic time series data using machine learning analysis","Volcanic eruptions exhibit large-scale transitions in behaviour, including repose-to-unrest, unrest-to-eruption, and eruption-to-quiescence, whose timing is a key challenge in volcanology. This thesis applies machine learning methods used in monitoring critical systems to infer when such transitions occur. It first models eruption-end timing from volcano-seismic time series for Nevado del Ruiz and Telica, improving constraints on cessation timescales. It then extends the approach to Augustine’s 2005–2006 multi-parameter unrest and eruption using models trained on non-eruptive data. Finally, deep active learning is used to reduce labelled data needs for automated volcano-seismic event classification on Nevado del Ruiz and Llaima.","Investigating large-scale change in volcanic time series data using machine learning analysis  \nGrace Manley  \nUniversity College  \nUniversity of Oxford  \nA thesis submitted for the degree of  \nDoctor of Philosophy  \nMichaelmas Term 2021  \nSupervisors: Prof. T.A. Mather, Prof. D.M. Pyle, Prof. D.A. Clifton, and Dr M. Rodgers  \nii  \nDeclaration  \nI declare that the contents ofthis thesis are entirely my own, except where explicitly noted.  \nGrace Manley  \nTuesday 2nd November 2021  \niv  \nAbstract  \nInvestigating large-scale change in volcanic time series data using machine learning analysis  \nGrace Manley  \nUniversity College, Oxford  \nMichaelmas 2021  \nVolcanic eruptions are characterised by large-scale transitions in behaviour, which include the transitions governing repose to unrest, unrest to eruption, and eruption to quiescence. Identification of these transitions is a fundamental goal in volcanology. This thesis aims to explore the use of machine learning approaches which are established for the monitoring of critical systems, such as healthcare or jet engine monitoring, to better understand the timing of large-scale transitions in volcanic activity. The first research chapter is an application of machine learning approaches to better understand the timing of eruption end, which has no systematic definition. Multi-class machine learning methods were applied to time series derived from volcano-seismic data from two volcanoes with contrasting eruption styles: Nevado del Ruiz, Colombia and Telica, Nicaragua. The resulting eruption end-dates agreed with previous, generic definitions of eruption end and provide an independent constraint on the timescale of eruption cessation processes. The second research chapter is an extension of this methodology to multi-parameter datasets from the 2005 – 2006 unrest and eruption of Augustine, Alaska. Both multi-class and novelty detection approaches, in which models are trained only on noneruptive data, are applied. The resulting transition from non-eruptive to eruptive identified from the modelling agrees with previous estimates of the timing of dike initiation prior to eruption. Additionally, I explored the use of different types of data and different seismic catalogues for distinguishing between eruptive and non-eruptive activity. The final research chapter is an application of deep active learning to automated volcano-seismic event classification. Active learning is the process by which a machine learning model actively selects the training data which it learns from.  \nThis approach has the potential to reduce the quantity of labelled data required to train a successful model. The deep active learning approach is applied to two datasets from Nevado del Ruiz, Colombia and Llaima, Chile. Active learning models performed better on unseen testing data for both datasets and achieved better performance during training for the Nevado del Ruiz dataset.  \nvi  \nAcknowledgements  \nFirstly, thanks to my dream team of supervisors. Thank you to my supervisors in the Earth Sciences department, Tamsin Mather and David Pyle, for allowing me the freedom to explore interesting ideas throughout my DPhil, and for their vast experience which helped me to refine them. I am very grateful for their support and encouragement to write up and present my work throughout. Thank you to David Clifton, for taking me on as a first-year DPhil student and bringing incredible insights to the project at every stage. Thank you to Mel Rodgers, both for our regular discussions and for invaluable technical discussions during critical points of the project.  \nAdditional thanks go to the collaborators who I have worked with from whom I have received  \nconsiderable feedback and advice, including Glenn Thompson, Diana Roman and John Makario Londoño.  \nAn enormous thanks go to Mel and Rocco for hosting me in Tampa during my first-year trip to the University of South Florida, where I learned much of the fundamentals of seismic data ","cbCaibc3dFRuIMtp","https://ap.wps.com/l/cbCaibc3dFRuIMtp","pdf",25010726,1,209,"English","en",105,"# Abstract\n## Eruption-end timing via multi-class classification\n## Transition detection from non-eruptive training data\n## Distinguishing eruptive vs non-eruptive activity\n## Deep active learning for event classification","[{\"question\":\"What main transitions in volcanic behaviour does the thesis focus on?\",\"answer\":\"It focuses on transitions that govern repose to unrest, unrest to eruption, and eruption to quiescence, with particular emphasis on timing.\"},{\"question\":\"How does the first research chapter address the timing of eruption end?\",\"answer\":\"It applies multi-class machine learning to volcano-seismic time series from Nevado del Ruiz and Telica to estimate eruption-end dates and compare them with prior generic definitions.\"},{\"question\":\"What is the role of active learning in the final research chapter?\",\"answer\":\"Deep active learning is used for automated volcano-seismic event classification, selecting training data to reduce the quantity of labelled data required while improving performance on unseen testing data.\"}]","Investigating large-scale change in volcanic time series data using machine learning analysis | PDF",1785806144,527,{"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},"investigating-large-scale-change-in-volcanic-time-series-data-using-machine-learning-analysis","",{"@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/investigating-large-scale-change-in-volcanic-time-series-data-using-machine-learning-analysis/121673/",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 main transitions in volcanic behaviour does the thesis focus on?","Question",{"text":75,"@type":76},"It focuses on transitions that govern repose to unrest, unrest to eruption, and eruption to quiescence, with particular emphasis on timing.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"How does the first research chapter address the timing of eruption end?",{"text":80,"@type":76},"It applies multi-class machine learning to volcano-seismic time series from Nevado del Ruiz and Telica to estimate eruption-end dates and compare them with prior generic definitions.",{"name":82,"@type":73,"acceptedAnswer":83},"What is the role of active learning in the final research chapter?",{"text":84,"@type":76},"Deep active learning is used for automated volcano-seismic event classification, selecting training data to reduce the quantity of labelled data required while improving performance on unseen testing data.","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"]