[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-126161-en":3,"doc-seo-126161-105":31,"detail-sidebar-cat-0-en-105":92},{"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":21,"is_downloadable":21,"audit_status":21,"page_count":22,"language":23,"language_code":24,"site_id":25,"html_lang":24,"table_of_contents":26,"faqs":27,"seo_title":28,"seo_description":14,"update_tm":29,"read_time":30},126161,3985741905716,"Rowan","https://ap-avatar.wpscdn.com/davatar_994ba38a5ba835b3df7d355c54d3ed8d",8,"Research & Report","CHARACTERISATION OF NATURALLY FRACTURED RESERVOIRS - FROM GEOLOGICAL WELL-TESTING TO MACHINE LEARNING-ASSISTED PRESSURE TRANSIENT ANALYSIS","The pressure signal recorded from dynamic well tests (e.g., pressure drawdown and pressure build-ups) encodes reservoir properties from a few meters to hundreds of meters around the wellbore. Pressure derivative  is used for identifying suitable reservoir models, yet concave v-shape diagnostics are non-unique for Naturally Fractured Reservoirs (NFRs). This thesis addresses how to represent the true diversity of v-shape responses and relate them to fracture-system properties. It proposes MachineLearning Assisted Pressure Transient Analysis (MLA-PTA), grounded in Geological Well Testing while enabling flexible NFR concepts, using unsupervised machine learning to classify signatures validated on 2500+ synthetic discrete fracture network models, and interpreted for two real field cases.","CHARACTERISATION OF NATURALLY FRACTURED RESERVOIRS: FROM GEOLOGICAL WELL-TESTING TO MACHINE LEARNING-ASSISTED PRESSURE TRANSIENT ANALYSIS  \nALFREDO EDUARDO FREITES CAMACARO  \nSubmitted for the degree of Doctor of Philosophy  \nInstitute of GeoEnergy Engineering  \nSchool of Energy, Geoscience, Infrastructure and Society  \nHeriot-Watt University  \nOctober 2024  \nABSTRACT  \nThe pressure signal recorded from dynamic well tests (e.g., pressure drawdown, pressure build-ups) reflects reservoir properties at scales ranging from a few meters to hundreds of meters around the wellbore. For quantifying these properties, it is essential to leverage the pressure derivative 􀝌 ’ for identifying suitable reservoir models. A concave inflexion 􀝌 ’ (i.e., v-shape) has been traditionally used as a diagnostic indicator of Naturally Fractured Reservoirs (NFRs), mainly because the standard model for NFRs produces a similar 􀝌 ’. However, multiple studies have shown that this model is rarely applicable because it does not represent common geologic features of NFRs, and that NFRs can manifest themselves in multiple different 􀝌 ’. Recognising the non-uniqueness of 􀝌 ’ in NFRs as well as the absence of a universally applicable NFRs model, the fundamental question is how to capture the true diversity of 􀝌 ’ and incorporate it into an interpretation framework that allows correlating the observed 􀝌 ’ to the underlying properties of the fractures. Addressing this question, this thesis introduces the MachineLearning Assisted Pressure Transient Analysis in NFRs (MLA-PTA), as a novel method for interpreting 􀝌 ’ in NFRs. MLA-PTA builds on the fundamental principle of the Geological Well Testing (GWT) method for ensuring geological consistency while interpreting 􀝌 ’, but enables higher flexibility to include multiple NFRs concepts or realisations. Central to the MLA-PTA method is an innovative proof-of-concept for classifying 􀝌 ’ responses using unsupervised machine learning aimed to facilitate identifying characteristic 􀝌 ’ signatures of different fracture systems. The proof-ofconcept was validated on a dataset encompassing over 2500 synthetic fracture models created from a bespoke discrete fracture network generator. The results helped provide insights about potential interpretations of two real field cases. Overall, the MLA-PTA provides a valuable alternative for capturing and understanding 􀝌 ’ behaviours of different NFRs and their correlation with real 􀝌 ’.  \nTo my beloved wife, Adelaide; son, Tiago and daughter, Maia.  \nACKNOWLEDGMENTS  \nThis thesis would not have been possible without the support of many people and organisations. First and foremost, I would like to express my sincere gratitude to Energi Simulation for funding my research and making this work a reality.  \nI am deeply grateful to my two primary supervisors, Prof. Sebastian Geiger and Prof. Patrick Corbett, for their invaluable guidance and mentorship. Prof. Corbett was the one who opened the door for me and trusted me to embark on this PhD journey. I will always appreciate his belief in me. Prof. Geiger not only fulfilled his supervisory duties but also provided immense personal support throughout my studies, going above and beyond to help me achieve this milestone. I will be eternally grateful to both of them for their unwavering support and encouragement. I would also like to acknowledge Prof. Florian Doster, who served as my internal supervisor and provided vital support in the final stages of my PhD journey.  \nAdditionally, I would like to extend my sincere thanks to Prof. Daniel Arnold and Prof. Katriona Eldmann for accepting to conduct my viva as examiners. I thoroughly enjoyed our scientific discussions and deeply appreciated their insights, which made the entire viva experience both engaging and rewarding.  \nDuring my PhD, I had the privilege of meeting and working with many wonderful people, some of whom have become close friends: Saeeda, Ali, Mohamed, Victoria, Julien, Fahed, Jackson","cbCaitKRpZyKGlzp","https://ap.wps.com/l/cbCaitKRpZyKGlzp","pdf",11037303,4,1,281,"English","en",105,"# Abstract\n## Background and problem\n## MLA-PTA method\n## Proof-of-concept validation\n## Key findings and impact","[{\"question\":\"Why is the v-shape pressure-derivative diagnostic insufficient for Naturally Fractured Reservoirs?\",\"answer\":\"Because the standard NFR model often fails to represent common geological features, and NFRs can produce multiple different v-shape responses. The v-shape is therefore non-unique as an indicator.\"},{\"question\":\"What is MLA-PTA in the thesis?\",\"answer\":\"MLA-PTA is MachineLearning Assisted Pressure Transient Analysis for NFRs. It keeps geological consistency via Geological Well Testing principles while allowing higher flexibility to include multiple NFR concepts.\"},{\"question\":\"How was the proposed approach validated?\",\"answer\":\"The proof-of-concept classification framework was validated on a dataset of over 2500 synthetic fracture models generated using a bespoke discrete fracture network generator, supporting interpretation insights for two real field cases.\"}]","CHARACTERISATION OF NATURALLY FRACTURED RESERVOIRS - FROM GEOLOGICAL WELL-TESTING TO MACHINE LEARNING-ASSISTED PRESSURE TRANSIENT ANALYSIS | PDF",1785903471,708,{"code":4,"msg":32,"data":33},"ok",{"site_id":25,"language":24,"slug":34,"title":13,"keywords":35,"description":14,"schema_data":36,"social_meta":87,"head_meta":89,"extra_data":91,"updated_unix":29},"characterisation-of-naturally-fractured-reservoirs-from-geological-well-testing-to-machine-learning-assisted-pressure-transient-analysis","",{"@graph":37,"@context":86},[38,54,69],{"@type":39,"itemListElement":40},"BreadcrumbList",[41,45,49,52],{"item":42,"name":43,"@type":44,"position":21},"https://docshare.wps.com","Home","ListItem",{"item":46,"name":47,"@type":44,"position":48},"https://docshare.wps.com/document/","Document",2,{"item":50,"name":12,"@type":44,"position":51},"https://docshare.wps.com/document/research-report/",3,{"item":53,"name":13,"@type":44,"position":20},"https://docshare.wps.com/document/characterisation-of-naturally-fractured-reservoirs-from-geological-well-testing-to-machine-learning-assisted-pressure-transient-analysis/126161/",{"url":53,"name":13,"@type":55,"author":56,"headline":13,"publisher":58,"fileFormat":61,"inLanguage":24,"description":14,"dateModified":62,"datePublished":63,"encodingFormat":61,"isAccessibleForFree":64,"interactionStatistic":65},"DigitalDocument",{"name":9,"@type":57},"Person",{"url":42,"name":59,"@type":60},"DocShare","Organization","application/pdf","2026-08-24","2026-08-05",true,{"@type":66,"interactionType":67,"userInteractionCount":20},"InteractionCounter",{"@type":68},"ViewAction",{"@type":70,"mainEntity":71},"FAQPage",[72,78,82],{"name":73,"@type":74,"acceptedAnswer":75},"Why is the v-shape pressure-derivative diagnostic insufficient for Naturally Fractured Reservoirs?","Question",{"text":76,"@type":77},"Because the standard NFR model often fails to represent common geological features, and NFRs can produce multiple different v-shape responses. The v-shape is therefore non-unique as an indicator.","Answer",{"name":79,"@type":74,"acceptedAnswer":80},"What is MLA-PTA in the thesis?",{"text":81,"@type":77},"MLA-PTA is MachineLearning Assisted Pressure Transient Analysis for NFRs. It keeps geological consistency via Geological Well Testing principles while allowing higher flexibility to include multiple NFR concepts.",{"name":83,"@type":74,"acceptedAnswer":84},"How was the proposed approach validated?",{"text":85,"@type":77},"The proof-of-concept classification framework was validated on a dataset of over 2500 synthetic fracture models generated using a bespoke discrete fracture network generator, supporting interpretation insights for two real field cases.","https://schema.org",{"og:url":53,"og:type":88,"og:title":13,"og:site_name":59,"og:description":14},"article",{"robots":90,"canonical":53},"index,follow",{"doc_id":7,"site_id":25},{"code":4,"msg":5,"data":93},[94,98,102,106,111,116,121,124,129,132,136],{"id":21,"doc_module":4,"doc_module_name":47,"category_name":95,"show_sort_weight":96,"slug":97},"Story & Novel",90,"story-novel",{"id":48,"doc_module":4,"doc_module_name":47,"category_name":99,"show_sort_weight":100,"slug":101},"Literature",80,"literature",{"id":20,"doc_module":4,"doc_module_name":47,"category_name":103,"show_sort_weight":104,"slug":105},"Exam",70,"exam",{"id":107,"doc_module":4,"doc_module_name":47,"category_name":108,"show_sort_weight":109,"slug":110},5,"Comic",60,"comic",{"id":112,"doc_module":4,"doc_module_name":47,"category_name":113,"show_sort_weight":114,"slug":115},6,"Technology",50,"technology",{"id":117,"doc_module":4,"doc_module_name":47,"category_name":118,"show_sort_weight":119,"slug":120},7,"Healthcare",40,"healthcare",{"id":11,"doc_module":4,"doc_module_name":47,"category_name":12,"show_sort_weight":122,"slug":123},30,"research-report",{"id":125,"doc_module":4,"doc_module_name":47,"category_name":126,"show_sort_weight":127,"slug":128},9,"Religion & Spirituality",20,"religion-spirituality",{"id":127,"doc_module":4,"doc_module_name":47,"category_name":130,"show_sort_weight":127,"slug":131},"World Cup","world-cup",{"id":133,"doc_module":4,"doc_module_name":47,"category_name":134,"show_sort_weight":133,"slug":135},10,"Lifestyle","lifestyle",{"id":137,"doc_module":4,"doc_module_name":47,"category_name":138,"show_sort_weight":107,"slug":139},19,"General","general"]