[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-122796-en":3,"doc-seo-122796-105":30,"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":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},122796,1649267921044,"Ava Thompson","https://us-avatar.wpscdn.com/avatar/1800007509477c92dfb?_k=1782875107921204101",8,"Research & Report","Machine Learning-Based Uncertainty Models for Reservoir Property Prediction and Forecasting - Doctoral Dissertation","Uncertainty in subsurface analytics arises from incomplete knowledge and information gaps about continuous and discrete properties, amplified by measurement errors, recording and processing choices, sampling bias, and heterogeneity. This dissertation develops and validates machine learning workflows that deliver property estimates with uncertainty and interpretable forecasting outputs. The research evaluates deep convolutional encoder-decoder ensembles, virtual ensembles for gradient-boosted decision tree well-log imputation, and temporal fusion transformer interpretability for temporal well performance prediction.","Copyright by  \nEduardo Maldonado Cruz 2023  \n1  \nThe Dissertation Committee for Eduardo Maldonado Cruz certifies that this is the approved version of the following dissertation:  \nMachine Learning-Based Uncertainty Models for Reservoir Property Prediction and Forecasting  \nCommittee:  \n\n| Michael J. Pyrcz, Supervisor |\n| --- |\n| Larry W. Lake |\n| John T. Foster |\n| Kamy Sepehrnoori |\n\nObiajulu J. Isebor  \nMachine Learning-Based Uncertainty Models for Reservoir Property Prediction and Forecasting  \nby  \nEduardo Maldonado Cruz  \nDISSERTATION  \nPresented to the Faculty of the Graduate School of The University of Texas at Austin in Partial Fulfillment  \nof the Requirements  \nfor the Degree of  \nDOCTOR OF PHILOSOPHY  \nTHE UNIVERSITY OF TEXAS AT AUSTIN  \nMay 2023  \nTo my wife, Paulina.  \n4  \nAcknowledgments  \nI would like to express my deepest gratitude to my supervisor Dr. Michael J. Pyrcz, for his invaluable guidance, unwavering support, and constant encouragement throughout my Ph.D. journey. Working with him has been an incredible experience that has enriched my knowledge and skills beyond measure.  \nI would like to thank Dr. Larry Lake, Dr. Kamy Sepehrnoori, Dr. John Foster, and Dr. Obiajulu Isebor for serving as part of my committee members.  \nI am especially grateful to Amy Douglas for her continuous support, assistance, and advice during my studies.  \nI want to thank my family for their continuous support and encouragement.  \nI am deeply grateful to ConTex for funding my Ph.D. studies and to Paloma Perry for her assistance during the course of my studies.  \nFinally, I would like to express my appreciation to the DiReCT consortium at the University of Texas at Austin for supporting this work.  \nMachine Learning-Based Uncertainty Models for Reservoir Property Prediction and Forecasting  \nEduardo Maldonado Cruz, Ph.D.  \nThe University of Texas at Austin, 2023  \nSupervisor: Michael J. Pyrcz  \nIn subsurface data analytics and machine learning, advances enable new methods and workflows for spatio-temporal, geoscience, and engineering property estimation and forecasting. These advances allow new and detailed models that contribute to field development planning cycles, such as reservoir modeling, volumetric assessment, pre-drill uncertainty, and production allocation.  \nUncertainty is caused by incomplete information and a lack of knowledge about continuous or discrete features. The presence of data uncertainty resulting from measurement errors, recording, data processing, sampling bias, and sample heterogeneity further exacerbates the need for reliable and interpretable uncertainty models, which are essential for effective subsurface prediction and forecasting. Therefore, developing robust, accurate, and precise models that provide the best possible estimates and account for the associated uncertainties is critical to improve decision-making.  \nThis research aims to develop innovative workflows to validate uncertainty models, predict properties with uncertainty, and create interpretable forecasting models. This research presents the following subjects: (1) The evaluation of machine learning-based uncertainty models,(2) the use of a deep convolutional encoder-decoder network to generate ensemble predictions and evaluate the uncertainty based on development parameters and geological information, (3) the use of virtual ensembles in gradient-boosted decision trees for well-log imputation, and (4) model interpretability in well performance forecasting with temporal fusion transformers. The developed workflows offer a reliable and understandable approach to uncertainty models critical for subsurface resource modeling and forecasting.  \nTable of Contents  \nAcknowledgments 5  \nAbstract 6  \nList of Tables 12  \nList of Figures 13  \nChapter 1 . Introduction 20  \n1.1 Problem description ........................ 20  \n1.2 Uncertainty models ........................ 22  \n1.3 Spatial uncertainty models with random functions ....... 23  \n1.4 Bootstr","cbCaiekAe2LkPt19","https://ap.wps.com/l/cbCaiekAe2LkPt19","pdf",17817962,1,225,"English","en",105,"# Acknowledgments\n# Abstract\n# List of Tables\n# List of Figures\n# Chapter 1 . Introduction\n## Problem description\n## Uncertainty models\n## Spatial uncertainty models with random functions\n## Bootstrap-based uncertainty models\n## Introduction to machine learning\n## Machine learning-based uncertainty models\n## Uncertainty estimation with dropout\n## Uncertainty estimation with virtual ensembles in gradient-boosted decision trees\n## Uncertainty estimation via quantile inference\n## Hypothesis\n## Dissertation outline\n# Chapter 2. Evaluation of uncertainty models\n## Summary\n## Introduction\n## Methodology\n## Results and discussion\n## Conclusions\n# Chapter 3 . Convolutional neural network-based surrogate flow model\n## Summary\n## Introduction\n## Methodology\n## Results and discussion","[{\"question\":\"What problem does the dissertation address in reservoir prediction?\",\"answer\":\"It addresses uncertainty caused by incomplete subsurface information and by data issues such as measurement errors, processing choices, sampling bias, and heterogeneity that affect property estimation and forecasting.\"},{\"question\":\"Which machine learning approaches are used to model uncertainty and predictions?\",\"answer\":\"It covers evaluation of machine learning-based uncertainty models, deep convolutional encoder-decoder networks for ensemble predictions, virtual ensembles in gradient-boosted decision trees for well-log imputation, and temporal fusion transformers for forecasting interpretability.\"},{\"question\":\"How does the work support better decision-making in subsurface modeling?\",\"answer\":\"By producing robust, accurate, and interpretable uncertainty-aware workflows and forecasting models that account for associated uncertainties, enabling more reliable planning and resource decisions.\"}]","Machine Learning-Based Uncertainty Models for Reservoir Property Prediction and Forecasting - Doctoral Dissertation | PDF",1785812937,567,{"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":87,"head_meta":89,"extra_data":91,"updated_unix":28},"machine-learning-based-uncertainty-models-for-reservoir-property-prediction-and-forecasting-doctoral-dissertation","",{"@graph":36,"@context":86},[37,54,69],{"@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/machine-learning-based-uncertainty-models-for-reservoir-property-prediction-and-forecasting-doctoral-dissertation/122796/",4,{"url":52,"name":13,"@type":55,"author":56,"headline":13,"publisher":58,"fileFormat":61,"inLanguage":23,"description":14,"dateModified":62,"datePublished":63,"encodingFormat":61,"isAccessibleForFree":64,"interactionStatistic":65},"DigitalDocument",{"name":9,"@type":57},"Person",{"url":41,"name":59,"@type":60},"DocShare","Organization","application/pdf","2026-08-05","2026-08-04",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},"What problem does the dissertation address in reservoir prediction?","Question",{"text":76,"@type":77},"It addresses uncertainty caused by incomplete subsurface information and by data issues such as measurement errors, processing choices, sampling bias, and heterogeneity that affect property estimation and forecasting.","Answer",{"name":79,"@type":74,"acceptedAnswer":80},"Which machine learning approaches are used to model uncertainty and predictions?",{"text":81,"@type":77},"It covers evaluation of machine learning-based uncertainty models, deep convolutional encoder-decoder networks for ensemble predictions, virtual ensembles in gradient-boosted decision trees for well-log imputation, and temporal fusion transformers for forecasting interpretability.",{"name":83,"@type":74,"acceptedAnswer":84},"How does the work support better decision-making in subsurface modeling?",{"text":85,"@type":77},"By producing robust, accurate, and interpretable uncertainty-aware workflows and forecasting models that account for associated uncertainties, enabling more reliable planning and resource decisions.","https://schema.org",{"og:url":52,"og:type":88,"og:title":13,"og:site_name":59,"og:description":14},"article",{"robots":90,"canonical":52},"index,follow",{"doc_id":7,"site_id":24},{"code":4,"msg":5,"data":93},[94,98,102,106,111,116,121,124,129,132,136],{"id":20,"doc_module":4,"doc_module_name":46,"category_name":95,"show_sort_weight":96,"slug":97},"Story & Novel",90,"story-novel",{"id":47,"doc_module":4,"doc_module_name":46,"category_name":99,"show_sort_weight":100,"slug":101},"Literature",80,"literature",{"id":53,"doc_module":4,"doc_module_name":46,"category_name":103,"show_sort_weight":104,"slug":105},"Exam",70,"exam",{"id":107,"doc_module":4,"doc_module_name":46,"category_name":108,"show_sort_weight":109,"slug":110},5,"Comic",60,"comic",{"id":112,"doc_module":4,"doc_module_name":46,"category_name":113,"show_sort_weight":114,"slug":115},6,"Technology",50,"technology",{"id":117,"doc_module":4,"doc_module_name":46,"category_name":118,"show_sort_weight":119,"slug":120},7,"Healthcare",40,"healthcare",{"id":11,"doc_module":4,"doc_module_name":46,"category_name":12,"show_sort_weight":122,"slug":123},30,"research-report",{"id":125,"doc_module":4,"doc_module_name":46,"category_name":126,"show_sort_weight":127,"slug":128},9,"Religion & Spirituality",20,"religion-spirituality",{"id":127,"doc_module":4,"doc_module_name":46,"category_name":130,"show_sort_weight":127,"slug":131},"World Cup","world-cup",{"id":133,"doc_module":4,"doc_module_name":46,"category_name":134,"show_sort_weight":133,"slug":135},10,"Lifestyle","lifestyle",{"id":137,"doc_module":4,"doc_module_name":46,"category_name":138,"show_sort_weight":107,"slug":139},19,"General","general"]