Machine Learning For The Subsurface Characterization At Core Well And Reservoir Scales

Advances in Subsurface Data Analytics: Traditional and Physics-Based Approaches brings together the fundamentals of popular and emerging machine learning (ML) algorithms with their applications in subsurface analysis, including geology, geophysics, petrophysics, and reservoir engineering. The book is divided into four parts: traditional ML, deep learning, physics-based ML, and new directions, with an increasing level of diversity and complexity of topics. Each chapter focuses on one ML algorithm with a detailed workflow for a specific application in geosciences. Some chapters also compare the results from an algorithm with others to better equip the readers with different strategies to implement automated workflows for subsurface analysis. Advances in Subsurface Data Analytics: Traditional and Physics-Based Approaches will help researchers in academia and professional geoscientists working on the subsurface-related problems (oil and gas, geothermal, carbon sequestration, and seismology) at different scales to understand and appreciate current trends in ML approaches, their applications, advances and limitations, and future potential in geosciences by bringing together several contributions in a single volume. Covers fundamentals of simple machine learning and deep learning algorithms, and physics-based approaches written by practitioners in academia and industry Presents detailed case studies of individual machine learning algorithms and optimal strategies in subsurface characterization around the world Offers an analysis of future trends in machine learning in geosciences

This book provides readers with a timely review and discussion of the success, promise, and perils of machine learning in geosciences. It explores the fundamentals of data science and machine learning, and how their advances have disrupted the traditional workflows used in the industry and academia, including geology, geophysics, petrophysics, geomechanics, and geochemistry. It then presents the real-world applications and explains that, while this disruption has affected the top-level executives, geoscientists as well as field operators in the industry and academia, machine learning will ultimately benefit these users. The book is written by a practitioner of machine learning and statistics, keeping geoscientists in mind. It highlights the need to go beyond concepts covered in STAT 101 courses and embrace new computational tools to solve complex problems in geosciences. It also offers practitioners, researchers, and academics insights into how to identify, develop, deploy, and recommend fit-for-purpose machine learning models to solve real-world problems in subsurface geosciences.

Machine Learning for Subsurface Characterization develops and applies neural networks, random forests, deep learning, unsupervised learning, Bayesian frameworks, and clustering methods for subsurface characterization. Machine learning (ML) focusses on developing computational methods/algorithms that learn to recognize patterns and quantify functional relationships by processing large data sets, also referred to as the "big data." Deep learning (DL) is a subset of machine learning that processes "big data" to construct numerous layers of abstraction to accomplish the learning task. DL methods do not require the manual step of extracting/engineering features; however, it requires us to provide large amounts of data along with high-performance computing to obtain reliable results in a timely manner. This reference helps the engineers, geophysicists, and geoscientists get familiar with data science and analytics terminology relevant to subsurface characterization and demonstrates the use of data-driven methods for outlier detection, geomechanical/electromagnetic characterization, image analysis, fluid saturation estimation, and pore-scale characterization in the subsurface. Learn from 13 practical case studies using field, laboratory, and simulation data Become knowledgeable with data science and analytics terminology relevant to subsurface characterization Learn frameworks, concepts, and methods important for the engineer’s and geoscientist’s toolbox needed to support

Artificial Intelligence for Subsurface Characterization and Monitoring provides an in-depth examination of how deep learning accelerates the process of subsurface characterization and monitoring and provides an end-to-end solution. In recent years, deep learning has been introduced to the geoscience community to overcome some longstanding technical challenges. This book explores some of the most important topics in this discipline to explain the unique capability of deep learning in subsurface characterization for hydrocarbon exploration and production and for energy transition. Readers will discover deep learning methods that can improve the quality and efficiency of many of the key steps in subsurface characterization and monitoring. The text is organized into five parts. The first two parts explore deep learning for data enrichment and well log data, including information extraction from unstructured well reports as well as log data QC and processing. Next is a review of deep learning applied to seismic data and data integration, which also covers intelligent processing for clearer seismic images and rock property inversion and validation. The closing section looks at deep learning in time lapse scenarios, including sparse data reconstruction for reducing the cost of 4D seismic data, time-lapse seismic data repeatability enforcement, and direct property prediction from pre-migration seismic data. Focuses on deep learning applications for geoscience provides a one-stop reference for deep learning applications for geoscience Provides comprehensive examples for state-of-art techniques throughout the subsurface characterization workflow Presented applications come with realistic field dataset examples so that readers can learn what to expect in real-life

Deep subsurface characterization technologies and demands are changing rapidly within the energy industry. In this swiftly evolving landscape, the wide range of analyses performed on the rocks and fluids obtained from cores remain fundamental tools in managing subsurface uncertainty and associated risk. During the energy transition large volumes of newly acquired and legacy core will be accessed to better understand both existing hydrocarbon resources and other subsurface energy-related systems, particularly for carbon capture, utilization and storage (CCUS), geothermal energy and the long-term storage of nuclear waste. Through state-of-the-art reviews and case studies this volume illustrates how innovative approaches continue to create value from both new and historical cores recovered for deep subsurface reservoir characterization and storage complex evaluation. Such an assessment is timely given that the sector sits at a pivotal point in terms of changing technologies, economics, demographics, skillsets and energy solutions.

RESERVOIR CHARACTERIZATION The second volume in the series, “Sustainable Energy Engineering,” written by some of the foremost authorities in the world on reservoir engineering, this groundbreaking new volume presents the most comprehensive and updated new processes, equipment, and practical applications in the field. Long thought of as not being “sustainable,” newly discovered sources of petroleum and newly developed methods for petroleum extraction have made it clear that not only can the petroleum industry march toward sustainability, but it can be made “greener” and more environmentally friendly. Sustainable energy engineering is where the technical, economic, and environmental aspects of energy production intersect and affect each other. This collection of papers covers the strategic and economic implications of methods used to characterize petroleum reservoirs. Born out of the journal by the same name, formerly published by Scrivener Publishing, most of the articles in this volume have been updated, and there are some new additions, as well, to keep the engineer abreast of any updates and new methods in the industry. Truly a snapshot of the state of the art, this groundbreaking volume is a must-have for any petroleum engineer working in the field, environmental engineers, petroleum engineering students, and any other engineer or scientist working with reservoirs. This outstanding new volume: Is a collection of papers on reservoir characterization written by world-renowned engineers and scientists and presents them here, in one volume Contains in-depth coverage of not just the fundamentals of reservoir characterization, but the anomalies and challenges, set in application-based, real-world situations Covers reservoir characterization for the engineer to be able to solve daily problems on the job, whether in the field or in the office Deconstructs myths that are prevalent and deeply rooted in the industry and reconstructs logical solutions Is a valuable resource for the veteran engineer, new hire, or petroleum engineering student

Reservoir Simulation: Machine Learning and Modeling helps the engineer step into the current and most popular advances in reservoir simulation, learning from current experiments and speeding up potential collaboration opportunities in research and technology. This reference explains common terminology, concepts, and equations through multiple figures and rigorous derivations, better preparing the engineer for the next step forward in a modeling project and avoid repeating existing progress. Well-designed exercises, case studies and numerical examples give the engineer a faster start on advancing their own cases. Both computational methods and engineering cases are explained, bridging the opportunities between computational science and petroleum engineering. This book delivers a critical reference for today’s petroleum and reservoir engineer to optimize more complex developments. Understand commonly used and recent progress on definitions, models, and solution methods used in reservoir simulation World leading modeling and algorithms to study flow and transport behaviors in reservoirs, as well as the application of machine learning Gain practical knowledge with hand-on trainings on modeling and simulation through well designed case studies and numerical examples.

Scientific progress over the last decade has been significantly facilitated by the evolution of a new breed of intelligent solutions, characterized by their ability to learn without being explicitly programmed with the governing physics. In the oil and gas industry, machine learning alternatives are becoming increasingly popular, however most solutions within this discipline are still very raw in their conceptualization and application. In this work, three major areas in petroleum engineering are addressed and resolved using machine learning: well placement evaluation and optimization, time-series output prediction, and geological modeling. Simultaneous optimization of well placements and controls is a recurring problem in reservoir management and field development. Because of their high computational expense, reservoir simulators are limited in their applicability to joint optimization procedures requiring many evaluations. Data-driven proxies could provide inexpensive alternatives for approximating reservoir responses, however, geologic complexity of most reservoirs often makes it impossible to model or reproduce the response surface using well location data alone. We propose a machine learning approach in which the feature set is augmented by a connectivity network comprised of pairwise well-to-well connectivities for any potential well configuration. Connectivities are represented by 'diffusive times of flight' of the pressure front, computed using the Fast Marching Method (FMM). The Gradient Boosting Method is then used to build intelligent models for making reservoir-wide predictions such as net present value, given any set of well locations and control values. Accurate prediction of future reservoir performance and well production rates is important for optimizing oil recovery strategies. In the absence of geologic models, this could purely be considered as a time-series analysis problem. The premise of this class of problems is that relationships between input and output sequences can be learned from historical data and used to predict future output. However, because the state of the reservoir changes with time, the value of a future output variable such as production rate also depends on its own history. We introduce a novel scheme to predict reservoir output during recovery processes using Recurrent Neural Networks (RNN) and Long Short-Term Memory (LSTM) networks. The method was applied to two case studies wherein predictive models were built to forecast well production using historical rate data, yielding satisfactory results. A synthetic demonstration showed that the proposed method outperformed Capacitance Resistance Modeling (CRM) in terms of prediction accuracy. Spatial interpolation and geologic modeling of petrophysical properties are traditionally performed using conventional geostatistical algorithms. The most common techniques include the Sequential Gaussian Simulation (SGS) for continuous variable modeling, and multiple-point simulation (MPS) for facies or categorical variable modeling. These techniques produce adequate results but are prone to subjectivity and could rely heavily on the modeler's intuition. Machine learning techniques provide a more automated alternative for geologic modeling, and have the ability to more accurately predict petrophysical properties outside the data locations. We propose a new hybridized method in which Bayesian Neural Network (BNN) predictions are used as kriging covariates in conjunction with SGS. The hybridized models show improved prediction accuracy in comparison with kriging and SGS, while retaining geological realism and producing exact estimates