Useful attributes capture and quantify key components of the seismic amplitude and texture for subsequent integration with well log, microseismic, and production data through either interactive visualization or machine learning. Although both approaches can accelerate and facilitate the interpretation process, they can by no means replace the interpreter. Interpreter “grayware” includes the incorporation and validation of depositional, diagenetic, and tectonic deformation models, the integration of rock physics systematics, and the recognition of unanticipated opportunities and hazards. This book is written to accompany and complement the 2018 SEG Distinguished Instructor Short Course that provides a rapid overview of how 3D seismic attributes provide a framework for data integration over the life of the oil and gas field. Key concepts are illustrated by example, showing modern workflows based on interactive interpretation and display as well as those aided by machine learning.

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

Reservoir Characterization, Modeling and Quantitative Interpretation: Recent Workflows to Emerging Technologies offers a wide spectrum of reservoir characterization techniques and technologies, focusing on the latest breakthroughs and most efficient methodologies in hydrocarbon exploration and development. Topics covered include 4D seismic technologies, AVAz inversion, fracture characterization, multiscale imaging technologies, static and dynamic reservoir characterization, among others. The content is delivered through an inductive approach, which will help readers gain comprehensive insights on advanced practices and be able to relate them to other subareas of reservoir characterization, including CO2 storage and data-driven modeling. This will be especially useful for field scientists in collecting and analyzing field data, prospect evaluation, developing reservoir models, and adopting new technologies to mitigate exploration risk. They will be able to solve the practical and challenging problems faced in the field of reservoir characterization, as it will offer systematic industrial workflows covering every aspect of this branch of Earth Science, including subsurface geoscientific perspectives of carbon geosequestration. This resource is a 21st Century guide for exploration geologists, geoscience students at postgraduate level and above, and petrophysicists working in the oil and gas industry. - Covers the latest and most effective technologies in reservoir characterization, including Avo analysis, AVAz inversion, wave field separation and Machine Learning techniques - Provides a balanced blend of both theoretical and practical approaches for solving challenges in reservoir characterization - Includes detailed industry-standard practical workflows, along with code structures for algorithms and practice exercises

Understanding Faults: Detecting, Dating, and Modeling offers a single resource for analyzing faults for a variety of applications, from hazard detection and earthquake processes, to geophysical exploration. The book presents the latest research, including fault dating using new mineral growth, fault reactivation, and fault modeling, and also helps bridge the gap between geologists and geophysicists working across fault-related disciplines. Using diagrams, formulae, and worldwide case studies to illustrate concepts, the book provides geoscientists and industry experts in oil and gas with a valuable reference for detecting, modeling, analyzing and dating faults. - Presents cutting-edge information relating to fault analysis, including mechanical, geometrical and numerical models, theory and methodologies - Includes calculations of fault sealing capabilities - Describes how faults are detected, what fault models predict, and techniques for dating fault movement - Utilizes worldwide case studies throughout the book to concretely illustrate key concepts

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.

This book introduces readers to the field of seismic data interpretation and evaluation, covering themes such as petroleum exploration and high resolution seismic data. It helps geoscientists and engineers who are practitioners in this area to both understand and to avoid the potential pitfalls of interpreting and evaluating such data, especially the over-reliance on sophisticated software packages and workstations alongside a lack of grasp on the elementary principles of geology and geophysics. Chapters elaborate on the necessary principles, from topics like seismic wave propagation and rock-fluid parameters to seismic modeling and inversions, explaining the need to understand geological implications. The difference between interpretation of data and its evaluation is highlighted and the author encourages imaginative, logical and practical application of knowledge. Readers will appreciate the exquisite illustrations included with the accessibly written text, which simplify the process of learning about interpretation of seismic data. This multidisciplinary, integrated and practical approach to data evaluation will prove to be a valuable tool for students and young professionals, especially those connected with oil companies.

This book introduces practical seismic analysis techniques and evaluation of interpretation confidence, for graduate students and industry professionals - independent of commercial software products.

In this volume, the geologic framework is established with review papers by experts in carbonate generation, rock properties, sequence and seismic stratigraphy, and structural deformation. Then seismic expression of carbonate terranes is explored in case studies showing the importance of integrating seismic and petrophysical control with geologic models.

Published in 2002, the first edition of Geostatistical Reservoir Modeling brought the practice of petroleum geostatistics into a coherent framework, focusing on tools, techniques, examples, and guidance. It emphasized the interaction between geophysicists, geologists, and engineers, and was received well by professionals, academics, and both graduate and undergraduate students. In this revised second edition, Deutsch collaborates with co-author Michael Pyrcz to provide an expanded (in coverage and format), full color illustrated, more comprehensive treatment of the subject with a full update on the latest tools, methods, practice, and research in the field of petroleum Geostatistics. Key geostatistical concepts such as integration of geologic data and concepts, scale considerations, and uncertainty models receive greater attention, and new comprehensive sections are provided on preliminary geological modeling concepts, data inventory, conceptual model, problem formulation, large scale modeling, multiple point-based simulation and event-based modeling. Geostatistical methods are extensively illustrated through enhanced schematics, work flows and examples with discussion on method capabilities and selection. For example, this expanded second edition includes extensive discussion on the process of moving from an inventory of data and concepts through conceptual model to problem formulation to solve practical reservoir problems. A greater number of examples are included, with a set of practical geostatistical studies developed to illustrate the steps from data analysis and cleaning to post-processing, and ranking. New methods, which have developed in the field since the publication of the first edition, are discussed, such as models for integration of diverse data sources, multiple point-based simulation, event-based simulation, spatial bootstrap and methods to summarize geostatistical realizations.