Название: A Primer on Machine Learning in Subsurface Geosciences
Автор: Shuvajit Bhattacharya
Издательство: Springer
Год: 2021
Страниц: 182
Язык: английский
Формат: pdf (true)
Размер: 12.0 MB

This book provides readers with a timely review and discussion of the success, promise, and perils of Machine Learning (ML) 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.

This book provides a timely review and discussion of the fundamentals, workflow, proven success, promises, and perils of ML. It can be used as a ready-to-go reference for understanding machine learning and its nuances in both subsurface and surface applications.

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.

Chapter 1 deals with the necessary foundations of data analytics, machine learning, geoscience databases, and the concept of scales. An overview of the history of ML narrates how different algorithms came into the community, offered new solutions, and were supplanted by new algorithms offering better new solutions.
Chapter 2 systematically discusses different statistical measures used in the geosciences and provides examples. This will prepare readers to understand the types of data analytics applied to geoscience data.
Chapter 3 deals with the basic ML workflow, including supervised, unsupervised, and semi-supervised approaches. The concepts of deep learning workflow are also included.
Chapter 4 provides a brief review of popular ML algorithms, including emerging deep learning and physics-informed ML. Each algorithm is covered with its fundamentals, network hyperparameters, optimization, and geoscience-specific examples.
Chapter 5 summarizes various ML applications in structure, stratigraphy, rock properties, and fluid-flow analysis using core, well log, seismic, and fiber-optic data.
Chapter 6 discusses the differences in modern data analytics approaches from past approaches, current challenges, and opportunities for geoscientists in both industry and academia.