Data Science and Machine Learning Applications in Subsurface Engineering

This book covers machine learning techniques for subsurface engineering, including unsupervised learning, supervised learning, clustering approaches, feature engineering, explainable AI, and multioutput regression models. It focuses on processing voluminous and complex data sets to identify patterns and predict relationships. The book discusses data pre-processing, feature selection, feature engineering, and outlier removal, and introduces new models to improve the performance of traditional ML models. It demonstrates the use of data-driven approaches for salt identification, seismic interpretation, oil recovery, pore fluid prediction, and other subsurface engineering applications.

Format: Hardback
Length: 306 pages
Publication date: 06 February 2024
Publisher: Taylor & Francis Ltd

Machine learning (ML) is a rapidly evolving field that focuses on developing data-driven methods and computational algorithms to understand and predict complex and non-linear patterns in data. It has gained significant importance in various industries, including subsurface engineering, where it is used to process voluminous and complex data sets to identify patterns and relationships between variables.

The primary objective of ML is to develop models that can learn from data and make accurate predictions. However, achieving accurate predictions requires several steps, including data pre-processing, feature selection, feature engineering, and outlier removal. This book covers these steps in detail, providing practical insights and techniques for subsurface engineering applications.

One of the key challenges in subsurface engineering is handling small and big data without manual adjustments. ML models can help address this challenge by leveraging existing ML architecture and learning theories to improve the performance of traditional ML models. This book demonstrates the use of new models and architectures to handle small and big data, enabling subsurface engineers to make more accurate predictions and decisions.

In addition to handling data, ML is also used in various subsurface engineering applications, such as salt identification, seismic interpretation, enhanced oil recovery factor estimation, pore fluid type prediction, petrophysical property prediction, pressure drop in pipelines, bubble point pressure prediction, enhancing drilling mud loss, smart well completion, and synthetic well log predictions. This book provides examples and case studies of these applications, showcasing the practical benefits of data-driven approaches in subsurface engineering.

Overall, this research-oriented book will help subsurface engineers, geophysicists, and geoscientists become familiar with data science and ML advances relevant to subsurface engineering. It demonstrates the use of data-driven approaches for solving complex subsurface engineering problems and provides practical insights and techniques for implementing ML solutions in practice.

Weight: 752g
Dimension: 234 x 156 (mm)
ISBN-13: 9781032433646