Artificial intelligence for a more sustainable oil and gas industry and the energy transition : case studies and code examples /

Artificial Intelligence for a More Sustainable Oil and Gas Industry and the Energy Transition: Case Studies and Code Examples presents a package for academic researchers and industries working on water resources and carbon capture and storage. This book contains fundamental knowledge on artificial i...

Full description

Bibliographic Details
Main Author:	Ahmadi, Mohammadali (Author)
Corporate Author:	ScienceDirect (Online service)
Format:	eBook
Language:	English
Published:	Amsterdam, Netherlands : Elsevier, 2024.
Subjects:	Petroleum industry and trade > Data processing. Artificial intelligence > Industrial applications. Petroleum industry and trade > Environmental aspects. Pétrole > Industrie et commerce > Informatique. Intelligence artificielle > Applications industrielles. Electronic books.
Online Access:	Connect to the full text of this electronic book

Table of Contents:

Front Cover
Artificial Intelligence for a More Sustainable Oil and Gas Industry and the Energy Transition
Copyright Page
Contents
1 Artificial intelligence (AI) overview
1.1 Introduction
1.2 Types of AI in terms of autonomy level and capabilities
1.2.1 Reactive machines
1.2.2 Limited memory
1.2.3 Theory of mind
1.2.4 Self-aware
1.2.5 Strong AI
1.2.6 Weak AI
1.3 Types of AI in terms of applications
1.3.1 Machine learning
1.3.2 Deep learning
1.3.3 Robotics
1.3.4 Expert systems
1.3.5 Computer vision
1.4 Opportunities and challenges
1.5 Summary
Disclosure
References
2 Machine learning
2.1 Introduction
2.2 Types of machine learning
2.2.1 Supervised learning
2.2.2 Unsupervised learning
2.2.3 Reinforcement learning
2.2.4 Semisupervised learning
2.3 Challenges of ML development in the oil and gas industry
2.4 Performance indicators of ML models
2.4.1 Confusion matrix
2.4.2 Classification accuracy
2.4.3 F1 score
2.4.4 Receiver operating characteristic curve
2.4.5 Area under curve
2.4.6 Mean absolute error
2.4.7 Mean squared error
2.4.8 Root mean square error
2.4.9 Average relative error
2.4.10 Squared correlation coefficient (R2)
2.4.11 Variance accounted for (VAF)
2.5 Summary
AI disclosure
References
3 Classification
3.1 Introduction
3.1.1 Statistical methods
3.1.2 Rule-based methods
3.1.3 Instance-based methods
3.1.4 Neural network methods
3.1.5 Ensemble methods
3.2 Statistical methods
3.2.1 Support vector machine
3.2.1.1 Linear kernel
3.2.1.2 Polynomial kernel
3.2.1.3 RBF kernel
3.2.1.4 Sigmoid kernel
3.2.2 Discriminant analysis
3.2.3 Naive Bayes
3.2.4 Logistic regression
3.3 Rule-based methods
3.3.1 Decision Trees
3.3.2 Rule-based classifiers
3.3.3 Associative classification
3.3.4 Bayesian networks
3.3.5 Decision Trees
3.3.6 Rule-based classifiers
3.3.7 Associative classification
3.3.8 Bayesian networks
3.4 Instance-based methods
3.4.1 K-Nearest Neighbor
3.4.2 Case-based reasoning
3.4.3 Locally weighted learning
3.5 Neural network methods
3.6 Ensemble methods
3.6.1 Bagging method
3.6.2 Boosting method
3.6.3 Random Forest
3.6.4 AdaBoost
3.6.5 Stacking
3.7 Case studies
3.7.1 Enhanced Oil Recovery type prediction
3.7.1.1 Data preprocessing
3.7.1.2 Classification models and evaluation
3.7.2 Lithology identification
3.7.3 Data loading and preprocessing
3.7.4 Data splitting and feature scaling
3.7.5 Classification models
3.7.6 Model evaluation and hyperparameter tuning
3.7.7 Results and visualizations
AI disclosure
References
4 Regression
4.1 Introduction
4.2 Regression types
4.2.1 Linear regression
4.2.2 Polynomial regression
4.2.3 Ridge regression