Artificial Intelligence and Data Analytics for Energy Exploration and Production

Fred Aminzadeh is an expert in artificial intelligence and energy. He was professor at the University of Houston and University of Southern California. He worked at dGB, Unocal (now part of Chevron) and Bell Laboratories. His work experience includes fossil energy, geothermal energy, and carbon sequestration. He served as the president of Society of Exploration Geophysicists. He has authored over 15 books and holds several patents. He was the editor in chief of The Journal of Sustainable Energy Engineering. Currently, he is president of FACT, an energy services company. He is also a member of technical advisory board of DOE/NETL’s SMART initiative and an adjunct Professor at the University of Wyoming.Cenk Temizel is a Sr. Reservoir Engineer with Saudi Aramco. He has over 15 years of experience in reservoir simulation, data analytics, smart fields, unconventional, enhanced oil recovery with Aera Energy, Schlumberger, and Halliburton in the Middle East, the U.S., and the U.K. He is the recipient of the Aramco Unconventional Resources Technical Contribution Award (2020), 2nd place at SPE Global R&D Competition at ATCE 2014, and the Halliburton Applause Award in Innovation (2012). He holds an MS degree in Petroleum Engineering from University of Southern California and was a research assistant at Stanford University before joining the industry.Yasin Hajizadeh is the founder and CEO of nowos, a boutique Texas based technology consulting firm with a focus on software product management and workforce development planning for industry 4.0. Previously, he was a program and product manager of Azure ML and IoT at Microsoft. Yasin has also worked for Schlumberger as a data scientist and reservoir engineer, University of Calgary as an associate professor of computer science, and CMG as an optimization and uncertainty quantification scientist. He holds a PhD in petroleum engineering from Heriot-Watt University, and a Masters in technology management from Memorial University of Newfoundland.

• Foreword xviiPreface xix1 Introduction to Modern Intelligent Data Analysis 11.1 Introduction 11.2 Introduction to Machine Learning 41.3 General Example of Machine Learning 81.4 E&P Examples of Machine Learning 91.5 Objectives of the Book 101.6 Outline of Chapters 102 Machine Learning and Human Computer Interface 232.1 Introduction 232.2 Visualization of Machine Learning 242.3 Interactive Machine Learning 303 Artificial Neural Networks 393.1 Introduction 393.2 Structure of Biological Neurons 413.2.1 Artificial Neurons Structure 423.2.2 Integration Function 433.2.3 Activation Function 443.2.4 Decision Boundaries 463.3 Learning and Deep Learning Process for ANN 473.3.1 ANN Learning 473.3.2 Deep Learning 503.4 Different Structures of ANNs 513.4.1 Multi-Layer Perceptron (MLP) 533.4.2 Radial Basis Function Neural Networks (RBF) 543.4.3 Modular Neural Networks (Committee Machines) 553.4.4 Self-Organizing Networks 583.4.5 Kohonen Networks 613.4.6 Generalized Regression (GRNN) and Probabilistic (pnn) 623.4.7 Convolutional Neural Network (CNN) 643.4.8 Generative Adversarial Network (GAN) 653.4.9 Recurrent Neural Network (RNN) 663.4.10 Long/Short-Term Memory (LSTM) 673.5 Pre-Processing of the ANN Input Data 673.5.1 Dimensionality Reduction 693.5.2 Artificial Neural Networks (ANN) Versus Conventional Computing Tools (CCT) 703.6 Combining ANN with Human Intelligence 703.7 ANN Applications to the Exploration and Production (E&P) Problems 733.7.1 First Break Picking Seismic Arrivals 743.7.2 Porosity Prediction in a CO2 Injection Project 763.7.3 CNN for Permeability Prediction 783.7.4 Creating Pseudologs 813.7.5 Facies Classification with Exhustive PNN 813.7.6 Machine Learning for Estimating the Stimulated Reservoir Volume (SRV) 834 Fuzzy Logic 854.1 Introduction to Fuzzy Logic 854.2 Theoretical Foundation and Formal Treatment of Fuzzy Logic 904.2.1 Some Definitions in Fuzzy Logic 934.2.2 Fuzzy Propositions 944.2.3 Thresholding or α-Cut Concept 954.2.4 Additional Properties of Fuzzy Logic 964.2.5 Fuzzy Extensions of Classical Mathematics 984.2.5.1 Fuzzy Averaging 984.2.5.2 Fuzzy Arithmetic 994.2.5.3 Fuzzy Function and Fuzzy Patches 1004.2.5.4 Fuzzy K-Means and C-Means or Clustering 1034.2.5.5 Fuzzy Kriging 1054.2.5.6 Fuzzy Differential Equations 1084.2.6 Fuzzy Systems, Fuzzy Rules 1094.2.6.1 Fuzzy Rules 1104.2.6.2 Fuzzy Knowledge-Based Systems 1124.2.7 Type-2 Fuzzy Sets and Systems 1144.2.8 Computing with Words and Linguistic Variable 1164.2.8.1 CWW versus Fuzzy Logic 1164.2.8.2 Linguistic Variables 1184.2.9 Mining Fuzzy Rules from Examples 1204.2.10 Fuzzy Logic Software 1214.3 Oil and Gas Industry Application Domain Discussion 1224.3.1 Linguistic Goal-Oriented Decision Making (LGODM) to Optimize Enhanced Oil Recovery in the Steam Injection Process 1234.3.2 Use of Fuzzy Clustering in Perforation Design 1244.3.3 Stratigraphic Interpretation Using Fuzzy Rules 1274.3.4 Fuzzy Logic-Based Interpolation to Improve Seismic Resolution 1324.4 Conclusions 1355 Integration of Conventional and Unconventional Methods 1375.1 Strengths and Weaknesses of Different Computing Techniques 1375.2 Why Integrate Different Methods? 1405.2.1 Neuro-Fuzzy Methods 1415.2.1.1 Why Combine NN and FL? 1425.2.1.2 NN-Based FL Inference 1435.2.2 Neuro-Genetic Methods 1455.2.3 Fuzzy-Genetic (FG) 1475.2.4 Soft Computing - Conventional (SC) Methods 1485.3 Oil and Gas Applications of NF, NG, FG, CF, and CN 1505.3.1 NN-CM- Rock Permeability Forecast Using Machine Learning and Monte Carlo Committee Machines 1515.3.2 (NN-CM) Pseudo Density Log Generation Using Artificial Neural Network 1545.3.2.1 Well Log Data Preprocessing 1555.3.2.2 Well Log Data Mining 1565.3.2.3 Data Postprocessing for Generating Pseudo Density Logs 1575.3.3 NN-FL- Integrating Neural Networks and Fuzzy Logic for Improved Reservoir Property Prediction and Prospect Ranking 1595.3.4 (FL-NN-CM) Gas Leak Detection 1615.3.5 GA-FL for Improving Oil Recovery Factor 1625.3.6 GA-FL to Improve Coal Mining Process 1655.4 Conclusions 1666 Natural Language Processing 1676.1 Introduction 1676.2 A Brief History of NLP 1686.3 Basics of the NLP Method 1716.3.1 Sentence Segmentation 1716.3.2 Tokenization 1726.3.3 Parts of Speech Prediction 1726.3.4 Lemmatization 1736.3.5 Stop Words Removal 1736.3.6 Dependency Parsing 1746.3.7 Named Entity Recognition 1756.3.8 Coreference Resolution 1756.4 Use Cases of NLP 1756.5 Applications of NLP in the Oil and Gas Industry 1776.6 Conclusion 1937 Data Science and Big Data Analytics 1957.1 Introduction 1957.2 Big Data 1957.3 Algorithms and Models in Data Sciences 1977.3.1 Automated Machine Learning 1987.3.2 Interpretable, Explainable, and Privacy-Preserving Machine Learning 1987.4 Infrastructure and Tooling for Data Science 2027.5 Oil and Gas Focused Issues Associated with Data Science and Big Data High Performance Computing in the Age of Big Data 2067.5.1 Big Data in Oil and Gas 2087.5.2 High-Performance Computing for Handling Big Data in Subsurface Imaging 2097.5.3 Access to Oil and Gas Data 2108 Applications of Machine Learning in Exploration 2138.1 Introduction 2138.1.1 Petroleum System and Exploration Risk Factors 2148.1.2 Data Acquisition, Processing, and Integration for Exploration 2158.1.3 Exploration and Appraisal Drilling 2178.2 AI for Exploration Risk Assessment 2188.2.1 Petroleum System Risk Assessment 2188.2.2 Geological Risk Assessment Level of Knowledge and Experience (LoK) 2218.3 AI for Data Acquisition, Processing, and Integration in Exploration 2248.3.1 Auto-Picking for Micro-Seismic Data 2248.3.2 Facies Classification Using Supervised CNN and Semi-Supervised GAN 2268.3.3 Generating Gas Chimney Cube Using MLP ANN 2278.3.4 Reservoir Geostatistical Estimation of Imprecise Information Using Fuzzy Kriging Approach 2308.3.5 Fracture Zone Identification Using Seismic, Micro-Seismic and Well Log Data 2329 Applications in Oil and Gas Drilling 2399.1 Real-Time Measurements in Drilling Automation 2399.2 Event Detection in Drilling 2439.3 Rate of Penetration Estimations 2519.4 Estimation of the Bottom Hole and Formation Temperature by Drilling Data 2559.5 Drilling Dysfunctions 2589.6 Machine Learning Applications in Well Drilling Operations 2629.7 Conclusion 26910 Applications in Reservoir Characterization and Field Development Optimization 27110.1 Introduction 27110.1.1 Reservoir Characterization 27310.1.1.1 Porous Media Characterization 27510.1.1.2 Porosity 27810.1.1.3 Permeability 27810.1.1.4 Permeability-Porosity Relationship 28110.1.2 Machine Learning Applications for Reservoir Characterization 28210.1.2.1 Reservoir Modeling 29110.1.2.2 Capabilities of Data Mining 29310.1.2.3 Computational Intelligence in Petroleum Application 29410.1.2.4 Computational Intelligence in Permeability and Porosity Prediction 29510.1.2.5 Hybrid Computational Intelligence (HCI) 29610.1.2.6 Ensemble Machine Learning for Reservoir Characterization 29710.1.2.7 Prediction of Sand Fraction (SF) by Using Machine Learning 30010.1.2.8 Machine Learning Application in Classification of Water Saturation 30110.1.2.9 Physics-Informed Machine Learning for Real-Time Reservoir Management 30210.1.2.10 Well-Log and Seismic Data Integration for Reservoir Characterization 30310.1.2.11 Machine Learning for Homogeneous Reservoir Characterization 30410.1.2.12 The Gradient Boosting Method for Reservoir Characterization 30510.1.2.13 The Parameterizing Uncertainty for Reservoir Characterization 30610.1.2.14 Geochemistry and Chemostratigraphy for Reservoir Characterization 30710.2 Conclusions 31011 Machine Learning Applications in Production Forecasting 31311.1 Introduction 31311.2 Analytical Solution 31511.2.1 Type Curves 31611.2.2 Limitations 31711.3 Numerical Solution 31711.3.1 Limitations 31811.3.2 Machine Learning Applications 31911.4 Decline Curve Analysis (DCA) 32011.4.1 Arps Method 32011.4.2 Method Modifications of the Arps Method 32111.4.3 Limitations 32611.4.4 Machine Learning Applications 32711.5 Data-Driven Solutions 33011.5.1 Sensitivity Analysis 33111.5.2 Machine Learning Applications 33111.5.3 Limitations 34911.6 Conclusion 35012 Applications in Production Optimization, Well Completion and Stimulation 35312.1 Introduction 35312.2 Production Optimization 35412.3 Stimulation 35812.4 Well Completion 36313 Machine Learning Applications in Reservoir Engineering and Reservoir Simulation 36913.1 Introduction 36913.2 Fluid Properties Estimation with Machine Learning Methods 37013.2.1 Machine Learning Applications in Reservoir Simulation 37613.2.2 Machine Learning Applications in Geothermal Reservoir Engineering 39013.3 Machine Learning Applications in Well Testing 39713.4 Conclusion 40314 Machine Learning Applications in Artificial Lift 40514.1 Introduction 40514.2 Big Data and Analytical Solutions in Drilling Operations 40714.3 Machine Learning 40814.3.1 Using Machine Learning in the Oil and Gas Industry 41014.3.2 Failure Prediction Frameworks and Algorithms for Artificial Lift Systems 41314.4 Artificial Lift 41514.4.1 Brief Overview of Production Systems Analysis 41614.4.2 Types of the Artificial Lift Systems 41814.4.2.1 Plunger Lift 41814.4.2.2 Gas Lift-Continuous and Intermittent 41914.4.2.3 Pumps 42114.4.3 Artificial Lift Applications, Monitoring, and Automation Services 42414.5 Conclusion 42915 Machine Learning Applications in Enhanced Oil Recovery (EOR) 43115.1 Introduction 43115.2 Enhanced Oil Recovery 43215.2.1 Thermal Methods 43715.2.2 Chemical Methods 43915.2.3 Gas Methods 44115.2.4 Microbial Methods 44415.3 Enhanced Oil Recovery (EOR) Reservoirs 44515.4 The Economic Value of EOR 45315.5 Simulation Models 45415.6 Machine Learning (ML) 45515.7 Machine Learning in Enhanced Oil Recovery (EOR) Applications 45815.8 Machine Learning in Enhanced Oil Recovery (EOR) Screening 46215.9 Applications 46515.10 Software 46715.11 Conclusion 46816 Conclusions and Future Directions 47116.1 Technology Advances in Artificial Intelligence and Data Science 47116.1.1 Technology Advances in Artificial Intelligence and Data Science 47116.1.2 Future Directions of Machine Learning and Human-Computer Interface 47116.1.3 Future Directions of Artificial Neural Networks 47416.1.4 Future Directions of Fuzzy Logic 47616.1.5 Future Directions of Integrated AI Techniques 47716.1.6 Future Directions of Natural Language Processing 47916.1.7 Future Directions of Data Science and Big Data Analytics 48016.2 Future Trends in the Energy Applications of Artificial Intelligence and Data Science 48216.2.1 Future Trends in Exploration Applications of AI-DA 48316.2.2 Future Trends in Drilling Applications of AI-DA 48416.2.3 Future Trends in Reservoir Characterization Applications of AI-DA 48616.2.4 Future Trends in Production Forecasting Applications of AI-DA 48716.2.5 Future Trends in Production Optimization, Well Completion and Stimulation Applications of AI-DA 48816.2.6 Future Trends in Reservoir Engineering and Simulation Applications of AI-DA 48916.2.7 Future Trends in Artificial Lift Applications of AI-DA 49116.2.8 Future Work for Machine Learning Applications in EOR 492References 495Index 555