Details

<p>Foreword xvii</p> <p>Preface xix</p> <p><b>1 Introduction to Modern Intelligent Data Analysis 1</b></p> <p>1.1 Introduction 1</p> <p>1.2 Introduction to Machine Learning 4</p> <p>1.3 General Example of Machine Learning 8</p> <p>1.4 E&P Examples of Machine Learning 9</p> <p>1.5 Objectives of the Book 10</p> <p>1.6 Outline of Chapters 10</p> <p><b>2 Machine Learning and Human Computer Interface 23</b></p> <p>2.1 Introduction 23</p> <p>2.2 Visualization of Machine Learning 24</p> <p>2.3 Interactive Machine Learning 30</p> <p><b>3 Artificial Neural Networks 39</b></p> <p>3.1 Introduction 39</p> <p>3.2 Structure of Biological Neurons 41</p> <p>3.2.1 Artificial Neurons Structure 42</p> <p>3.2.2 Integration Function 43</p> <p>3.2.3 Activation Function 44</p> <p>3.2.4 Decision Boundaries 46</p> <p>3.3 Learning and Deep Learning Process for ANN 47</p> <p>3.3.1 ANN Learning 47</p> <p>3.3.2 Deep Learning 50</p> <p>3.4 Different Structures of ANNs 51</p> <p>3.4.1 Multi-Layer Perceptron (MLP) 53</p> <p>3.4.2 Radial Basis Function Neural Networks (RBF) 54</p> <p>3.4.3 Modular Neural Networks (Committee Machines) 55</p> <p>3.4.4 Self-Organizing Networks 58</p> <p>3.4.5 Kohonen Networks 61</p> <p>3.4.6 Generalized Regression (GRNN) and Probabilistic (pnn) 62</p> <p>3.4.7 Convolutional Neural Network (CNN) 64</p> <p>3.4.8 Generative Adversarial Network (GAN) 65</p> <p>3.4.9 Recurrent Neural Network (RNN) 66</p> <p>3.4.10 Long/Short-Term Memory (LSTM) 67</p> <p>3.5 Pre-Processing of the ANN Input Data 67</p> <p>3.5.1 Dimensionality Reduction 69</p> <p>3.5.2 Artificial Neural Networks (ANN) Versus Conventional Computing Tools (CCT) 70</p> <p>3.6 Combining ANN with Human Intelligence 70</p> <p>3.7 ANN Applications to the Exploration and Production (E&P) Problems 73</p> <p>3.7.1 First Break Picking Seismic Arrivals 74</p> <p>3.7.2 Porosity Prediction in a CO₂ Injection Project 76</p> <p>3.7.3 CNN for Permeability Prediction 78</p> <p>3.7.4 Creating Pseudologs 81</p> <p>3.7.5 Facies Classification with Exhustive PNN 81</p> <p>3.7.6 Machine Learning for Estimating the Stimulated Reservoir Volume (SRV) 83</p> <p><b>4 Fuzzy Logic 85</b></p> <p>4.1 Introduction to Fuzzy Logic 85</p> <p>4.2 Theoretical Foundation and Formal Treatment of Fuzzy Logic 90</p> <p>4.2.1 Some Definitions in Fuzzy Logic 93</p> <p>4.2.2 Fuzzy Propositions 94</p> <p>4.2.3 Thresholding or α-Cut Concept 95</p> <p>4.2.4 Additional Properties of Fuzzy Logic 96</p> <p>4.2.5 Fuzzy Extensions of Classical Mathematics 98</p> <p>4.2.5.1 Fuzzy Averaging 98</p> <p>4.2.5.2 Fuzzy Arithmetic 99</p> <p>4.2.5.3 Fuzzy Function and Fuzzy Patches 100</p> <p>4.2.5.4 Fuzzy K-Means and C-Means or Clustering 103</p> <p>4.2.5.5 Fuzzy Kriging 105</p> <p>4.2.5.6 Fuzzy Differential Equations 108</p> <p>4.2.6 Fuzzy Systems, Fuzzy Rules 109</p> <p>4.2.6.1 Fuzzy Rules 110</p> <p>4.2.6.2 Fuzzy Knowledge-Based Systems 112</p> <p>4.2.7 Type-2 Fuzzy Sets and Systems 114</p> <p>4.2.8 Computing with Words and Linguistic Variable 116</p> <p>4.2.8.1 CWW versus Fuzzy Logic 116</p> <p>4.2.8.2 Linguistic Variables 118</p> <p>4.2.9 Mining Fuzzy Rules from Examples 120</p> <p>4.2.10 Fuzzy Logic Software 121</p> <p>4.3 Oil and Gas Industry Application Domain Discussion 122</p> <p>4.3.1 Linguistic Goal-Oriented Decision Making (LGODM) to Optimize Enhanced Oil Recovery in the Steam Injection Process 123</p> <p>4.3.2 Use of Fuzzy Clustering in Perforation Design 124</p> <p>4.3.3 Stratigraphic Interpretation Using Fuzzy Rules 127</p> <p>4.3.4 Fuzzy Logic-Based Interpolation to Improve Seismic Resolution 132</p> <p>4.4 Conclusions 135</p> <p><b>5 Integration of Conventional and Unconventional Methods 137</b></p> <p>5.1 Strengths and Weaknesses of Different Computing Techniques 137</p> <p>5.2 Why Integrate Different Methods? 140</p> <p>5.2.1 Neuro-Fuzzy Methods 141</p> <p>5.2.1.1 Why Combine NN and FL? 142</p> <p>5.2.1.2 NN-Based FL Inference 143</p> <p>5.2.2 Neuro-Genetic Methods 145</p> <p>5.2.3 Fuzzy-Genetic (FG) 147</p> <p>5.2.4 Soft Computing - Conventional (SC) Methods 148</p> <p>5.3 Oil and Gas Applications of NF, NG, FG, CF, and CN 150</p> <p>5.3.1 NN-CM- Rock Permeability Forecast Using Machine Learning and Monte Carlo Committee Machines 151</p> <p>5.3.2 (NN-CM) Pseudo Density Log Generation Using Artificial Neural Network 154</p> <p>5.3.2.1 Well Log Data Preprocessing 155</p> <p>5.3.2.2 Well Log Data Mining 156</p> <p>5.3.2.3 Data Postprocessing for Generating Pseudo Density Logs 157</p> <p>5.3.3 NN-FL- Integrating Neural Networks and Fuzzy Logic for Improved Reservoir Property Prediction and Prospect Ranking 159</p> <p>5.3.4 (FL-NN-CM) Gas Leak Detection 161</p> <p>5.3.5 GA-FL for Improving Oil Recovery Factor 162</p> <p>5.3.6 GA-FL to Improve Coal Mining Process 165</p> <p>5.4 Conclusions 166</p> <p><b>6 Natural Language Processing 167</b></p> <p>6.1 Introduction 167</p> <p>6.2 A Brief History of NLP 168</p> <p>6.3 Basics of the NLP Method 171</p> <p>6.3.1 Sentence Segmentation 171</p> <p>6.3.2 Tokenization 172</p> <p>6.3.3 Parts of Speech Prediction 172</p> <p>6.3.4 Lemmatization 173</p> <p>6.3.5 Stop Words Removal 173</p> <p>6.3.6 Dependency Parsing 174</p> <p>6.3.7 Named Entity Recognition 175</p> <p>6.3.8 Coreference Resolution 175</p> <p>6.4 Use Cases of NLP 175</p> <p>6.5 Applications of NLP in the Oil and Gas Industry 177</p> <p>6.6 Conclusion 193</p> <p><b>7 Data Science and Big Data Analytics 195</b></p> <p>7.1 Introduction 195</p> <p>7.2 Big Data 195</p> <p>7.3 Algorithms and Models in Data Sciences 197</p> <p>7.3.1 Automated Machine Learning 198</p> <p>7.3.2 Interpretable, Explainable, and Privacy-Preserving Machine Learning 198</p> <p>7.4 Infrastructure and Tooling for Data Science 202</p> <p>7.5 Oil and Gas Focused Issues Associated with Data Science and Big Data High Performance Computing in the Age of Big Data 206</p> <p>7.5.1 Big Data in Oil and Gas 208</p> <p>7.5.2 High-Performance Computing for Handling Big Data in Subsurface Imaging 209</p> <p>7.5.3 Access to Oil and Gas Data 210</p> <p><b>8 Applications of Machine Learning in Exploration 213</b></p> <p>8.1 Introduction 213</p> <p>8.1.1 Petroleum System and Exploration Risk Factors 214</p> <p>8.1.2 Data Acquisition, Processing, and Integration for Exploration 215</p> <p>8.1.3 Exploration and Appraisal Drilling 217</p> <p>8.2 AI for Exploration Risk Assessment 218</p> <p>8.2.1 Petroleum System Risk Assessment 218</p> <p>8.2.2 Geological Risk Assessment Level of Knowledge and Experience (LoK) 221</p> <p>8.3 AI for Data Acquisition, Processing, and Integration in Exploration 224</p> <p>8.3.1 Auto-Picking for Micro-Seismic Data 224</p> <p>8.3.2 Facies Classification Using Supervised CNN and Semi-Supervised GAN 226</p> <p>8.3.3 Generating Gas Chimney Cube Using MLP ANN 227</p> <p>8.3.4 Reservoir Geostatistical Estimation of Imprecise Information Using Fuzzy Kriging Approach 230</p> <p>8.3.5 Fracture Zone Identification Using Seismic, Micro-Seismic and Well Log Data 232</p> <p><b>9 Applications in Oil and Gas Drilling 239</b></p> <p>9.1 Real-Time Measurements in Drilling Automation 239</p> <p>9.2 Event Detection in Drilling 243</p> <p>9.3 Rate of Penetration Estimations 251</p> <p>9.4 Estimation of the Bottom Hole and Formation Temperature by Drilling Data 255</p> <p>9.5 Drilling Dysfunctions 258</p> <p>9.6 Machine Learning Applications in Well Drilling Operations 262</p> <p>9.7 Conclusion 269</p> <p><b>10 Applications in Reservoir Characterization and Field Development Optimization 271</b></p> <p>10.1 Introduction 271</p> <p>10.1.1 Reservoir Characterization 273</p> <p>10.1.1.1 Porous Media Characterization 275</p> <p>10.1.1.2 Porosity 278</p> <p>10.1.1.3 Permeability 278</p> <p>10.1.1.4 Permeability-Porosity Relationship 281</p> <p>10.1.2 Machine Learning Applications for Reservoir Characterization 282</p> <p>10.1.2.1 Reservoir Modeling 291</p> <p>10.1.2.2 Capabilities of Data Mining 293</p> <p>10.1.2.3 Computational Intelligence in Petroleum Application 294</p> <p>10.1.2.4 Computational Intelligence in Permeability and Porosity Prediction 295</p> <p>10.1.2.5 Hybrid Computational Intelligence (HCI) 296</p> <p>10.1.2.6 Ensemble Machine Learning for Reservoir Characterization 297</p> <p>10.1.2.7 Prediction of Sand Fraction (SF) by Using Machine Learning 300</p> <p>10.1.2.8 Machine Learning Application in Classification of Water Saturation 301</p> <p>10.1.2.9 Physics-Informed Machine Learning for Real-Time Reservoir Management 302</p> <p>10.1.2.10 Well-Log and Seismic Data Integration for Reservoir Characterization 303</p> <p>10.1.2.11 Machine Learning for Homogeneous Reservoir Characterization 304</p> <p>10.1.2.12 The Gradient Boosting Method for Reservoir Characterization 305</p> <p>10.1.2.13 The Parameterizing Uncertainty for Reservoir Characterization 306</p> <p>10.1.2.14 Geochemistry and Chemostratigraphy for Reservoir Characterization 307</p> <p>10.2 Conclusions 310</p> <p><b>11 Machine Learning Applications in Production Forecasting 313</b></p> <p>11.1 Introduction 313</p> <p>11.2 Analytical Solution 315</p> <p>11.2.1 Type Curves 316</p> <p>11.2.2 Limitations 317</p> <p>11.3 Numerical Solution 317</p> <p>11.3.1 Limitations 318</p> <p>11.3.2 Machine Learning Applications 319</p> <p>11.4 Decline Curve Analysis (DCA) 320</p> <p>11.4.1 Arps Method 320</p> <p>11.4.2 Method Modifications of the Arps Method 321</p> <p>11.4.3 Limitations 326</p> <p>11.4.4 Machine Learning Applications 327</p> <p>11.5 Data-Driven Solutions 330</p> <p>11.5.1 Sensitivity Analysis 331</p> <p>11.5.2 Machine Learning Applications 331</p> <p>11.5.3 Limitations 349</p> <p>11.6 Conclusion 350</p> <p><b>12 Applications in Production Optimization, Well Completion and Stimulation 353</b></p> <p>12.1 Introduction 353</p> <p>12.2 Production Optimization 354</p> <p>12.3 Stimulation 358</p> <p>12.4 Well Completion 363</p> <p><b>13 Machine Learning Applications in Reservoir Engineering and Reservoir Simulation 369</b></p> <p>13.1 Introduction 369</p> <p>13.2 Fluid Properties Estimation with Machine Learning Methods 370</p> <p>13.2.1 Machine Learning Applications in Reservoir Simulation 376</p> <p>13.2.2 Machine Learning Applications in Geothermal Reservoir Engineering 390</p> <p>13.3 Machine Learning Applications in Well Testing 397</p> <p>13.4 Conclusion 403</p> <p><b>14 Machine Learning Applications in Artificial Lift 405</b></p> <p>14.1 Introduction 405</p> <p>14.2 Big Data and Analytical Solutions in Drilling Operations 407</p> <p>14.3 Machine Learning 408</p> <p>14.3.1 Using Machine Learning in the Oil and Gas Industry 410</p> <p>14.3.2 Failure Prediction Frameworks and Algorithms for Artificial Lift Systems 413</p> <p>14.4 Artificial Lift 415</p> <p>14.4.1 Brief Overview of Production Systems Analysis 416</p> <p>14.4.2 Types of the Artificial Lift Systems 418</p> <p>14.4.2.1 Plunger Lift 418</p> <p>14.4.2.2 Gas Lift-Continuous and Intermittent 419</p> <p>14.4.2.3 Pumps 421</p> <p>14.4.3 Artificial Lift Applications, Monitoring, and Automation Services 424</p> <p>14.5 Conclusion 429</p> <p><b>15 Machine Learning Applications in Enhanced Oil Recovery (EOR) 431</b></p> <p>15.1 Introduction 431</p> <p>15.2 Enhanced Oil Recovery 432</p> <p>15.2.1 Thermal Methods 437</p> <p>15.2.2 Chemical Methods 439</p> <p>15.2.3 Gas Methods 441</p> <p>15.2.4 Microbial Methods 444</p> <p>15.3 Enhanced Oil Recovery (EOR) Reservoirs 445</p> <p>15.4 The Economic Value of EOR 453</p> <p>15.5 Simulation Models 454</p> <p>15.6 Machine Learning (ML) 455</p> <p>15.7 Machine Learning in Enhanced Oil Recovery (EOR) Applications 458</p> <p>15.8 Machine Learning in Enhanced Oil Recovery (EOR) Screening 462</p> <p>15.9 Applications 465</p> <p>15.10 Software 467</p> <p>15.11 Conclusion 468</p> <p><b>16 Conclusions and Future Directions 471</b></p> <p>16.1 Technology Advances in Artificial Intelligence and Data Science 471</p> <p>16.1.1 Technology Advances in Artificial Intelligence and Data Science 471</p> <p>16.1.2 Future Directions of Machine Learning and Human-Computer Interface 471</p> <p>16.1.3 Future Directions of Artificial Neural Networks 474</p> <p>16.1.4 Future Directions of Fuzzy Logic 476</p> <p>16.1.5 Future Directions of Integrated AI Techniques 477</p> <p>16.1.6 Future Directions of Natural Language Processing 479</p> <p>16.1.7 Future Directions of Data Science and Big Data Analytics 480</p> <p>16.2 Future Trends in the Energy Applications of Artificial Intelligence and Data Science 482</p> <p>16.2.1 Future Trends in Exploration Applications of AI-DA 483</p> <p>16.2.2 Future Trends in Drilling Applications of AI-DA 484</p> <p>16.2.3 Future Trends in Reservoir Characterization Applications of AI-DA 486</p> <p>16.2.4 Future Trends in Production Forecasting Applications of AI-DA 487</p> <p>16.2.5 Future Trends in Production Optimization, Well Completion and Stimulation Applications of AI-DA 488</p> <p>16.2.6 Future Trends in Reservoir Engineering and Simulation Applications of AI-DA 489</p> <p>16.2.7 Future Trends in Artificial Lift Applications of AI-DA 491</p> <p>16.2.8 Future Work for Machine Learning Applications in EOR 492</p> <p>References 495</p> <p>Index 555</p>

<p><b>Fred Aminzadeh</b> 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 <i>The Journal of Sustainable Energy Engineering</i>. 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. <p><b>Cenk Temizel</b> 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), 2^nd 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. <p><b>Yasin Hajizadeh</b> 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.

<p><b>This groundbreaking new book is written by some of the foremost authorities on the application of data science and artificial intelligence techniques in exploration and production in the energy industry, covering the most comprehensive and updated new processes, concepts, and practical applications in the field.</b> <p>The book provides an in-depth treatment of the foundations of Artificial Intelligence (AI) Machine Learning, and Data Analytics (DA). It also includes many of AI-DA applications in oil and gas reservoirs exploration, development, and production. The book covers the basic technical details on many tools used in “smart oil fields”. This includes topics such as pattern recognition, neural networks, fuzzy logic, evolutionary computing, expert systems, artificial intelligence machine learning, human-computer interface, natural language processing, data analytics and next-generation visualization. While theoretical details will be kept to the minimum, these topics are introduced from oil and gas applications viewpoints. <p>In this volume, many case histories from the recent applications of intelligent data to a number of different oil and gas problems are highlighted. The applications cover a wide spectrum of practical problems from exploration to drilling and field development to production optimization, artificial lift, and secondary recovery. Also, the authors demonstrate the effectiveness of intelligent data analysis methods in dealing with many oil and gas problems requiring combining machine and human intelligence as well as dealing with linguistic and imprecise data and rules.

US