Pethuru Raj Chelliah, PhD, is the Vice President and Chief Architect at Reliance Jio Platforms Ltd. In Bangalore, India. Venkatraman Jayasankar is the Lead Solutions Architect (Upstream) at a leading oil and gas company. Mats Agerstam is a Principal Engineer at Intel’s Network and Edge Group, Portland, Oregon, USA. B. Sundaravadivazhagan, PhD, is a Professor with the Department of Information Technology at the University of Technology and Applied Sciences Al Mussanah, Oman. Robin Cyriac, PhD, is a Professor with the Department of Information Technology at the University of Technology and Applied Sciences Al Mussanah, Oman.

• About the Authors xxiiiForeword xxvPreface xxvii1 A Perspective of the Oil and Gas Industry 11.1 Exploration and Production 21.2 Midstream Transportation 41.3 Downstream–Refining and Marketing 61.4 Meaning of Different Terms of Products Produced by the Oil and Gas Industry 71.5 Oil and Gas Pricing 161.6 A Note on Renewable Energy Sources 171.7 Environmental Impact 201.8 Uses of Hydrogen 202 Artificial Intelligence (AI) for the Future of the Oil and Gas (O&G) Industry 232.1 Introduction 232.2 The Emergence of Digitization Technologies and Tools 242.3 Demystifying Digitalization Technologies and Tools 252.4 Briefing the Potentials of Artificial Intelligence (AI) 252.5 AI for the Oil and Gas (O&G) Industry 272.6 Computer Vision (CV)-Enabled Use Cases 342.7 Natural Language Processing (NLP) Use Cases 362.8 Robots in the Oil and Gas Industry 362.9 Drones in the Oil and Gas Industry 372.10 AI Applications for the Oil and Gas (O&G) Industry 392.11 Better Decision-Making Using AI 412.12 Cloud AI vs. Edge AI for the Oil and Gas Industry 442.13 AI Model Optimization Techniques 472.14 Conclusion 483 Artificial Intelligence for Sophisticated Applications in the Oil and Gas Industry 513.1 Introduction 513.2 Oil and Gas Industry 523.3 Artificial Intelligence 543.4 Lifecycle of Oil and Gas Industry 543.5 Applications of AI in Oil and Gas industry 563.6 Chatbots 563.7 Optimized Procurement 593.8 Drilling, Production, and Reservoir Management 613.9 Inventory Management 623.10 Well Monitoring 643.11 Process Excellence and Automation 643.12 Asset Tracking and Maintenance/Digital Twins 653.13 Optimizing Production and Scheduling 673.14 Emission Tracking 683.15 Logistics Network Optimizations 693.16 Conclusion 704 Demystifying the Oil and Gas Exploration and Extraction Process 734.1 Process of Crude Oil Formation 734.2 Composition of Crude Oil 744.3 Crude Oil Classification 744.4 Crude Oil Production Process 764.5 Oil Exploration 774.6 Oil Extraction 784.7 Processing of Crude Oil 814.8 Overview of Refining 884.9 Marketing and Distribution of Oil and Gas 924.10 End of Production 934.11 Factors Influencing the Timing of Oil and Gas Exploration and Production 934.12 Non-revenue Benefits of the Oil and Gas Industry 954.13 Conclusion 955 Explaining the Midstream Activities in the Oil and Gas Domain 975.1 Introduction 975.2 Role of Midstream Sector in Oil and Gas Industry 985.3 Midstream Oil and Gas Operations 995.4 Technological Advancements in Midstream Sector 1045.5 Midstream Sector Challenges 1115.6 Conclusion 1146 The Significance of the Industrial Internet of Things (IIoT) for the Oil and Gas Space 1176.1 Overview of IIoT 1176.2 Technical Innovators of Industrial Internet 1256.3 IoT for Oil and Gas Sector 1276.4 Rebellion of IoT in the Oil and Gas Sector 1326.5 Oil and Gas Remote Monitoring Systems 1366.6 Advantages of IIOT for the Oil and Gas Industry 1426.7 Conclusion 1447 The Power of Edge AI Technologies for Real-Time Use Cases in the Oil and Gas Domain 1477.1 Introduction 1477.2 Demystifying the Paradigm of Artificial Intelligence (AI) 1487.3 Describing the Phenomenon of Edge Computing 1497.4 Delineating Edge Computing Advantages 1517.5 Demarcating the Move Toward Edge AI 1547.6 Why Edge AI Gains Momentum? 1557.7 The Enablers of Edge AI 1607.8 5G-Advanced Communication 1607.9 Why Edge AI is Being Pursued with Alacrity? 1647.10 Edge AI Frameworks and Accelerators 1657.11 Conclusion 1758 AI-Enabled Robots for Automating Oil and Gas Operations 1778.1 Briefing the Impending Digital Era 1778.2 Depicting the Digital Power 1788.3 Robotics: The Use Cases 1818.4 Real-Life Examples of Robotic Solutions in the Oil and Gas Industry 1848.5 The Advantages of Robotic Solutions 1908.6 The Dawn of the Internet of Robotic Things 1948.7 Conclusion 1979 AI-Empowered Drones for Versatile Oil and Gas Use Cases 1999.1 Introduction 1999.2 The Upstream Process 2009.3 The Midstream Process 2019.4 The Downstream Process 2029.5 Navigation Technologies for Drones 2029.6 Drones Specialities and Successes 2069.7 The Emergence of State-of-the-Art Drones 2099.8 Drones in the Oil and Gas Industry 2159.9 AI-Enabled Drone Services 2179.10 AI Platforms for Drones 2199.11 Conclusion 22210 The Importance of Artificial Intelligence for the Oil and Gas Industry 22410.1 Introduction 22410.2 Reducing Well/Equipment Downtime 22510.3 Optimizing Production and Scheduling 22810.4 Detecting Anomalies by Enabling Automation in Assets using Robots 23010.5 Inspection and Cleanliness of Reactors, Heat Exchangers, and Its Components 23310.6 AI-Enabled Training and Safety 23410.7 Summary 23411 Illustrating the 5G Communication Capabilities for the Future of the Oil and Gas Industry 23711.1 Introduction to 5G Communication 23711.2 5G Architecture 24311.3 Antennas For 5G 24611.4 5G Use Cases 24711.5 5G and Digitalization in Oil and Gas 25211.6 5G Smart Monitoring Instruments 25911.7 Conclusion 26012 Delineating the Cloud and Edge-Native Technologies for Intelligent Oil and Gas Systems 26312.1 Introduction 26312.2 Cloud Native Technologies – Motivation 26412.3 Containers 26512.4 Microservices 26812.5 Continuous Integration, Continuous Deployment (CI/CD) 27412.6 Edge Computing 27712.7 Conclusion 29213 Explaining the Industrial IoT Standardization Efforts Toward Interoperability 29313.1 Introduction 29313.2 Different Aspects of Interoperability 29313.3 ISA95 29413.4 SCADA (Supervisory Control and Data Acquisition) 29613.5 The Choice of Network Technology 29613.6 OPAF 30213.7 OPC-UA 30513.8 DDS 31013.9 Integration with Telemetry and Big Data 31113.10 IEC Standards used in the OPAF 31113.11 RedFish 31213.12 The FieldComm Group 31414 Digital Twins for the Digitally Transformed O&G Industry 31614.1 Digital Twins (DTs) 31614.2 Digital Twins in Manufacturing 31614.3 Digital Twins in Process Efficiency 31714.4 Digital Twins and Quality Assurance 31714.5 Digital Twins and Supply Chain 31714.6 Digital Twins and Predictive Maintenance 31714.7 Industry 4.0 31814.8 Digital Twin Concept 31914.9 Standards and Interoperability 32014.10 IDTA Standard 32114.11 Digital Twin Consortium 32214.12 Digital Twin in O&G 32214.13 DT Complexity and Trade-offs 32314.14 Architectural Concepts 32314.15 Simulations 32414.16 Digital Twins vs. Simulations 32714.17 Digital Twin Products 32814.18 Digital Twins and Manufacturing in the Future 32915 IoT Edge Security Methods for Secure and Safe Oil and Gas Environments 33115.1 Introduction 33115.2 Protecting Data 33215.3 Past Examples of Security Attacks 33215.4 Security Foundation 33415.5 Cryptographic Hash Function 33715.6 Keyed Hash Message Authentication Code 33815.7 Public Key Infrastructure (PKI) 33815.8 Digital Signatures 34015.9 Threat Analysis and Understanding Adversaries 34115.10 Trusted Computing Base 34215.11 Edge Security and RoT (Root of Trust) 34215.12 DICE – Device Identifier Composition Engine 34315.13 Boot Integrity 34315.14 Data Sanitization 34515.15 Total Memory Encryption 34615.16 Secure Device Onboarding 34715.17 Attestation 35015.18 Defense in Depth 35215.19 Zero Trust Architecture (ZTA) 35415.20 Security Hardened Edge Compute Architectures 35416 Securing the Energy Industry with AI-Powered Cybersecurity Solutions 35616.1 Introduction 35616.2 Energy Industry 35716.3 Present and Future of Energy Industry Supply Chain 35916.4 Cybersecurity 36116.5 Digitizing of the Energy Industry 36416.6 MITRE ATT&CK Framework 36716.7 CVE 36816.8 CWE 37016.9 CAPEC 37016.10 CPE 37016.11 Cybersecurity Framework 37016.12 NIST Framework 37116.13 Zero-Day Vulnerability 37216.14 Machine Learning 37316.15 Artificial Intelligence 37416.16 Fusing AI into Cybersecurity 37516.17 Threat Modeling in AI 37916.18 Incident Response 38216.19 Fire Sale Scenario 38316.20 Conclusion 38417 Explainable Artificial Intelligence (XAI) for the Trust and Transparency of the Oil and Gas Systems 38717.1 Introduction 38717.2 The Growing Power of Artificial Intelligence 38817.3 The Challenges and Concerns of Artificial Intelligence 39017.4 About the Need for AI Explainability 39117.5 AI Explainability: The Problem It Solves 39217.6 What is the AI Explainability Challenges? 39317.7 The Importance of Explainable AI 39317.8 The Importance of Model Interpretation 39617.9 Briefing Feature Importance Scoring Methods 40117.10 Local Interpretable Model-agnostic Explanations (LIME) 40217.11 SHAP Explainability Algorithm 40417.12 Conclusion 40718 Blockchain for Enhanced Efficiency, Trust, and Transparency in the Oil and Gas Domain 40918.1 Introduction 40918.2 The Brewing Challenges of the Oil and Gas Industry 41018.3 About the Blockchain Technology 41318.4 Blockchain-Powered Use Cases for the Oil and Gas Industry 41518.5 Blockchain for Improved Trust 41618.6 Sensor-Enabled Invoicing 41718.7 Transportation Tracing 41818.8 Data Storage and Management 41918.9 Digital Oil and Gas: Strengthening and Simplifying Supply Chain 41918.10 Commodity Trading 42118.11 Land Record Management 42118.12 Financial Reconciliation 42218.13 Oil Wells and Equipment Maintenance 42318.14 Waste Management and Recycling 42318.15 Tracking Carbon Footprint 42418.16 Improved Pipeline Inspection 42418.17 Other Miscellaneous Advantages of Blockchain 42518.18 Blockchain Challenges 42518.19 Conclusion 42619 AI-Inspired Digital Twins for the Oil and Gas Domain 42819.1 How to Ensure Certainty Using DT for AI 43219.2 Tools Needed to Develop Digital Twins 43419.3 Digital Twin Implementation Approach at a High Level 43419.4 Digital Twin of Oil and Gas Production 44119.5 Solution Approach 44219.6 Future of Digital Twins 44320 Future Directions of Green Hydrogen and Other Fueling Sources 44720.1 Introduction 44720.2 Green Hydrogen Technologies 44820.3 Current and Future Industrial Applications of Hydrogen 44920.4 The Exploitation of Hydrogen Fuel in a Future System 45020.5 Green Hydrogen: Fuel of the Future 45120.6 Extraction of Hydrogen with Diagrammatic Representation 45320.7 Hydrogen Fuel System Advantages and Disadvantages 45420.8 AI-Based Approach for Emerging Green Hydrogen Technologies for Sustainability 45520.9 Challenges of Hydrogen with AI Technologies 45820.10 The Expected Use and Forecast for Hydrogen Fuel Cells in the Future 45820.11 Conclusion 459Bibliography 460Index 461

Pethuru Raj Chelliah, PhD, is the Vice President and Chief Architect at Reliance Jio Platforms Ltd. In Bangalore, India. Venkatraman Jayasankar is the Lead Solutions Architect (Upstream) at a leading oil and gas company. Mats Agerstam is a Principal Engineer at Intel’s Network and Edge Group, Portland, Oregon, USA. B. Sundaravadivazhagan, PhD, is a Professor with the Department of Information Technology at the University of Technology and Applied Sciences Al Mussanah, Oman. Robin Cyriac, PhD, is a Professor with the Department of Information Technology at the University of Technology and Applied Sciences Al Mussanah, Oman.

• About the Authors xxiiiForeword xxvPreface xxvii1 A Perspective of the Oil and Gas Industry 11.1 Exploration and Production 21.2 Midstream Transportation 41.3 Downstream–Refining and Marketing 61.4 Meaning of Different Terms of Products Produced by the Oil and Gas Industry 71.5 Oil and Gas Pricing 161.6 A Note on Renewable Energy Sources 171.7 Environmental Impact 201.8 Uses of Hydrogen 202 Artificial Intelligence (AI) for the Future of the Oil and Gas (O&G) Industry 232.1 Introduction 232.2 The Emergence of Digitization Technologies and Tools 242.3 Demystifying Digitalization Technologies and Tools 252.4 Briefing the Potentials of Artificial Intelligence (AI) 252.5 AI for the Oil and Gas (O&G) Industry 272.6 Computer Vision (CV)-Enabled Use Cases 342.7 Natural Language Processing (NLP) Use Cases 362.8 Robots in the Oil and Gas Industry 362.9 Drones in the Oil and Gas Industry 372.10 AI Applications for the Oil and Gas (O&G) Industry 392.11 Better Decision-Making Using AI 412.12 Cloud AI vs. Edge AI for the Oil and Gas Industry 442.13 AI Model Optimization Techniques 472.14 Conclusion 483 Artificial Intelligence for Sophisticated Applications in the Oil and Gas Industry 513.1 Introduction 513.2 Oil and Gas Industry 523.3 Artificial Intelligence 543.4 Lifecycle of Oil and Gas Industry 543.5 Applications of AI in Oil and Gas industry 563.6 Chatbots 563.7 Optimized Procurement 593.8 Drilling, Production, and Reservoir Management 613.9 Inventory Management 623.10 Well Monitoring 643.11 Process Excellence and Automation 643.12 Asset Tracking and Maintenance/Digital Twins 653.13 Optimizing Production and Scheduling 673.14 Emission Tracking 683.15 Logistics Network Optimizations 693.16 Conclusion 704 Demystifying the Oil and Gas Exploration and Extraction Process 734.1 Process of Crude Oil Formation 734.2 Composition of Crude Oil 744.3 Crude Oil Classification 744.4 Crude Oil Production Process 764.5 Oil Exploration 774.6 Oil Extraction 784.7 Processing of Crude Oil 814.8 Overview of Refining 884.9 Marketing and Distribution of Oil and Gas 924.10 End of Production 934.11 Factors Influencing the Timing of Oil and Gas Exploration and Production 934.12 Non-revenue Benefits of the Oil and Gas Industry 954.13 Conclusion 955 Explaining the Midstream Activities in the Oil and Gas Domain 975.1 Introduction 975.2 Role of Midstream Sector in Oil and Gas Industry 985.3 Midstream Oil and Gas Operations 995.4 Technological Advancements in Midstream Sector 1045.5 Midstream Sector Challenges 1115.6 Conclusion 1146 The Significance of the Industrial Internet of Things (IIoT) for the Oil and Gas Space 1176.1 Overview of IIoT 1176.2 Technical Innovators of Industrial Internet 1256.3 IoT for Oil and Gas Sector 1276.4 Rebellion of IoT in the Oil and Gas Sector 1326.5 Oil and Gas Remote Monitoring Systems 1366.6 Advantages of IIOT for the Oil and Gas Industry 1426.7 Conclusion 1447 The Power of Edge AI Technologies for Real-Time Use Cases in the Oil and Gas Domain 1477.1 Introduction 1477.2 Demystifying the Paradigm of Artificial Intelligence (AI) 1487.3 Describing the Phenomenon of Edge Computing 1497.4 Delineating Edge Computing Advantages 1517.5 Demarcating the Move Toward Edge AI 1547.6 Why Edge AI Gains Momentum? 1557.7 The Enablers of Edge AI 1607.8 5G-Advanced Communication 1607.9 Why Edge AI is Being Pursued with Alacrity? 1647.10 Edge AI Frameworks and Accelerators 1657.11 Conclusion 1758 AI-Enabled Robots for Automating Oil and Gas Operations 1778.1 Briefing the Impending Digital Era 1778.2 Depicting the Digital Power 1788.3 Robotics: The Use Cases 1818.4 Real-Life Examples of Robotic Solutions in the Oil and Gas Industry 1848.5 The Advantages of Robotic Solutions 1908.6 The Dawn of the Internet of Robotic Things 1948.7 Conclusion 1979 AI-Empowered Drones for Versatile Oil and Gas Use Cases 1999.1 Introduction 1999.2 The Upstream Process 2009.3 The Midstream Process 2019.4 The Downstream Process 2029.5 Navigation Technologies for Drones 2029.6 Drones Specialities and Successes 2069.7 The Emergence of State-of-the-Art Drones 2099.8 Drones in the Oil and Gas Industry 2159.9 AI-Enabled Drone Services 2179.10 AI Platforms for Drones 2199.11 Conclusion 22210 The Importance of Artificial Intelligence for the Oil and Gas Industry 22410.1 Introduction 22410.2 Reducing Well/Equipment Downtime 22510.3 Optimizing Production and Scheduling 22810.4 Detecting Anomalies by Enabling Automation in Assets using Robots 23010.5 Inspection and Cleanliness of Reactors, Heat Exchangers, and Its Components 23310.6 AI-Enabled Training and Safety 23410.7 Summary 23411 Illustrating the 5G Communication Capabilities for the Future of the Oil and Gas Industry 23711.1 Introduction to 5G Communication 23711.2 5G Architecture 24311.3 Antennas For 5G 24611.4 5G Use Cases 24711.5 5G and Digitalization in Oil and Gas 25211.6 5G Smart Monitoring Instruments 25911.7 Conclusion 26012 Delineating the Cloud and Edge-Native Technologies for Intelligent Oil and Gas Systems 26312.1 Introduction 26312.2 Cloud Native Technologies – Motivation 26412.3 Containers 26512.4 Microservices 26812.5 Continuous Integration, Continuous Deployment (CI/CD) 27412.6 Edge Computing 27712.7 Conclusion 29213 Explaining the Industrial IoT Standardization Efforts Toward Interoperability 29313.1 Introduction 29313.2 Different Aspects of Interoperability 29313.3 ISA95 29413.4 SCADA (Supervisory Control and Data Acquisition) 29613.5 The Choice of Network Technology 29613.6 OPAF 30213.7 OPC-UA 30513.8 DDS 31013.9 Integration with Telemetry and Big Data 31113.10 IEC Standards used in the OPAF 31113.11 RedFish 31213.12 The FieldComm Group 31414 Digital Twins for the Digitally Transformed O&G Industry 31614.1 Digital Twins (DTs) 31614.2 Digital Twins in Manufacturing 31614.3 Digital Twins in Process Efficiency 31714.4 Digital Twins and Quality Assurance 31714.5 Digital Twins and Supply Chain 31714.6 Digital Twins and Predictive Maintenance 31714.7 Industry 4.0 31814.8 Digital Twin Concept 31914.9 Standards and Interoperability 32014.10 IDTA Standard 32114.11 Digital Twin Consortium 32214.12 Digital Twin in O&G 32214.13 DT Complexity and Trade-offs 32314.14 Architectural Concepts 32314.15 Simulations 32414.16 Digital Twins vs. Simulations 32714.17 Digital Twin Products 32814.18 Digital Twins and Manufacturing in the Future 32915 IoT Edge Security Methods for Secure and Safe Oil and Gas Environments 33115.1 Introduction 33115.2 Protecting Data 33215.3 Past Examples of Security Attacks 33215.4 Security Foundation 33415.5 Cryptographic Hash Function 33715.6 Keyed Hash Message Authentication Code 33815.7 Public Key Infrastructure (PKI) 33815.8 Digital Signatures 34015.9 Threat Analysis and Understanding Adversaries 34115.10 Trusted Computing Base 34215.11 Edge Security and RoT (Root of Trust) 34215.12 DICE – Device Identifier Composition Engine 34315.13 Boot Integrity 34315.14 Data Sanitization 34515.15 Total Memory Encryption 34615.16 Secure Device Onboarding 34715.17 Attestation 35015.18 Defense in Depth 35215.19 Zero Trust Architecture (ZTA) 35415.20 Security Hardened Edge Compute Architectures 35416 Securing the Energy Industry with AI-Powered Cybersecurity Solutions 35616.1 Introduction 35616.2 Energy Industry 35716.3 Present and Future of Energy Industry Supply Chain 35916.4 Cybersecurity 36116.5 Digitizing of the Energy Industry 36416.6 MITRE ATT&CK Framework 36716.7 CVE 36816.8 CWE 37016.9 CAPEC 37016.10 CPE 37016.11 Cybersecurity Framework 37016.12 NIST Framework 37116.13 Zero-Day Vulnerability 37216.14 Machine Learning 37316.15 Artificial Intelligence 37416.16 Fusing AI into Cybersecurity 37516.17 Threat Modeling in AI 37916.18 Incident Response 38216.19 Fire Sale Scenario 38316.20 Conclusion 38417 Explainable Artificial Intelligence (XAI) for the Trust and Transparency of the Oil and Gas Systems 38717.1 Introduction 38717.2 The Growing Power of Artificial Intelligence 38817.3 The Challenges and Concerns of Artificial Intelligence 39017.4 About the Need for AI Explainability 39117.5 AI Explainability: The Problem It Solves 39217.6 What is the AI Explainability Challenges? 39317.7 The Importance of Explainable AI 39317.8 The Importance of Model Interpretation 39617.9 Briefing Feature Importance Scoring Methods 40117.10 Local Interpretable Model-agnostic Explanations (LIME) 40217.11 SHAP Explainability Algorithm 40417.12 Conclusion 40718 Blockchain for Enhanced Efficiency, Trust, and Transparency in the Oil and Gas Domain 40918.1 Introduction 40918.2 The Brewing Challenges of the Oil and Gas Industry 41018.3 About the Blockchain Technology 41318.4 Blockchain-Powered Use Cases for the Oil and Gas Industry 41518.5 Blockchain for Improved Trust 41618.6 Sensor-Enabled Invoicing 41718.7 Transportation Tracing 41818.8 Data Storage and Management 41918.9 Digital Oil and Gas: Strengthening and Simplifying Supply Chain 41918.10 Commodity Trading 42118.11 Land Record Management 42118.12 Financial Reconciliation 42218.13 Oil Wells and Equipment Maintenance 42318.14 Waste Management and Recycling 42318.15 Tracking Carbon Footprint 42418.16 Improved Pipeline Inspection 42418.17 Other Miscellaneous Advantages of Blockchain 42518.18 Blockchain Challenges 42518.19 Conclusion 42619 AI-Inspired Digital Twins for the Oil and Gas Domain 42819.1 How to Ensure Certainty Using DT for AI 43219.2 Tools Needed to Develop Digital Twins 43419.3 Digital Twin Implementation Approach at a High Level 43419.4 Digital Twin of Oil and Gas Production 44119.5 Solution Approach 44219.6 Future of Digital Twins 44320 Future Directions of Green Hydrogen and Other Fueling Sources 44720.1 Introduction 44720.2 Green Hydrogen Technologies 44820.3 Current and Future Industrial Applications of Hydrogen 44920.4 The Exploitation of Hydrogen Fuel in a Future System 45020.5 Green Hydrogen: Fuel of the Future 45120.6 Extraction of Hydrogen with Diagrammatic Representation 45320.7 Hydrogen Fuel System Advantages and Disadvantages 45420.8 AI-Based Approach for Emerging Green Hydrogen Technologies for Sustainability 45520.9 Challenges of Hydrogen with AI Technologies 45820.10 The Expected Use and Forecast for Hydrogen Fuel Cells in the Future 45820.11 Conclusion 459Bibliography 460Index 461

Pethuru Raj Chelliah, PhD, is the Vice President and Chief Architect at Reliance Jio Platforms Ltd. In Bangalore, India. Venkatraman Jayasankar is the Lead Solutions Architect (Upstream) at a leading oil and gas company. Mats Agerstam is a Principal Engineer at Intel’s Network and Edge Group, Portland, Oregon, USA. B. Sundaravadivazhagan, PhD, is a Professor with the Department of Information Technology at the University of Technology and Applied Sciences Al Mussanah, Oman. Robin Cyriac, PhD, is a Professor with the Department of Information Technology at the University of Technology and Applied Sciences Al Mussanah, Oman.

• About the Authors xxiiiForeword xxvPreface xxvii1 A Perspective of the Oil and Gas Industry 11.1 Exploration and Production 21.2 Midstream Transportation 41.3 Downstream–Refining and Marketing 61.4 Meaning of Different Terms of Products Produced by the Oil and Gas Industry 71.5 Oil and Gas Pricing 161.6 A Note on Renewable Energy Sources 171.7 Environmental Impact 201.8 Uses of Hydrogen 202 Artificial Intelligence (AI) for the Future of the Oil and Gas (O&G) Industry 232.1 Introduction 232.2 The Emergence of Digitization Technologies and Tools 242.3 Demystifying Digitalization Technologies and Tools 252.4 Briefing the Potentials of Artificial Intelligence (AI) 252.5 AI for the Oil and Gas (O&G) Industry 272.6 Computer Vision (CV)-Enabled Use Cases 342.7 Natural Language Processing (NLP) Use Cases 362.8 Robots in the Oil and Gas Industry 362.9 Drones in the Oil and Gas Industry 372.10 AI Applications for the Oil and Gas (O&G) Industry 392.11 Better Decision-Making Using AI 412.12 Cloud AI vs. Edge AI for the Oil and Gas Industry 442.13 AI Model Optimization Techniques 472.14 Conclusion 483 Artificial Intelligence for Sophisticated Applications in the Oil and Gas Industry 513.1 Introduction 513.2 Oil and Gas Industry 523.3 Artificial Intelligence 543.4 Lifecycle of Oil and Gas Industry 543.5 Applications of AI in Oil and Gas industry 563.6 Chatbots 563.7 Optimized Procurement 593.8 Drilling, Production, and Reservoir Management 613.9 Inventory Management 623.10 Well Monitoring 643.11 Process Excellence and Automation 643.12 Asset Tracking and Maintenance/Digital Twins 653.13 Optimizing Production and Scheduling 673.14 Emission Tracking 683.15 Logistics Network Optimizations 693.16 Conclusion 704 Demystifying the Oil and Gas Exploration and Extraction Process 734.1 Process of Crude Oil Formation 734.2 Composition of Crude Oil 744.3 Crude Oil Classification 744.4 Crude Oil Production Process 764.5 Oil Exploration 774.6 Oil Extraction 784.7 Processing of Crude Oil 814.8 Overview of Refining 884.9 Marketing and Distribution of Oil and Gas 924.10 End of Production 934.11 Factors Influencing the Timing of Oil and Gas Exploration and Production 934.12 Non-revenue Benefits of the Oil and Gas Industry 954.13 Conclusion 955 Explaining the Midstream Activities in the Oil and Gas Domain 975.1 Introduction 975.2 Role of Midstream Sector in Oil and Gas Industry 985.3 Midstream Oil and Gas Operations 995.4 Technological Advancements in Midstream Sector 1045.5 Midstream Sector Challenges 1115.6 Conclusion 1146 The Significance of the Industrial Internet of Things (IIoT) for the Oil and Gas Space 1176.1 Overview of IIoT 1176.2 Technical Innovators of Industrial Internet 1256.3 IoT for Oil and Gas Sector 1276.4 Rebellion of IoT in the Oil and Gas Sector 1326.5 Oil and Gas Remote Monitoring Systems 1366.6 Advantages of IIOT for the Oil and Gas Industry 1426.7 Conclusion 1447 The Power of Edge AI Technologies for Real-Time Use Cases in the Oil and Gas Domain 1477.1 Introduction 1477.2 Demystifying the Paradigm of Artificial Intelligence (AI) 1487.3 Describing the Phenomenon of Edge Computing 1497.4 Delineating Edge Computing Advantages 1517.5 Demarcating the Move Toward Edge AI 1547.6 Why Edge AI Gains Momentum? 1557.7 The Enablers of Edge AI 1607.8 5G-Advanced Communication 1607.9 Why Edge AI is Being Pursued with Alacrity? 1647.10 Edge AI Frameworks and Accelerators 1657.11 Conclusion 1758 AI-Enabled Robots for Automating Oil and Gas Operations 1778.1 Briefing the Impending Digital Era 1778.2 Depicting the Digital Power 1788.3 Robotics: The Use Cases 1818.4 Real-Life Examples of Robotic Solutions in the Oil and Gas Industry 1848.5 The Advantages of Robotic Solutions 1908.6 The Dawn of the Internet of Robotic Things 1948.7 Conclusion 1979 AI-Empowered Drones for Versatile Oil and Gas Use Cases 1999.1 Introduction 1999.2 The Upstream Process 2009.3 The Midstream Process 2019.4 The Downstream Process 2029.5 Navigation Technologies for Drones 2029.6 Drones Specialities and Successes 2069.7 The Emergence of State-of-the-Art Drones 2099.8 Drones in the Oil and Gas Industry 2159.9 AI-Enabled Drone Services 2179.10 AI Platforms for Drones 2199.11 Conclusion 22210 The Importance of Artificial Intelligence for the Oil and Gas Industry 22410.1 Introduction 22410.2 Reducing Well/Equipment Downtime 22510.3 Optimizing Production and Scheduling 22810.4 Detecting Anomalies by Enabling Automation in Assets using Robots 23010.5 Inspection and Cleanliness of Reactors, Heat Exchangers, and Its Components 23310.6 AI-Enabled Training and Safety 23410.7 Summary 23411 Illustrating the 5G Communication Capabilities for the Future of the Oil and Gas Industry 23711.1 Introduction to 5G Communication 23711.2 5G Architecture 24311.3 Antennas For 5G 24611.4 5G Use Cases 24711.5 5G and Digitalization in Oil and Gas 25211.6 5G Smart Monitoring Instruments 25911.7 Conclusion 26012 Delineating the Cloud and Edge-Native Technologies for Intelligent Oil and Gas Systems 26312.1 Introduction 26312.2 Cloud Native Technologies – Motivation 26412.3 Containers 26512.4 Microservices 26812.5 Continuous Integration, Continuous Deployment (CI/CD) 27412.6 Edge Computing 27712.7 Conclusion 29213 Explaining the Industrial IoT Standardization Efforts Toward Interoperability 29313.1 Introduction 29313.2 Different Aspects of Interoperability 29313.3 ISA95 29413.4 SCADA (Supervisory Control and Data Acquisition) 29613.5 The Choice of Network Technology 29613.6 OPAF 30213.7 OPC-UA 30513.8 DDS 31013.9 Integration with Telemetry and Big Data 31113.10 IEC Standards used in the OPAF 31113.11 RedFish 31213.12 The FieldComm Group 31414 Digital Twins for the Digitally Transformed O&G Industry 31614.1 Digital Twins (DTs) 31614.2 Digital Twins in Manufacturing 31614.3 Digital Twins in Process Efficiency 31714.4 Digital Twins and Quality Assurance 31714.5 Digital Twins and Supply Chain 31714.6 Digital Twins and Predictive Maintenance 31714.7 Industry 4.0 31814.8 Digital Twin Concept 31914.9 Standards and Interoperability 32014.10 IDTA Standard 32114.11 Digital Twin Consortium 32214.12 Digital Twin in O&G 32214.13 DT Complexity and Trade-offs 32314.14 Architectural Concepts 32314.15 Simulations 32414.16 Digital Twins vs. Simulations 32714.17 Digital Twin Products 32814.18 Digital Twins and Manufacturing in the Future 32915 IoT Edge Security Methods for Secure and Safe Oil and Gas Environments 33115.1 Introduction 33115.2 Protecting Data 33215.3 Past Examples of Security Attacks 33215.4 Security Foundation 33415.5 Cryptographic Hash Function 33715.6 Keyed Hash Message Authentication Code 33815.7 Public Key Infrastructure (PKI) 33815.8 Digital Signatures 34015.9 Threat Analysis and Understanding Adversaries 34115.10 Trusted Computing Base 34215.11 Edge Security and RoT (Root of Trust) 34215.12 DICE – Device Identifier Composition Engine 34315.13 Boot Integrity 34315.14 Data Sanitization 34515.15 Total Memory Encryption 34615.16 Secure Device Onboarding 34715.17 Attestation 35015.18 Defense in Depth 35215.19 Zero Trust Architecture (ZTA) 35415.20 Security Hardened Edge Compute Architectures 35416 Securing the Energy Industry with AI-Powered Cybersecurity Solutions 35616.1 Introduction 35616.2 Energy Industry 35716.3 Present and Future of Energy Industry Supply Chain 35916.4 Cybersecurity 36116.5 Digitizing of the Energy Industry 36416.6 MITRE ATT&CK Framework 36716.7 CVE 36816.8 CWE 37016.9 CAPEC 37016.10 CPE 37016.11 Cybersecurity Framework 37016.12 NIST Framework 37116.13 Zero-Day Vulnerability 37216.14 Machine Learning 37316.15 Artificial Intelligence 37416.16 Fusing AI into Cybersecurity 37516.17 Threat Modeling in AI 37916.18 Incident Response 38216.19 Fire Sale Scenario 38316.20 Conclusion 38417 Explainable Artificial Intelligence (XAI) for the Trust and Transparency of the Oil and Gas Systems 38717.1 Introduction 38717.2 The Growing Power of Artificial Intelligence 38817.3 The Challenges and Concerns of Artificial Intelligence 39017.4 About the Need for AI Explainability 39117.5 AI Explainability: The Problem It Solves 39217.6 What is the AI Explainability Challenges? 39317.7 The Importance of Explainable AI 39317.8 The Importance of Model Interpretation 39617.9 Briefing Feature Importance Scoring Methods 40117.10 Local Interpretable Model-agnostic Explanations (LIME) 40217.11 SHAP Explainability Algorithm 40417.12 Conclusion 40718 Blockchain for Enhanced Efficiency, Trust, and Transparency in the Oil and Gas Domain 40918.1 Introduction 40918.2 The Brewing Challenges of the Oil and Gas Industry 41018.3 About the Blockchain Technology 41318.4 Blockchain-Powered Use Cases for the Oil and Gas Industry 41518.5 Blockchain for Improved Trust 41618.6 Sensor-Enabled Invoicing 41718.7 Transportation Tracing 41818.8 Data Storage and Management 41918.9 Digital Oil and Gas: Strengthening and Simplifying Supply Chain 41918.10 Commodity Trading 42118.11 Land Record Management 42118.12 Financial Reconciliation 42218.13 Oil Wells and Equipment Maintenance 42318.14 Waste Management and Recycling 42318.15 Tracking Carbon Footprint 42418.16 Improved Pipeline Inspection 42418.17 Other Miscellaneous Advantages of Blockchain 42518.18 Blockchain Challenges 42518.19 Conclusion 42619 AI-Inspired Digital Twins for the Oil and Gas Domain 42819.1 How to Ensure Certainty Using DT for AI 43219.2 Tools Needed to Develop Digital Twins 43419.3 Digital Twin Implementation Approach at a High Level 43419.4 Digital Twin of Oil and Gas Production 44119.5 Solution Approach 44219.6 Future of Digital Twins 44320 Future Directions of Green Hydrogen and Other Fueling Sources 44720.1 Introduction 44720.2 Green Hydrogen Technologies 44820.3 Current and Future Industrial Applications of Hydrogen 44920.4 The Exploitation of Hydrogen Fuel in a Future System 45020.5 Green Hydrogen: Fuel of the Future 45120.6 Extraction of Hydrogen with Diagrammatic Representation 45320.7 Hydrogen Fuel System Advantages and Disadvantages 45420.8 AI-Based Approach for Emerging Green Hydrogen Technologies for Sustainability 45520.9 Challenges of Hydrogen with AI Technologies 45820.10 The Expected Use and Forecast for Hydrogen Fuel Cells in the Future 45820.11 Conclusion 459Bibliography 460Index 461