Muutke küpsiste eelistusi

E-raamat: Data-Driven Analytics for the Geological Storage of CO2

  • Formaat: 302 pages
  • Ilmumisaeg: 20-May-2018
  • Kirjastus: CRC Press
  • Keel: eng
  • ISBN-13: 9781315280806
Teised raamatud teemal:
  • Formaat - PDF+DRM
  • Hind: 76,69 €*
  • * hind on lõplik, st. muud allahindlused enam ei rakendu
  • Lisa ostukorvi
  • Lisa soovinimekirja
  • See e-raamat on mõeldud ainult isiklikuks kasutamiseks. E-raamatuid ei saa tagastada.
Data-Driven Analytics for the Geological Storage of CO2Suurem pilt
  • Formaat: 302 pages
  • Ilmumisaeg: 20-May-2018
  • Kirjastus: CRC Press
  • Keel: eng
  • ISBN-13: 9781315280806
Teised raamatud teemal:

DRM piirangud

  • Kopeerimine (copy/paste):

    ei ole lubatud

  • Printimine:

    ei ole lubatud

  • Kasutamine:

    Digitaalõiguste kaitse (DRM)
    Kirjastus on väljastanud selle e-raamatu krüpteeritud kujul, mis tähendab, et selle lugemiseks peate installeerima spetsiaalse tarkvara. Samuti peate looma endale  Adobe ID Rohkem infot siin. E-raamatut saab lugeda 1 kasutaja ning alla laadida kuni 6'de seadmesse (kõik autoriseeritud sama Adobe ID-ga).

    Vajalik tarkvara
    Mobiilsetes seadmetes (telefon või tahvelarvuti) lugemiseks peate installeerima selle tasuta rakenduse: PocketBook Reader (iOS / Android)

    PC või Mac seadmes lugemiseks peate installima Adobe Digital Editionsi (Seeon tasuta rakendus spetsiaalselt e-raamatute lugemiseks. Seda ei tohi segamini ajada Adober Reader'iga, mis tõenäoliselt on juba teie arvutisse installeeritud )

    Seda e-raamatut ei saa lugeda Amazon Kindle's. 

Data driven analytics is enjoying unprecedented popularity among oil and gas professionals. Many reservoir engineering problems associated with geological storage of CO2 require the development of numerical reservoir simulation models. This book is the first to examine the contribution of Artificial Intelligence and Machine Learning in data driven analytics of fluid flow in porous environments, including saline aquifers and depleted gas and oil reservoirs. Drawing from actual case studies, this book demonstrates how smart proxy models can be developed for complex numerical reservoir simulation models. Smart proxy incorporates pattern recognition capabilities of Artificial Intelligence and Machine Learning to build smart models that learn the intricacies of physical, mechanical and chemical interactions using precise numerical simulations. This ground breaking technology makes it possible and practical to use high fidelity, complex numerical reservoir simulation models in the design, analysis and optimization of carbon storage in geological formations projects.

Nomenclature ix
Acknowledgments xi
Author xiii
Contributors xv
Introduction xvii
1 Storage of CO2 in Geological Formations 1(6)
Shahab D. Mohaghegh
Alireza Haghighat
Shohreh Amini
1.1 Carbon Capture and Storage: CCS
2(3)
1.2 Numerical Reservoir Simulation
5(2)
2 Petroleum Data Analytics 7(26)
Shahab D. Mohaghegh
2.1 Artificial Intelligence
8(1)
2.2 Data Mining
9(2)
2.2.1 Steps Involved in Data Mining
10(1)
2.3 Artificial Neural Networks
11(23)
2.3.1 Structure of a Neural Network
11(2)
2.3.2 Mechanics of Neural Networks Operation
13(4)
2.3.3 Practical Considerations during the Training of a Neural Network
17(24)
2.3.3.1 Selection of Input Parameters
18(2)
2.3.3.2 Partitioning the Dataset
20(2)
2.3.3.3 Structure and Topology
22(3)
2.3.3.4 Training Process
25(6)
2.3.3.5 Convergence
31(2)
3 Smart Proxy Modeling 33(12)
Shahab D. Mohaghegh
3.1 Engineering Application of Data Science
34(2)
3.2 Smart Proxy Modeling in Reservoir Engineering
36(2)
3.3 Mechanics of Smart Proxy Modeling
38(3)
3.4 Initial Examples of Smart Proxy Modeling
41(5)
3.4.1 A Giant Onshore Oilfield in the Middle East
42(3)
4 CO2 Storage in Depleted Gas Reservoirs 45(20)
Shahab D. Mohaghegh
Shohreh Amini
4.1 Numerical Reservoir Simulation: The Base Model
46(4)
4.2 History Matching the Numerical Reservoir Simulation
50(3)
4.3 Developing a Smart Proxy Model
53(6)
4.3.1 Design of the Simulation Runs
54(1)
4.3.2 Spatio-Temporal Database
55(3)
4.3.3 Data-Driven Predictive Models
58(1)
4.4 Results and Discussions
59(6)
5 CO2 Storage in Saline Aquifers 65(54)
Shahab D. Mohaghegh
Alireza Haghighat
5.1 Storage Capacity
66(2)
5.2 Saline Aquifer Distribution
68(2)
5.3 CO2 Trapping Mechanisms
70(1)
5.4 CO2 Storage in Saline Aquifers: Case Study
71(3)
5.4.1 Sleipner (Norway)
71(1)
5.4.2 Snohvit (Norway)
72(1)
5.4.3 The Mississippi Test Site (US)
72(1)
5.4.4 In Salah (Algeria)
73(1)
5.5 CO2 Storage in Citronelle Saline Aquifer: Simulation and Modeling
74(9)
5.5.1 Geology of the Storage Formation
75(1)
5.5.2 Reservoir Simulation Model
76(7)
5.6 Reservoir Characteristics Sensitivity
83(9)
5.6.1 Permeability
83(1)
5.6.2 Permeability Ratio
84(1)
5.6.3 Gas Relative Permeability Curves
85(1)
5.6.4 Maximum Residual Gas Saturation
86(1)
5.6.5 Brine Compressibility
87(2)
5.6.6 Brine Density
89(1)
5.6.7 Boundary Condition
90(2)
5.7 Trapping Mechanisms
92(6)
5.7.1 Structural Trapping
92(1)
5.7.2 Residual or Capillary Gas Trapping Modeling
93(1)
5.7.3 Solubility Trapping Modeling
94(1)
5.7.4 Mineral Trapping Modeling
95(1)
5.7.5 Trapping Mechanisms Sensitivity
96(2)
5.8 Seal Quality Analysis
98(6)
5.9 Post Injection Site Care
104(4)
5.10 The Model's History Match
108(12)
5.10.1 Model Validation
116(3)
6 CO2 Storage in Shale Using Smart Proxy 119(22)
Shahab D. Mohaghegh
Amirmasoud Kalantari-Dahaghi
6.1 Using Numerical Simulation for Shale
120(1)
6.2 Challenges and Solutions of the Numerical Simulation of Shale
120(1)
6.3 Traditional vs. Smart Proxy Models
121(1)
6.4 History Matching Production from the Marcellus Shale
122(2)
6.5 Generating the Spatio-Temporal Database
124(2)
6.6 Results and Discussion
126(13)
6.6.1 Prediction of CH4 Production Profiles
127(4)
6.6.2 Prediction of CO2 Injection Profiles
131(2)
6.6.3 Prediction of CO2 Breakthrough Time and Production Profiles
133(2)
6.6.4 Blind Validation of the Smart Proxy Model
135(4)
6.7 Summary and Conclusions
139(2)
7 CO2-EOR as a Storage Mechanism 141(40)
Shahab D. Mohaghegh
Alireza Shahkarami
Vida Gholami
7.1 The Field and Some Background
143(2)
7.2 The Reservoir
145(1)
7.3 Geologic Description
146(2)
7.4 Performance History
148(1)
7.5 Water Flooding Evaluation
149(1)
7.6 Enhanced Oil Recovery Methods
150(1)
7.6.1 Enriched Miscible Gas Process
150(1)
7.6.2 Carbon Dioxide Process
151(1)
7.7 Development of Numerical Reservoir Simulation
151(3)
7.8 Proxies of the Numerical Simulation Models
154(9)
7.8.1 Surrogate Reservoir Models
161(2)
7.9 Development of the Smart Proxy
163(5)
7.10 Results and Discussion
168(11)
7.11 Concluding Remarks
179(2)
8 Leak Detection in CO2 Storage Sites 181(74)
Shahab D. Mohaghegh
Alireza Haghighat
8.1 CO2 Leakage from Underground Storage
183(7)
8.1.1 CO2 Leakage Conduits
183(6)
8.1.1.1 Well Leakage
183(3)
8.1.1.2 Cap Rock Leakage
186(2)
8.1.1.3 Fault Leakage
188(1)
8.1.2 CO2 Leakage Impacts
189(1)
8.2 Storage Site Monitoring
190(2)
8.2.1 Well Monitoring
190(1)
8.2.1.1 Permanent (Pressure) Down-Hole Gauges (PDGs)
190(1)
8.2.2 Seismic Imaging
190(1)
8.2.3 Gravity Surveys
191(1)
8.2.4 Satellite Imaging
192(1)
8.3 Strategy for Leakage Prevention and Remediation
192(1)
8.4 Smart Well Technology
192(2)
8.4.1 Definition of a Smart Well
193(1)
8.4.2 Application of Smart Wells
193(1)
8.5 Closed-Loop Reservoir Management
194(1)
8.6 CO2 Leakage Detection Using Smart Well Technology: Case Study
195(4)
8.6.1 Leakage Detection: Leakage Test with Analytical Model
195(2)
8.6.2 Leakage Detection with Neural Networks and Reservoir Simulation Model
197(2)
8.7 Intelligent Leakage Detection System
199(18)
8.7.1 ILDS Development Based on the Homogenous Model
200(11)
8.7.1.1 Reservoir Simulation Model
200(1)
8.7.1.2 CO2 Leakage Modeling
201(3)
8.7.1.3 Data Summarization
204(2)
8.7.1.4 Data Partitioning for Neural Network Modeling
206(1)
8.7.1.5 Neural Network Architecture Design and Results
207(4)
8.7.2 ILDS Development Based on the Heterogeneous Model
211(6)
8.7.2.1 CO2 Leakage Modeling
212(1)
8.7.2.2 Neural Network Data Preparation
213(1)
8.7.2.3 Neural Network Architecture and Results
213(4)
8.8 Enhancement and Evaluation of the ILDS
217(38)
8.8.1 RT-ILDS
217(5)
8.8.1.1 Neural Network Data Preparation
218(1)
8.8.1.2 Results and Validations
219(3)
8.8.2 Detection Time
222(2)
8.8.3 Testing RT-ILDS for Multiple Geological Realizations
224(2)
8.8.4 Detection of Leaks at Different Vertical Locations along the Wells
226(4)
8.8.5 Impact of Gauge Accuracy or Pressure Drift on RT-ILDS Results
230(1)
8.8.6 Use of Well Head Pressure at Injection Well
231(1)
8.8.7 RT-ILDS for Variable CO2 Leakage Rates
232(5)
8.8.8 Use of the PDG in the Injection Well
237(2)
8.8.9 Leakage from the Cap-Rock
239(4)
8.8.10 Multi-Well Leakage
243(4)
8.8.11 Data Cleansing
247(4)
8.8.11.1 Determination of Noise Level and Distribution
247(2)
8.8.11.2 De-Noising the Pressure Readings
249(2)
8.8.12 Concluding Remarks
251(4)
Bibliography 255(20)
Index 275
Shahab D. Mohaghegh, a pioneer in the application of Artificial Intelligence and Data Mining in the Exploration and Production industry, is the president and CEO of Intelligent Solutions, Inc. (ISI) and Professor of Petroleum and Natural Gas Engineering at West Virginia University. He holds B.S., MS, and PhD degrees in petroleum and natural gas engineering.

He has authored more than 150 technical papers and carried out more than 50 projects for NOCs and IOCs. He is a SPE Distinguished Lecturer and has been featured in the Distinguished Author Series of SPEs Journal of Petroleum Technology (JPT) four times. He is the founder of Petroleum Data-Driven Analytics, SPEs Technical Section dedicated to data mining. He has been honoured by the U.S. Secretary of Energy for his technical contribution in the aftermath of the Deepwater Horizon (Macondo) incident in the Gulf of Mexico and was a member of the U.S. Secretary of Energys Technical Advisory Committee on Unconventional Resources (20082014). He represents the United States in the International Standard Organization (ISO) on Carbon Capture and Storage.
Lisainfo e-raamatute kohta Lisainfo e-raamatute kohta
Püsilink: https://www.kriso.ee/db/97813152808062e.html
Märksõnad: