Unconventional Hydrocarbon Resources: Prediction and Modeling Using Artificial Intelligence Approaches

by Ouadfeul, Sid-Ali

• ISBN13: 9781119389361
• ISBN10: 1119389364
• Edition: 1st
• Format: Hardcover
• Copyright: 2023-08-15
• Publisher: Wiley

Summary

Unconventional Hydrocarbon Resources

Enables readers to save time and effort in exploring and exploiting shale gas and other unconventional fossil fuels by making use of advanced predictive tools

Unconventional Hydrocarbon Resources highlights novel concepts and techniques for the geophysical exploration of shale and other tight hydrocarbon reservoirs, focusing on artificial intelligence approaches for modeling and predicting key reservoir properties such as pore pressure, water saturation, and wellbore stability. Numerous application examples and case studies present real-life data from different unconventional hydrocarbon fields such as the Barnett Shale (USA), the Williston Basin (USA), and the Berkine Basin (Algeria).

Unconventional Hydrocarbon Resources explores a wide range of reservoir properties, including modeling of the geomechanics of shale gas reservoirs, petrophysics analysis of shale and tight sand gas reservoirs, and prediction of hydraulic fracturing effects, fluid flow, and permeability.

Sample topics covered in Unconventional Hydrocarbon Resources include:

• Calculation of petrophysical parameter curves for non-conventional reservoir modeling and characterization
• Comparison of the Levenberg-Marquardt and conjugate gradient learning methods for total organic carbon prediction in the Barnett shale gas reservoir
• Use of pore effective compressibility for quantitative evaluation of low resistive pays and identifying sweet spots in shale reservoirs
• Pre-drill pore pressure estimation in shale gas reservoirs using seismic genetic inversion
• Using well-log data to classify lithofacies of a shale gas reservoir

Unconventional Hydrocarbon Resources is a valuable resource for researchers and professionals working on unconventional hydrocarbon exploration and in geoengineering projects.

Author Biography

Sid-Ali Ouadfeul, Professor, Department of Geophysics, Geology and Reservoir Engineering, Algerian Petroleum Institute-IAP Corporate University, Algeria.

Table of Contents

1. Pre-drill Pore Pressure Estimation in Shale Gas Reservoirs Using Seismic Genetic Inversion

2. An Analysis of the Barnett Shale's Seismic Anisotropy's Role in the Exploration of Shale Gas Reservoirs

3. Wellbore Stability in Shale Gas Reservoirs with a Case Study from the Barnett Shale

4. A comparison of the Levenberg-Marquardt and Conjugate Gradient Learning Methods for Total Organic Carbon Prediction in the Barnett Shale Gas Reservoir

5. Identifying Sweet Spots in Shale Reservoirs

6. Surfactants in Shale Reservoirs

7. Neuro-Fuzzy Algorithm Classification of Ordovician Tight Reservoir Facies in Algeria

8. Automatic Recognition of Lithology Utilizing a New Artificial Neural Network Algorithm

9. A New Artificial Neural Network Based Compensator for the Low Resistivity Phenomena Saturation Computation Based on Logging Curves

10. A Practical Workflow for Improving the Correlation of Sub-seismic Geological Structures and Natural Fractures Using Seismic Attributes

11. Calculation of Petrophysical Parameter Curves for Non-Conventional Reservoir Modeling and Characterization

12. Fuzzy Logic for Predicting Pore Pressure in Shale Gas Reservoirs with a Barnett Shale Application

13. Using Well-Log Data, a Hidden Weight Optimization Method Neural Network Can Classify the Lithofacies of a Shale Gas Reservoir: Barnett Shale Application

14. The Use of Pore Effective Compressibility for Quantitative Evaluation of Low Resistive Pays

15. The Influence of Pore Levels on Reservoir Quality Based on Rock Typing: A Case Study of Quartzite El Hamra, Algeria

16. Integration of Rock Types and Hydraulic Flow Unitsfor Reservoir Characterization. Application to Three Forks Formation, Williston Basin, North Dakota, USA

17. Petrophysical Analysis of Three Forks Formation in Williston Basin, North Dakota, USA

18. Stress-Dependent Permeability, Porosity and Hysteresis. Application to the Three Forks Formation, Williston Basin, North Dakota, USA

19. Water Saturation Prediction Using Machine Learning and Deep Learning. Application to Three Forks Formation in Williston Basin, North Dakota, USA