Details

Meta-attributes and Artificial Networking


Meta-attributes and Artificial Networking

A New Tool for Seismic Interpretation
Special Publications, Band 76 1. Aufl.

von: Kalachand Sain, Priyadarshi Chinmoy Kumar

126,99 €

Verlag: Wiley
Format: PDF
Veröffentl.: 22.06.2022
ISBN/EAN: 9781119481911
Sprache: englisch
Anzahl Seiten: 288

DRM-geschütztes eBook, Sie benötigen z.B. Adobe Digital Editions und eine Adobe ID zum Lesen.

Beschreibungen

<p><b>Applying machine learning to the interpretation of seismic data</b></p> <p>Seismic data gathered on the surface can be used to generate numerous seismic attributes that enable better understanding of subsurface geological structures and stratigraphic features. With an ever-increasing volume of seismic data available, machine learning augments faster data processing and interpretation of complex subsurface geology.</p> <p><i>Meta-Attributes and Artificial Networking: A New Tool for Seismic Interpretation</i> explores how artificial neural networks can be used for the automatic interpretation of 2D and 3D seismic data.</p> <p><b>Volume highlights include:</b></p> <ul> <li>Historic evolution of seismic attributes</li> <li>Overview of meta-attributes and how to design them</li> <li>Workflows for the computation of meta-attributes from seismic data</li> <li>Case studies demonstrating the application of meta-attributes</li> <li>Sets of exercises with solutions provided</li> <li>Sample data sets available for hands-on exercises</li> </ul> <p><i>The American Geophysical Union promotes discovery in Earth and space science for the benefit of humanity. Its publications disseminate scientific knowledge and provide resources for researchers, students, and professionals.</i></p>
<p>Preface</p> <p>About the Authors</p> <p>Abbreviations</p> <p>List of Symbols and Operators</p> <p><b>PART I: SEISMIC ATTRIBUTES</b></p> <p><b>1. An Overview of Seismic Attributes</b></p> <p>1.1 Introduction</p> <p>1.2 Historical evolution of seismic attributes</p> <p>1.3 Characteristics of Seismic Attributes</p> <p>1.4 A glance at seismic characteristics</p> <p>1.4.1 Amplitude</p> <p>1.4.2 Phase</p> <p>1.4.3 Frequency</p> <p>1.4.4 Bandwidth</p> <p>1.4.5 Amplitude Change</p> <p>1.4.6 Slope Dip and Azimuth</p> <p>1.4.7 Curvature</p> <p>1.4.8 Seismic Discontinuity</p> <p>1.5 Summary</p> <p>&nbsp;References</p> <p><b>2. Complex Trace, Structural and Stratigraphic Attributes</b></p> <p>2.1 Introduction</p> <p>2.2 Complex Trace Attributes: Mathematical Formulations and Derivations</p> <p>2.3 Other Derived Complex Trace Attributes</p> <p>2.3.1 Instantaneous Frequency</p> <p>2.3.2 Sweetness</p> <p>2.3.3 Relative Amplitude Change and Instantaneous Bandwidth</p> <p>2.3.4 RMS Frequency</p> <p>2.3.5 Q-factor</p> <p>2.4 Structural and Stratigraphic Attributes</p> <p>2.4.1 Dip and Azimuth Attributes</p> <p>Slope and Dip Exaggeration</p> <p>Dip-steering</p> <p>2.4.2 Coherence Attribute</p> <p>2.4.3 Similarity Attribute</p> <p>2.4.4 Curvature Attribute</p> <p>2.4.5 Advanced structural attributes</p> <p>Ridge Enhancement Filter (REF) attribute</p> <p>Thin Fault Likelihood (TFL) attribute</p> <p>Pseudo Relief attribute</p> <p>2.4.6 Amplitude Variance</p> <p>2.4.7 Reflection Spacing</p> <p>2.4.8 Reflection Divergence</p> <p>2.4.9 Reflection Parallelism</p> <p>2.4.10 Spectral Decomposition</p> <p>2.4.11 Velocity, Reflectivity and Attenuation attributes</p> <p>2.5 A glance on interpretation pitfalls</p> <p>2.6 Summary</p> <p>References</p> <p><b>3. Be an Interpreter: Brainstorming Session </b></p> <p>3.1 Task 1</p> <p>3.2 Task 2</p> <p>3.3 Task 3</p> <p>3.4 Task 4</p> <p>3.5 Task 5</p> <p>3.6 Task 6</p> <p>3.7 Task 7</p> <p>3.8 Task 8</p> <p>3.9 Task 9</p> <p>3.10 Task 10</p> <p><b>PART II: META-ATTRIBUTES</b></p> <p><b>4. An Overview of Meta-attributes</b></p> <p>4.1 Introduction</p> <p>4.2 Meta-attributes</p> <p>4.3 Types of Meta-attributes</p> <p>4.3.1 Hydrocarbon Probability meta-attribute</p> <p>4.3.2 Chimney Cube meta-attribute</p> <p>4.3.3 Fault Cube meta-attribute</p> <p>4.3.4 Intrusion Cube meta-attribute</p> <p>4.3.5 Sill Cube meta-attribute</p> <p>4.3.6 Mass Transport Deposit Cube meta-attribute</p> <p>4.3.7 Lithology meta-attribute</p> <p>4.4 Summary</p> <p>References</p> <p><b>5. An Overview of Artificial Neural Networks</b></p> <p>5.1 Introduction</p> <p>5.2 Historical Evolution</p> <p>5.3 Biological Neuron Vs Mathematical Neuron</p> <p>5.3.1 Biological Neuron</p> <p>5.3.2 Mathematical Neuron</p> <p>5.4 Activation or Transfer Function</p> <p>5.5 Types of Learning</p> <p>5.6 Multi-layer Perceptron (MLP) and the Backpropagation Algorithm</p> <p>5.7 Different Types of ANNs</p> <p>5.7.1 Radial Basis Function (RBF) Network</p> <p>5.7.2 Probabilistic Neural Network (PNN)</p> <p>5.7.3 Generalized Regression Neural Network (GRNN)</p> <p>5.7.4 Modular Neural Network (MNN)</p> <p>5.7.5 Self Organizing Maps (SOM)</p> <p>5.8 Summary</p> <p>References</p> <p><b>6. How to Design Meta-attributes</b></p> <p>6.1 Introduction</p> <p>6.2 Meta-attribute design</p> <p>6.2.1 Seismic Data conditioning</p> <p>Mean Filter (or Running-Average filter)</p> <p>Median Filter</p> <p>Alpha-Trimmed Mean Filter</p> <p>6.2.2 Selection and Extraction of Seismic Attributes</p> <p>6.2.3 Example Location</p> <p>6.2.4 NN operation</p> <p>Evaluation of intelligent neural model</p> <p>6.2.5 Validation</p> <p>6.3 RGB Blending and Geo-body Extraction</p> <p>6.4 Summary</p> <p>References</p> <p><b>PART III: CASE STUDIES OF META-ATTRIBUTES</b></p> <p><b>7. Chimney interpretation using meta-attribute</b></p> <p>7.1 Gas Chimneys: a clue for hydrocarbon exploration</p> <p>7.2 Research Methodology</p> <p>7.3 Chimney Validation</p> <p>7.3.1 Geological Validation</p> <p>7.3.2 Petrophysical Validation</p> <p>7.3.3 Soft sediment deformation anomalies</p> <p>7.4 Interpretation using Chimney Cube</p> <p>7.5 Summary</p> <p>&nbsp;References</p> <p><b>8. Fault Interpretation Using Meta-attribute</b></p> <p>8.1 Fault meta-attribute: a motivation</p> <p>8.2 Research Methodology</p> <p>8.3 Results and Interpretation</p> <p>8.4 Efficiency of the optimized TFC</p> <p>8.5 Summary</p> <p>References</p> <p><b>9. Fault and Fluid Migration Interpretation Using Meta-attribute</b></p> <p>9.1 Introduction</p> <p>9.2 Geophysical Data</p> <p>9.3 Results and Interpretation</p> <p>9.3.1 Thinned Fault Cube (TFC) and Fluid Cube (FlC)</p> <p>9.3.2 Neural Design for the TFC and FlC</p> <p>9.3.3 Interpretation using TFC and FlC</p> <p>9.4 Summary</p> <p>References</p> <p><b>10. Magmatic Sill Interpretation Using Meta-attribute (Part 1: Taranaki Basin example)</b></p> <p>10.1 Magmatic Sills: Interpretation techniques</p> <p>10.2 Research Methods</p> <p>10.2.1 Structural conditioning</p> <p>10.2.2 Selection of attributes</p> <p>10.2.3 Example Locations</p> <p>10.2.4 Neural Network</p> <p>10.2.5 Validation</p> <p>10.3 Results and Interpretation</p> <p>10.4 Discussion</p> <p>10.4.1 Sill cube an efficient interpretation tool for magmatic sills</p> <p>10.4.2 Limitations of the Sill Cube automated approach</p> <p>10.5 Conclusions</p> <p>References</p> <p><b>11. Magmatic Sill Interpretation Using Meta-attribute (Part 2: V&oslash;ring Basin example)</b></p> <p>11.1 Introduction: The V&oslash;ring Basin case</p> <p>11.2 Description of the Data</p> <p>11.3 Interpretation based on SC meta-attribute computation</p> <p>11.4 Summary</p> <p>References</p> <p><b>12. Magmatic Sill and Fluid Plumbing Interpretation Using Meta-attribute (Canterbury Basin example)</b></p> <p>12.1 Introduction: The Canterbury Basin case</p> <p>12.2 Description of the Data</p> <p>12.3 Results and Interpretation</p> <p>12.3.1 Data Enhancement, Attribute Analysis and Neural Operation</p> <p>12.3.2 Interpretation through Sill Cube (SC) and Fluid Cube (FlC) meta-attributes</p> <p>12.3.3 Limitation of the automated approach</p> <p>12.4 Summary</p> <p>References</p> <p><b>13. Volcanic System Interpretation Using Meta-attribute </b></p> <p>13.1 Introduction</p> <p>13.2 Research Workflow</p> <p>13.3 Results and Interpretation</p> <p>13.3.1 Seismic Data Enhancement</p> <p>13.3.2 Neural Networks: Analysis and Optimization</p> <p>13.3.3 Geologic interpretation using IC meta-attribute</p> <p>13.3.4 Validation of the IC meta-attribute</p> <p>13.4 Summary</p> <p>References</p> <p><b>14. Interpretation of Mass Transport Deposits Using Meta-attribute </b></p> <p>14.1 Introduction</p> <p>14.2 Data and Research Workflow</p> <p>14.3 Results and Interpretation</p> <p>14.4 Summary</p> <p>References</p> <p><b>Appendix A</b></p> <p>A.1 Mathematical formulation of some common series and transformation</p> <p>A.1.1 Fourier Series</p> <p>A.1.2 Fourier and Inverse Fourier Transforms</p> <p>A.1.3 Hilbert Transform</p> <p>A.1.4 Convolution</p> <p>A.2 Dip-Steering</p> <p><b>Appendix B</b></p> <p>B.1 Answers to seismic cross-section interpretation (Tasks 1-6)</p> <p>B.2 Answers to numerical tasks (Tasks 7-10)</p> <p>Glossary</p>
<p><b>Kalachand Sain,</b> Wadia Institute of Himalayan Geology, India</p> <p><b>Priyadarshi Chinmoy Kumar, </b>Wadia Institute of Himalayan Geology, India
<p><b>Meta-Attributes and Artificial Networking</b><br> A New Tool for Seismic Interpretation</p> <p>Seismic data gathered on the surface can be used to generate numerous seismic attributes that enable better understanding of subsurface geological structures and stratigraphic features. With an ever-increasing volume of seismic data available, machine learning augments faster data processing and interpretation of complex subsurface geology. <p><i>Meta-Attributes and Artificial Networking: A New Tool for Seismic Interpretation</i> explores how artificial neural networks can be used for the automatic interpretation of 2D and 3D seismic data. <p><b>Volume highlights include:</b> <ul><li>Historic evolution of seismic attributes</li> <li>Overview of meta-attributes and how to design them</li> <li>Workflows for the computation of meta-attributes from seismic data</li> <li>Case studies demonstrating the application of meta-attributes</li> <li>Sets of exercises with solutions provided</li> <li>Sample data sets available for hands-on exercises</li></ul> <p><i>The American Geophysical Union promotes discovery in Earth and space science for the benefit of humanity. Its publications disseminate scientific knowledge and provide resources for researchers, students, and professionals.</i>

Diese Produkte könnten Sie auch interessieren:

Landslide Hazard and Risk
Landslide Hazard and Risk
von: Thomas Glade, Malcolm G. Anderson, Michael J. Crozier
PDF ebook
225,99 €
Field Techniques in Glaciology and Glacial Geomorphology
Field Techniques in Glaciology and Glacial Geomorphology
von: Bryn Hubbard, Neil F. Glasser
PDF ebook
51,99 €
The Field Description of Igneous Rocks
The Field Description of Igneous Rocks
von: Dougal Jerram, Nick Petford
PDF ebook
30,99 €