Computational Neural Networks for Geophysical Data Processing (eBook)

M.M. Poulton (Herausgeber)

eBook Download: PDF

2001 | 1. Auflage
352 Seiten
Elsevier Science (Verlag)
978-0-08-052965-3 (ISBN)

Infos

This book was primarily written for an audience that has heard about neural networks or has had some experience with the algorithms, but would like to gain a deeper understanding of the fundamental material. For those that already have a solid grasp of how to create a neural network application, this work can provide a wide range of examples of nuances in network design, data set design, testing strategy, and error analysis.

Computational, rather than artificial, modifiers are used for neural networks in this book to make a distinction between networks that are implemented in hardware and those that are implemented in software. The term artificial neural network covers any implementation that is inorganic and is the most general term. Computational neural networks are only implemented in software but represent the vast majority of applications.

While this book cannot provide a blue print for every conceivable geophysics application, it does outline a basic approach that has been used successfully.

Inhalt

Cover 1
Table of Contents 6
Preface 12
Contributing Authors 14
Part I: Introduction to Computational Neural Networks 16
Chapter 1. A Brief History 18
1. Introduction 18
2. Historical Development 20
Chapter 2. Biological Versus Computational Neural Networks 34
1. Computational Neural Networks 34
2. Biological Neural Networks 34
3. Evolution of the Computational Neural Network 38
Chapter 3. Multi-Layer Perceptrons and Back-Propagation Learning 42
1. Vocabulary 42
2. Back-Propagation 43
3. Parameters 50
4. Time-Varying Data 65
Chapter 4. Design of Training and Testing Sets 70
1. Introduction 70
2. Re-Scaling 71
3. Data Distribution 73
4. Size Reduction 73
5. Data Coding 75
6. Order of Data 76
Chapter 5. Alternative Architectures and Learning Rules 82
1. Improving on Back-Propagation 82
2. Hybrid Networks 89
3. Alternative Architectures 93
Chapter 6. Software and Other Resources 104
1. Introduction 104
2. Commercial Software Packages 104
3. Open Source Software 112
4. News Groups 112
Part II: Seismic Data Processing 114
Chapter 7. Seismic Interpretation and Processing Applications 116
1. Introduction 116
2. Waveform Recognition 116
3. Picking Arrival Times 118
4. Trace Editing 125
5. Velocity Analysis 125
6. Elimination of Multiples 127
7. Deconvolution 128
8. Inversion 131
Chapter 8. Rock Mass and Reservoir Characterization 134
1. Introduction 134
2. Horizon Tracking and Facies Maps 134
3. Time-Lapse Interpretation 136
4. Predicting Log Properties 136
5. Rock/Reservoir Characterization 139
Chapter 9. Identifying Seismic Crew Noise 144
1. Introduction 144
2. Training Set Design and Network Architecture 149
3. Testing 154
4. Analysis of Training and Testing 156
5. Validation 165
6. Conclusions 168
Chapter 10. Self-Organizing Map (SOM) Network for Tracking Horizons and Classifying Seismic Traces 170
1. Introduction 170
2. Self-Organizing Map Network 170
3. Horizon Tracking 172
4. Classification of the Seismic Traces 176
5. Conclusions 184
Chapter 11. Permeability Estimation with an RBF Network and Levenberg-Marquardt Learning 186
1. Introduction 186
2. Relationship Between Seismic and Petrophysical Parameters 187
3. Parameters That Affect Permeability: Porosity, Grain Size, Clay Content 191
4. Neural Network Modeling of Permeability Data 193
5. Summary and Conclusions 199
Chapter 12. Caianiello Neural Network Method for Geophysical Inverse Problems 202
1. Introduction 202
2. Generalized Geophysical Inversion 203
3. Caianiello Neural Network Method 209
4. Inversion With Simplified Physical Models 214
5. Inversion With Empirically-Derived Models 221
6. Example 223
7. Discussions and Conclusions 225
Part III: Non-Seismic Applications 232
Chapter 13. Non-Seismic Applications 234
1. Introduction 234
2. Well Logging 235
3. Gravity and Magnetics 239
4. Electromagnetics 240
5. Resistivity 244
6. Multi-Sensor Data 245
Chapter 14. Detection of AEM Anomalies Corresponding to Dike Structures 250
1. Introduction 250
2. Airborne Electromagnetic Method- Theoretical Background 251
3. Feedforward Computational Neural Networks (CNN) 255
4. Concept 258
5. CNNs to Calculate Homogeneous Halfspaces 259
6. CNN for Detecting 2D Structures 262
7. Testing 265
8. Conclusion 267
Chapter 15. Locating Layer Boundaries with Unfocused Resistivity Tools 272
1. Introduction 272
2. Layer Boundary Picking 275
3. Modular Neural Network 277
4. Training With Multiple Logging Tools 280
5. Analysis of Results 283
6. Conclusions 298
Chapter 16. A Neural Network Interpretation System for Near-Surface Geophysics Electromagnetic Ellipticity Soundings 302
1. Introduction 302
2. Function Approximation 304
3. Neural Network Training 309
4. Case History 312
5. Conclusion 318
Chapter 17. Extracting IP Parameters From TEM Data 322
1. Introduction 322
2. Forward Modeling 325
3. Inverse Modeling With Neural Networks 325
4. Testing Results 326
5. Uncertainty Evaluation 335
6. Sensitivity Evaluation 336
7. Case Study 336
8. Conclusions 339
Author Index 342
Index 346

Produkt-Details

• Erscheint lt. Verlag: 13.6.2001
• Sprache: englisch
• Themenwelt: Sachbuch/Ratgeber
• Themenwelt: Informatik ► Theorie / Studium ► Künstliche Intelligenz / Robotik
• Themenwelt: Naturwissenschaften ► Geowissenschaften ► Geologie
• Themenwelt: Naturwissenschaften ► Geowissenschaften ► Geophysik
• Themenwelt: Naturwissenschaften ► Physik / Astronomie
• Themenwelt: Technik ► Bergbau
• ISBN-10: 0-08-052965-8 / 0080529658
• ISBN-13: 978-0-08-052965-3 / 9780080529653