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
Author(s): Poulton M.M.
Year: 2001
Language: English
Pages: 351
Front Cover......Page 1
Computational Neural Networks for Geophysical Data Processing......Page 4
Copyright Page......Page 5
Table of Contents......Page 6
Preface......Page 12
Contributing Authors......Page 14
Part I: Introduction to Computational Neural Networks......Page 16
1. Introduction......Page 18
2. Historical Development......Page 20
2. Biological Neural Networks......Page 34
3. Evolution of the Computational Neural Network......Page 38
1. Vocabulary......Page 42
2. Back-Propagation......Page 43
3. Parameters......Page 50
4. Time-Varying Data......Page 65
1. Introduction......Page 70
2. Re-Scaling......Page 71
4. Size Reduction......Page 73
5. Data Coding......Page 75
6. Order of Data......Page 76
1. Improving on Back-Propagation......Page 82
2. Hybrid Networks......Page 89
3. Alternative Architectures......Page 93
2. Commercial Software Packages......Page 104
4. News Groups......Page 112
Part II: Seismic Data Processing......Page 114
2. Waveform Recognition......Page 116
3. Picking Arrival Times......Page 118
5. Velocity Analysis......Page 125
6. Elimination of Multiples......Page 127
7. Deconvolution......Page 128
8. Inversion......Page 131
2. Horizon Tracking and Facies Maps......Page 134
4. Predicting Log Properties......Page 136
5. Rock/Reservoir Characterization......Page 139
1. Introduction......Page 144
2. Training Set Design and Network Architecture......Page 149
3. Testing......Page 154
4. Analysis of Training and Testing......Page 156
5. Validation......Page 165
6. Conclusions......Page 168
2. Self-Organizing Map Network......Page 170
3. Horizon Tracking......Page 172
4. Classification of the Seismic Traces......Page 176
5. Conclusions......Page 184
1. Introduction......Page 186
2. Relationship Between Seismic and Petrophysical Parameters......Page 187
3. Parameters That Affect Permeability: Porosity, Grain Size, Clay Content......Page 191
4. Neural Network Modeling of Permeability Data......Page 193
5. Summary and Conclusions......Page 199
1. Introduction......Page 202
2. Generalized Geophysical Inversion......Page 203
3. Caianiello Neural Network Method......Page 209
4. Inversion With Simplified Physical Models......Page 214
5. Inversion With Empirically-Derived Models......Page 221
6. Example......Page 223
7. Discussions and Conclusions......Page 225
Part III: Non-Seismic Applications......Page 232
1. Introduction......Page 234
2. Well Logging......Page 235
3. Gravity and Magnetics......Page 239
4. Electromagnetics......Page 240
5. Resistivity......Page 244
6. Multi-Sensor Data......Page 245
1. Introduction......Page 250
2. Airborne Electromagnetic Method- Theoretical Background......Page 251
3. Feedforward Computational Neural Networks (CNN)......Page 255
4. Concept......Page 258
5. CNNs to Calculate Homogeneous Halfspaces......Page 259
6. CNN for Detecting 2D Structures......Page 262
7. Testing......Page 265
8. Conclusion......Page 267
1. Introduction......Page 272
2. Layer Boundary Picking......Page 275
3. Modular Neural Network......Page 277
4. Training With Multiple Logging Tools......Page 280
5. Analysis of Results......Page 283
6. Conclusions......Page 298
1. Introduction......Page 302
2. Function Approximation......Page 304
3. Neural Network Training......Page 309
4. Case History......Page 312
5. Conclusion......Page 318
1. Introduction......Page 322
3. Inverse Modeling With Neural Networks......Page 325
4. Testing Results......Page 326
5. Uncertainty Evaluation......Page 335
7. Case Study......Page 336
8. Conclusions......Page 339
Author Index......Page 342
Index......Page 346
