Elsevier S & T

Computational Neural Networks for Geophysical Data Processing

Poulton, M.M.

In stock
No reviews
63.000 KD inc. VAT
License
Table of contents
  • Table of Contentsv
  • Prefacexi
  • Contributing Authorsxiii
  • Part I: Introduction to Computational Neural Networks1
  • Chapter 1. A Brief History3
  • 1. Introduction3
  • 2. Historical Development5
  • Chapter 2. Biological Versus Computational Neural Networks19
  • 1. Computational Neural Networks19
  • 2. Biological Neural Networks19
  • 3. Evolution of the Computational Neural Network23
  • Chapter 3. Multi-Layer Perceptrons and Back-Propagation Learning27
  • 1. Vocabulary27
  • 2. Back-Propagation28
  • 3. Parameters35
  • 4. Time-Varying Data50
  • Chapter 4. Design of Training and Testing Sets55
  • 1. Introduction55
  • 2. Re-Scaling56
  • 3. Data Distribution58
  • 4. Size Reduction58
  • 5. Data Coding60
  • 6. Order of Data61
  • Chapter 5. Alternative Architectures and Learning Rules67
  • 1. Improving on Back-Propagation67
  • 2. Hybrid Networks74
  • 3. Alternative Architectures78
  • Chapter 6. Software and Other Resources89
  • 1. Introduction89
  • 2. Commercial Software Packages89
  • 3. Open Source Software97
  • 4. News Groups97
  • Part II: Seismic Data Processing99
  • Chapter 7. Seismic Interpretation and Processing Applications101
  • 1. Introduction101
  • 2. Waveform Recognition101
  • 3. Picking Arrival Times103
  • 4. Trace Editing110
  • 5. Velocity Analysis110
  • 6. Elimination of Multiples112
  • 7. Deconvolution113
  • 8. Inversion116
  • Chapter 8. Rock Mass and Reservoir Characterization119
  • 1. Introduction119
  • 2. Horizon Tracking and Facies Maps119
  • 3. Time-Lapse Interpretation121
  • 4. Predicting Log Properties121
  • 5. Rock/Reservoir Characterization124
  • Chapter 9. Identifying Seismic Crew Noise129
  • 1. Introduction129
  • 2. Training Set Design and Network Architecture134
  • 3. Testing139
  • 4. Analysis of Training and Testing141
  • 5. Validation150
  • 6. Conclusions153
  • Chapter 10. Self-Organizing Map (SOM) Network for Tracking Horizons and Classifying Seismic Traces155
  • 1. Introduction155
  • 2. Self-Organizing Map Network155
  • 3. Horizon Tracking157
  • 4. Classification of the Seismic Traces161
  • 5. Conclusions169
  • Chapter 11. Permeability Estimation with an RBF Network and Levenberg-Marquardt Learning171
  • 1. Introduction171
  • 2. Relationship Between Seismic and Petrophysical Parameters172
  • 3. Parameters That Affect Permeability: Porosity, Grain Size, Clay Content176
  • 4. Neural Network Modeling of Permeability Data178
  • 5. Summary and Conclusions184
  • Chapter 12. Caianiello Neural Network Method for Geophysical Inverse Problems187
  • 1. Introduction187
  • 2. Generalized Geophysical Inversion188
  • 3. Caianiello Neural Network Method194
  • 4. Inversion With Simplified Physical Models199
  • 5. Inversion With Empirically-Derived Models206
  • 6. Example208
  • 7. Discussions and Conclusions210
  • Part III: Non-Seismic Applications217
  • Chapter 13. Non-Seismic Applications219
  • 1. Introduction219
  • 2. Well Logging220
  • 3. Gravity and Magnetics224
  • 4. Electromagnetics225
  • 5. Resistivity229
  • 6. Multi-Sensor Data230
  • Chapter 14. Detection of AEM Anomalies Corresponding to Dike Structures235
  • 1. Introduction235
  • 2. Airborne Electromagnetic Method- Theoretical Background236
  • 3. Feedforward Computational Neural Networks (CNN)240
  • 4. Concept243
  • 5. CNNs to Calculate Homogeneous Halfspaces244
  • 6. CNN for Detecting 2D Structures247
  • 7. Testing250
  • 8. Conclusion252
  • Chapter 15. Locating Layer Boundaries with Unfocused Resistivity Tools257
  • 1. Introduction257
  • 2. Layer Boundary Picking260
  • 3. Modular Neural Network262
  • 4. Training With Multiple Logging Tools265
  • 5. Analysis of Results268
  • 6. Conclusions283
  • Chapter 16. A Neural Network Interpretation System for Near-Surface Geophysics Electromagnetic Ellip287
  • 1. Introduction287
  • 2. Function Approximation289
  • 3. Neural Network Training294
  • 4. Case History297
  • 5. Conclusion303
  • Chapter 17. Extracting IP Parameters From TEM Data307
  • 1. Introduction307
  • 2. Forward Modeling310
  • 3. Inverse Modeling With Neural Networks310
  • 4. Testing Results311
  • 5. Uncertainty Evaluation320
  • 6. Sensitivity Evaluation321
  • 7. Case Study321
  • 8. Conclusions324
  • Author Index327
  • Index331
Book details
  • Vendor Elsevier S & T
  • SKU 9780080439860
  • ISBN-13 9780080529653
  • Author Poulton, M.M.
  • Category Technology & Engineering
  • Subject Mining

Do you have questions about this book?

Ask an expert!

Description eBook delivery & access Reviews
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.