Syntactic pattern recognition for seismic oil exploration

Title:

Personal Author:

Huang, Kou-Yuan

Series:

Series in machine perception and artificial intelligence ; 46

Publication Information:

River Edge, N.J. : World Scientific, 2002

ISBN:

9789810246006

Subject Term:

Petroleum -- Prospecting -- Data processing

Pattern recognition systems

Seismic reflection method -- Data processing

Available:*

Library	Item Barcode	Call Number	Material Type	Item Category 1	Status
Searching... PSZ JB	30000010018118	TN271.P4 H88 2002	Open Access Book	Book	Searching... Unknown
Searching... SPACE Kerteh Library	30000010022787	TN271.P4 H88 2002	Open Access Book	Book	Searching... Unknown
Searching... SPACE Kerteh Library	30000010022785	TN271.P4 H88 2002	Open Access Book	Book	Searching... Unknown
Searching... SPACE KL Main Library	30000010022786	TN271.P4 H88 2002	Open Access Book	Book	Searching... Unknown
Searching... SPACE KL Main Library	30000010022788	TN271.P4 H88 2002	Open Access Book	Book	Searching... Unknown

The use of pattern recognition has become more and more important in seismic oil exploration. Interpreting a large volume of seismic data is a challenging problem. Seismic reflection data in the one-shot seismogram and stacked seismogram may contain some structural information from the response of the subsurface. Syntactic/structural pattern recognition techniques can recognize the structural seismic patterns and improve seismic interpretations.The syntactic analysis methods include: (1) the error-correcting finite-state parsing, (2) the modified error-correcting Earley's parsing, (3) the parsing using the match primitive measure, (4) the Levenshtein distance computation, (5) the likelihood ratio test, (6) the error-correcting tree automata, and (7) a hierarchical system.Syntactic seismic pattern recognition can be one of the milestones of a geophysical intelligent interpretation system. The syntactic methods in this book can be applied to other areas, such as the medical diagnosis system. The book will benefit geophysicists, computer scientists and electrical engineers.

Author's Biography	p. vii
Preface	p. ix
1 Introduction to Syntactic Pattern Recognition	p. 1
1.1. Summary	p. 1
1.2. Introduction	p. 1
1.3. Organization of This Book	p. 3
2 Introduction to Formal Languages and Automata	p. 7
2.1. Summary	p. 7
2.2. Languages and Grammars	p. 7
Type 0 (unrestricted) grammar	p. 9
Type 1 (context-sensitive) grammar	p. 9
Type 2 (context-free) grammar	p. 9
Type 3 (finite-state or regular) grammar	p. 9
2.3. Finite-State Automaton	p. 10
2.4. Earley's Parsing	p. 14
2.5. Finite-State Grammatical Inference	p. 16
2.5.1. Inference of Canonical Finite-State Grammar	p. 16
2.5.2. Inference of Finite-State Grammar Based on K-Tails	p. 17
2.6. String Distance Computation	p. 18
3 Error-Correcting Finite-State Automaton for Recognition of Ricker Wavelets	p. 21
3.1. Summary	p. 21
3.2. Introduction	p. 21
3.3. Syntactic Pattern Recognition	p. 22
3.3.1. Training and Testing Ricker Wavelets	p. 22
3.3.2. Location of Waveforms and Pattern Representation	p. 25
3.4. Expanded Grammars	p. 25
3.4.1. General Expanded Finite-State Grammar	p. 25
3.4.2. Restricted Expanded Finite-State Grammar	p. 28
3.5. Minimum-Distance Error-Correcting Finite-State Parsing	p. 31
3.6. Classification of Ricker Wavelets	p. 32
3.7. Discussion and Conclusions	p. 37
4 Attributed Grammar and Error-Correcting Earley's Parsing	p. 39
4.1. Summary	p. 39
4.2. Introduction	p. 39
4.3. Attributed Primitives and String	p. 41
4.4. Definition of Error Transformations for Attributed Strings	p. 41
4.5. Inference of Attributed Grammar	p. 42
4.6. Minimum-Distance Error-Correcting Earley's Parsing for Attributed String	p. 45
4.7. Experiment	p. 47
5 Attributed Grammar and Match Primitive Measure (MPM) for Recognition of Seismic Wavelets	p. 51
5.1. Summary	p. 51
5.2. Similarity Measure of Attributed String Matching	p. 51
5.3. Inference of Attributed Grammar	p. 55
5.4. Top-Down Parsing Using Mpm	p. 56
5.5. Experiments of Seismic Pattern Recognition	p. 58
5.5.1. Recognition of Seismic Ricker Wavelets	p. 58
5.5.2. Recognition of Wavelets in Real Seismogram	p. 60
5.6. Conclusions	p. 64
6 String Distance and Likelihood Ratio test for Detection of Candidate Bright Spot	p. 65
6.1. Summary	p. 65
6.2. Introduction	p. 65
6.3. Optimal Quantization Encoding	p. 66
6.4. Likelihood Ratio Test (LRT)	p. 67
6.5. Levenshtein Distance and Error Probability	p. 68
6.6. Experiment at Mississippi Canyon	p. 69
6.6.1. Likelihood Ratio Test (LRT)	p. 72
6.6.2. Threshold for Global Detection	p. 72
6.6.3. Threshold for the Detection of Candidate Bright Spot	p. 72
6.7. Experiment at High Island	p. 73
7 Tree Grammar and Automaton for Seismic Pattern Recognition	p. 75
7.1. Summary	p. 75
7.2. Introduction	p. 75
7.3. Tree Grammar and Language	p. 77
7.4. Tree Automaton	p. 78
7.5. Tree Representations of Patterns	p. 84
7.6. Inference of Expansive Tree Grammar	p. 85
7.7. Weighted Minimum-Distance Specta	p. 86
7.8. Modified Maximum-Likelihood Specta	p. 92
7.9. Minimum Distance Gecta	p. 94
7.10. Experiments on Input Testing Seismograms	p. 95
7.11. Discussion and Conclusions	p. 102
8 A Hierarchical Recognition System of Seismic Patterns and Future Study	p. 103
8.1. Summary	p. 103
8.2. Introduction	p. 103
8.3. Syntactic Pattern Recognition	p. 107
8.3.1. Linking Processing and Segmentation	p. 107
8.3.2. Primitive Recognition	p. 107
8.3.3. Training Patterns	p. 108
8.3.4. Grammatical Inference	p. 109
8.3.5. Finite-state Error Correcting Parsing	p. 109
8.4. Common-source Simulated Seismogram Results	p. 110
8.5. Stacked Simulated Seismogram Results	p. 117
8.6. Conclusions	p. 121
8.7. Future Study	p. 121
References	p. 123
Index	p. 131

Available:*

On Order

Summary

Summary

Table of Contents