Details

Enhance Oil and Gas Exploration with Data-Driven Geophysical and Petrophysical Models


Enhance Oil and Gas Exploration with Data-Driven Geophysical and Petrophysical Models


Wiley and SAS Business Series 1. Aufl.

von: Keith R. Holdaway, Duncan H. B. Irving

73,99 €

Verlag: Wiley
Format: EPUB
Veröffentl.: 04.10.2017
ISBN/EAN: 9781119302582
Sprache: englisch
Anzahl Seiten: 368

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

Beschreibungen

<b>Leverage Big Data analytics methodologies to add value to geophysical and petrophysical exploration data</b> <p><i>Enhance Oil & Gas Exploration with Data-Driven Geophysical and Petrophysical Models</i> demonstrates a new approach to geophysics and petrophysics data analysis using the latest methods drawn from Big Data. Written by two geophysicists with a combined 30 years in the industry, this book shows you how to leverage continually maturing computational intelligence to gain deeper insight from specific exploration data. Case studies illustrate the value propositions of this alternative analytical workflow, and in-depth discussion addresses the many Big Data issues in geophysics and petrophysics. From data collection and context through real-world everyday applications, this book provides an essential resource for anyone involved in oil and gas exploration. <p>Recent and continual advances in machine learning are driving a rapid increase in empirical modeling capabilities. This book shows you how these new tools and methodologies can enhance geophysical and petrophysical data analysis, increasing the value of your exploration data. <ul> <li>Apply data-driven modeling concepts in a geophysical and petrophysical context</li> <li>Learn how to get more information out of models and simulations</li> <li>Add value to everyday tasks with the appropriate Big Data application</li> <li>Adjust methodology to suit diverse geophysical and petrophysical contexts</li> </ul> <p>Data-driven modeling focuses on analyzing the total data within a system, with the goal of uncovering connections between input and output without definitive knowledge of the system's physical behavior. This multi-faceted approach pushes the boundaries of conventional modeling, and brings diverse fields of study together to apply new information and technology in new and more valuable ways. <i>Enhance Oil & Gas Exploration with Data-Driven Geophysical and Petrophysical Models</i> takes you beyond traditional deterministic interpretation to the future of exploration data analysis.
<p>Foreword xv</p> <p>Preface xxi</p> <p>Acknowledgments xxiii</p> <p><b>Chapter 1 Introduction to Data-Driven Concepts 1</b></p> <p>Introduction 2</p> <p>Current Approaches 2</p> <p>Is There a Crisis in Geophysical and Petrophysical Analysis? 3</p> <p>Applying an Analytical Approach 4</p> <p>What Are Analytics and Data Science? 5</p> <p>Meanwhile, Back in the Oil Industry 8</p> <p>How Do I Do Analytics and Data Science? 10</p> <p>What Are the Constituent Parts of an Upstream Data Science Team? 13</p> <p>A Data-Driven Study Timeline 15</p> <p>What Is Data Engineering? 18</p> <p>A Workflow for Getting Started 19</p> <p>Is It Induction or Deduction? 30</p> <p>References 32</p> <p><b>Chapter 2 Data-Driven Analytical Methods Used in E&P 34</b></p> <p>Introduction 35</p> <p>Spatial Datasets 36</p> <p>Temporal Datasets 37</p> <p>Soft Computing Techniques 39</p> <p>Data Mining Nomenclature 40</p> <p>Decision Trees 43</p> <p>Rules-Based Methods 44</p> <p>Regression 45</p> <p>Classification Tasks 45</p> <p>Ensemble Methodology 48</p> <p>Partial Least Squares 50</p> <p>Traditional Neural Networks: The Details 51</p> <p>Simple Neural Networks 54</p> <p>Random Forests 59</p> <p>Gradient Boosting 60</p> <p>Gradient Descent 60</p> <p>Factorized Machine Learning 62</p> <p>Evolutionary Computing and Genetic Algorithms 62</p> <p>Artificial Intelligence: Machine and Deep Learning 64</p> <p>References 65</p> <p><b>Chapter 3 Advanced Geophysical and Petrophysical Methodologies 68</b></p> <p>Introduction 69</p> <p>Advanced Geophysical Methodologies 69</p> <p>How Many Clusters? 70</p> <p>Case Study: North Sea Mature Reservoir Synopsis 72</p> <p>Case Study: Working with Passive Seismic Data 74</p> <p>Advanced Petrophysical Methodologies 78</p> <p>Well Logging and Petrophysical Data Types 78</p> <p>Data Collection and Data Quality 82</p> <p>What Does Well Logging Data Tell Us? 84</p> <p>Stratigraphic Information 86</p> <p>Integration with Stratigraphic Data 87</p> <p>Extracting Useful Information from Well Reports 89</p> <p>Integration with Other Well Information 90</p> <p>Integration with Other Technical Domains at the Well Level 90</p> <p>Fundamental Insights 92</p> <p>Feature Engineering in Well Logs 95</p> <p>Toward Machine Learning 98</p> <p>Use Cases 98</p> <p>Concluding Remarks 99</p> <p>References 99</p> <p><b>Chapter 4 Continuous Monitoring 102</b></p> <p>Introduction 103</p> <p>Continuous Monitoring in the Reservoir 104</p> <p>Machine Learning Techniques for Temporal Data 105</p> <p>Spatiotemporal Perspectives 106</p> <p>Time Series Analysis 107</p> <p>Advanced Time Series Prediction 108</p> <p>Production Gap Analysis 112</p> <p>Digital Signal Processing Theory 117</p> <p>Hydraulic Fracture Monitoring and Mapping 117</p> <p>Completions Evaluation 118</p> <p>Reservoir Monitoring: Real-Time Data Quality 119</p> <p>Distributed Acoustic Sensing 122</p> <p>Distributed Temperature Sensing 123</p> <p>Case Study: Time Series to Optimize Hydraulic Fracture Strategy 129</p> <p>Reservoir Characterization and Tukey Diagrams 131</p> <p>References 138</p> <p><b>Chapter 5 Seismic Reservoir Characterization 140</b></p> <p>Introduction 141</p> <p>Seismic Reservoir Characterization: Key Parameters 141</p> <p>Principal Component Analysis 146</p> <p>Self-Organizing Maps 146</p> <p>Modular Artificial Neural Networks 147</p> <p>Wavelet Analysis 148</p> <p>Wavelet Scalograms 157</p> <p>Spectral Decomposition 159</p> <p>First Arrivals 160</p> <p>Noise Suppression 161</p> <p>References 171</p> <p><b>Chapter 6 Seismic Attribute Analysis 174</b></p> <p>Introduction 175</p> <p>Types of Seismic Attributes 176</p> <p>Seismic Attribute Workflows 180</p> <p>SEMMA Process 181</p> <p>Seismic Facies Classification 183</p> <p>Seismic Facies Dataset 188</p> <p>Seismic Facies Study: Preprocessing 189</p> <p>Hierarchical Clustering 190</p> <p>k-means Clustering 193</p> <p>Self-Organizing Maps (SOMs) 194</p> <p>Normal Mixtures 195</p> <p>Latent Class Analysis 196</p> <p>Principal Component Analysis (PCA) 198</p> <p>Statistical Assessment 200</p> <p>References 204</p> <p><b>Chapter 7 Geostatistics: Integrating Seismic and Petrophysical Data 206</b></p> <p>Introduction 207</p> <p>Data Description 208</p> <p>Interpretation 210</p> <p>Estimation 210</p> <p>The Covariance and the Variogram 211</p> <p>Case Study: Spatially Predicted Model of Anisotropic Permeability 214</p> <p>What Is Anisotropy? 214</p> <p>Analysis with Surface Trend Removal 215</p> <p>Kriging and Co-kriging 224</p> <p>Geostatistical Inversion 229</p> <p>Geophysical Attribute: Acoustic Impedance 230</p> <p>Petrophysical Properties: Density and Lithology 230</p> <p>Knowledge Synthesis: Bayesian Maximum Entropy (BME) 231</p> <p>References 237</p> <p><b>Chapter 8 Artificial Intelligence: Machine and Deep Learning 240</b></p> <p>Introduction 241</p> <p>Data Management 243</p> <p>Machine Learning Methodologies 243</p> <p>Supervised Learning 244</p> <p>Unsupervised Learning 245</p> <p>Semi-Supervised Learning 245</p> <p>Deep Learning Techniques 247</p> <p>Semi-Supervised Learning 249</p> <p>Supervised Learning 250</p> <p>Unsupervised Learning 250</p> <p>Deep Neural Network Architectures 251</p> <p>Deep Forward Neural Network 251</p> <p>Convolutional Deep Neural Network 253</p> <p>Recurrent Deep Neural Network 260</p> <p>Stacked Denoising Autoencoder 262</p> <p>Seismic Feature Identification Workflow 268</p> <p>Efficient Pattern Recognition Approach 268</p> <p>Methods and Technologies: Decomposing Images into Patches 270</p> <p>Representing Patches with a Dictionary 271</p> <p>Stacked Autoencoder 272</p> <p>References 274</p> <p><b>Chapter 9 Case Studies: Deep Learning in E&P 276</b></p> <p>Introduction 277</p> <p>Reservoir Characterization 277</p> <p>Case Study: Seismic Profile Analysis 280</p> <p>Supervised and Unsupervised Experiments 280</p> <p>Unsupervised Results 282</p> <p>Case Study: Estimated Ultimate Recovery 288</p> <p>Deep Learning for Time Series Modeling 289</p> <p>Scaling Issues with Large Datasets 292</p> <p>Conclusions 292</p> <p>Case Study: Deep Learning Applied to Well Data 293</p> <p>Introduction 293</p> <p>Restricted Boltzmann Machines 294</p> <p>Mathematics 297</p> <p>Case Study: Geophysical Feature Extraction: Deep Neural Networks 298</p> <p>CDNN Layer Development 299</p> <p>Case Study: Well Log Data-Driven Evaluation for Petrophysical Insights 302</p> <p>Case Study: Functional Data Analysis in Reservoir Management 306</p> <p>References 312</p> <p>Glossary 314</p> <p>About the Authors 320</p> <p>Index 323</p>
<p><b>KEITH R. HOLDAWAY</b> is advisory industry consultant and principal solutions architect at SAS. He holds seven patents and is the author of <i>Harness Oil and Gas Big Data with Analytics</i>. <p><b>DUNCAN H. B. IRVING</b> is a practice partner for oil and gas consulting at Teradata. He publishes regularly on big data analytics applied to the upstream domain<i>.</i>
<p><b>UNEARTH A RICHER VALUE FROM GEOPHYSICAL AND PETROPHYSICAL EXPLORATION DATA</b> <p>The disruptive effects of big data have reached the oil and gas industry and resulted in extraordinary advancements. <i>Enhance Oil & Gas Exploration with Data-Driven Geophysical and Petrophysical Models</i> is your practical guidebook to getting the most out of continually maturing computational intelligence in order to give you the highest quality, real-time information to make the right business decisions. <p>Written by two thought leaders in the field, this collection of easy-to-follow discussions offers a relevant depth of coverage and clarifying case studies to fully prepare you to use this dependable probabilistic model in the real world to: <ul> <li>Add greater value to your exploration data with new tools and methodologies for advanced geophysical and petrophysical data analysis</li> <li>Break down business silos to streamline processes, produce more accurate determinations, and strip away the negative side effects of data compartmentalization</li> <li>Blend traditional deterministic interpretation with data-driven deep learning and data mining to overcome a diverse variety of business challenges</li> </ul> <p>Let your data tell you where profits lie with <i>Enhance Oil & Gas Exploration with Data-Driven Geophysical and Petrophysical Models.</i>

Diese Produkte könnten Sie auch interessieren:

Designated Drivers
Designated Drivers
von: G. E. Anderson
PDF ebook
22,99 €
Quantitative Financial Economics
Quantitative Financial Economics
von: Keith Cuthbertson, Dirk Nitzsche
PDF ebook
40,99 €