Data Science and Machine Learning Applications in Subsurface Engineering

by Daniel Asante Otchere (Editor)

Overview

This book covers unsupervised learning, supervised learning, clustering approaches, feature engineering, explainable AI and multioutput regression models for subsurface engineering problems. Processing voluminous and complex data sets are the primary focus of the field of machine learning (ML). ML aims to develop data-driven methods and computational algorithms that can learn to identify complex and non-linear patterns to understand and predict the relationships between variables by analysing extensive data. Although ML models provide the final output for predictions, several steps need to be performed to achieve accurate predictions. These steps, data pre-processing, feature selection, feature engineering and outlier removal, are all contained in this book. New models are also developed using existing ML architecture and learning theories to improve the performance of traditional ML models and handle small and big data without manual adjustments.

This research-oriented book will help subsurface engineers, geophysicists, and geoscientists become familiar with data science and ML advances relevant to subsurface engineering. Additionally, it demonstrates the use of data-driven approaches for salt identification, seismic interpretation, estimating enhanced oil recovery factor, predicting pore fluid types, petrophysical property prediction, estimating pressure drop in pipelines, bubble point pressure prediction, enhancing drilling mud loss, smart well completion and synthetic well log predictions.

Product Details

ISBN-13:	9781032433646
Publisher:	CRC Press
Publication date:	02/06/2024
Pages:	322
Product dimensions:	6.12(w) x 9.19(h) x (d)

About the Author

Daniel Asante Otchere is an AI/ML Scientific Engineer at the Institute of Computational and Data Sciences (ICDS) at Pennsylvania State University, USA. He holds a PhD in petroleum engineering from Universiti Teknologi PETRONAS (UTP) in Malaysia, a Master's degree in Petroleum Geoscience from the University of Manchester in UK, and a Bachelor's degree in Geological Engineering from the University of Mines and Technology in Ghana. Professionally, Daniel has extensive experience across the mining and oil and gas industry, working on several onshore and offshore projects that have had a significant impact on the industry in Africa and South East Asia. He serves as a technical committee member of the World Geothermal Congress and teaches several AI topics on his YouTube channel "Study with Dani". His expertise has resulted in numerous collaborative research efforts, yielding several articles published in renowned journals and conferences. He was recognised for excellence in teaching and research in the Petroleum Engineering Department at UTP and received the 2021 best postgraduate student and the Graduate Assistant merit award in 2021 and 2022. He enjoys watching movies, listening to Highlife and Afrobeats music, hockey, and playing football. He also excels in the realm of video games, having won numerous PlayStation-FIFA tournaments held in the United Kingdom, Ghana, and Malaysia.

Table of Contents

Foreword

Preface

1.   Introduction

2.  Enhancing Drilling Fluid Lost-circulation Prediction: Using Model Agnostic and Supervised Machine Learning

Introduction

Background of Machine Learning Regression Models

Data Collection and Description

Methodology

Results and Discussion

Conclusions

References 

3.  Application of a Novel Stacked Ensemble Model in Predicting Total Porosity and Free Fluid Index via Wireline and NMR Logs

Introduction

Nuclear Magnetic Resonance

Methodology

Results and Discussion

Conclusions

References 

4.  Compressional and Shear Sonic Log Determination: Using Data-Driven Machine Learning Techniques

Introduction

Literature Review

Background of Machine Learning Regression Models

Data Collection and Description

Methodology

Results and Discussion

Conclusions

References 

5.  Data-Driven Virtual Flow Metering Systems

Introduction

VFM Key Characteristics

Data Driven VFM Main Application Areas

Methodology of Building Data-driven VFMs

Field Experience with a Data-driven VFM System

References 

6.  Data-driven and Machine Learning Approach in Estimating Multi-zonal ICV Water Injection Rates in a Smart Well Completion Introduction

Brief Overview of Intelligent Well Completion

Methodology

Results and Discussion

Conclusions

References 

7.    Carbon Dioxide Low Salinity Water Alternating Gas (CO₂ LSWAG) Oil Recovery Factor Prediction in Carbonate Reservoir: Using Supervised Machine Learning Models

Introduction

Methodology

Results and Discussion

Conclusion

References 

8.  Improving Seismic Salt Mapping through Transfer Learning Using a Pre-trained Deep Convolutional Neural Network: A Case Study on Groningen Field

Introduction

Method

Results and Discussion

Conclusions

References 

9.  Super-Vertical-Resolution Reconstruction of Seismic Volume Using a Pre-trained Deep Convolutional Neural Network: A Case Study on Opunake Field

Introduction

Brief Overview

Methodology

Results and Discussion

Conclusions

References 

10.  Petroleum Reservoir Characterisation: A Review from Empirical to Computer-Based Applications

Introduction

Empirical Models for Petrophysical Property Prediction

Fractal Analysis in Reservoir Characterisation

Application of Artificial Intelligence in Petrophysical Property Prediction

Lithology and Facies Analysis

Seismic Guided Petrophysical Property Prediction

Hybrid Models of AI for Petrophysical Property Prediction

Summary

Challenges and Perspectives

Conclusions

References 

11.  Artificial Lift Design for Future Inflow and Outflow Performance for Jubilee Oilfield: Using Historical Production Data and Artificial Neural Network Models

 Introduction

 Methodology

 Results and Discussion

 Conclusions

 References

12.  Modelling Two-phase Flow Parameters Utilizing Machine-learning Methodology

 Introduction

 Data Sources and Existing Correlations

 Methodology

 Results and Discussions

 Comparison between ML Algorithms and Existing Correlations

 Conclusions and Recommendations

 Nomenclature

 References

Index