book

Data Science and Machine Learning Applications in Subsurface Engineering

Name: Data Science and Machine Learning Applications in Subsurface Engineering
Author: Daniel Asante Otchere
ISBN: 9781003860228

by Daniel Asante Otchere

February 2024

Intermediate to advanced

322 pages

9h 36m

English

CRC Press

Read now

Unlock full access

Cover Page
Title Page
Copyright Page
Dedication
Foreword
Preface
Contents
1. Introduction
2. Enhancing Drilling Fluid Lost-circulation Prediction: Using Model Agnostic and Supervised Machine Learning
1. Introduction2. Background of Machine Learning Regression Models3. Data Collection and Description4. Methodology4.1 Data Analysis and Visualisation4.2 Machine Learning Model Application4.3 Explainable AI5. Results and Discussion5.1 Evaluation of Model Performance5.2 Model Agnostic Results5.3 Analysis of Features Using Model Agnostic Metrics5.4 Analysis of Features Using Shapley Values Model Agnostic Metrics5.5 Evaluation of Top Features5.6 Model Optimisation5.7 Sensitivity Analysis6. ConclusionsAcknowledgementData AvailabilityReferences
3. Application of a Novel Stacked Ensemble Model in Predicting Total Porosity and Free Fluid Index via Wireline and NMR Logs
1. Introduction2. Nuclear Magnetic Resonance2.1 Concept and Application2.2 Works Related to the Use of Machine Learning in NMR for Reservoir Characterisation3. Methodology3.1 Data Collection and Description3.2 Data Analysis and Feature Engineering3.3 Machine Learning Model Application3.4 Criteria for Model Evaluation4. Results and Discussion4.1 Evaluation of Models' Performances5. ConclusionsAcknowledgementReferences

4. Compressional and Shear Sonic Log Determination Using Data-Driven Machine Learning Techniques
1. Introduction2. Literature Review3. Background of Machine Learning Regression Models3.1 Decision Tree Conceptual Overview3.2 Random Forest Conceptual Overview3.3 Extremely Randomised Trees Conceptual Overview4. Data Collection and Description5. Methodology5.1 Data Analysis and Visualisation5.2 Machine Learning Model Application6. Results and Discussion6.1 Evaluation of Model Performance6.2 Model Optimisation6.3 Model Deployment7. ConclusionsAcknowledgementData AvailabilityReferences
5. Data-Driven Virtual Flow Metering Systems
1. Introduction2. VFM Key Characteristics3. Data Driven VFM Main Application Areas3.1 Virtual Sensing in ESP Wells3.2 Virtual Sensing for SRP Wells3.3 Virtual Sensing for Gas Lifted Wells3.4 Virtual Sensing for Gas Wells and Plunger Lifted Wells3.5 Miscellaneous Applications for Identifying Flow Regimes4. Methodology of Building Data-driven VFMs4.1 Data Collection and Preprocessing4.2 Model Development5. Field Experience with a Data-driven VFM SystemReferences
6. Data-driven and Machine Learning Approach in Estimating Multi-zonal ICV Water Injection Rates in a Smart Well Completion
1. Introduction2. Brief Overview of Intelligent Well Completion2.1 ICV Setting and Determination2.2 Literature Review of ICV Innovations and Machine Learning Applications3. Methodology3.1 A Brief Overview of Models Used in This Study3.2 Criteria for Model Evaluation4. Results and Discussion4.1 Explainable AI4.2 Model Evaluation4.3 Sensitivity Analysis4.4 Model Deployment5. ConclusionsCode AvailabilityAcknowledgementReferences
7. Carbon Dioxide Low Salinity Water Alternating Gas (CO2 LSWAG) Oil Recovery Factor Prediction in Carbonate Reservoir: Using Supervised Machine Learning Models
1. Introduction2. Methodology2.1 Modelling of CO2-LSWAG2.2 Geochemical Reactions of CO2-LSWAG2.3 Machine Learning Methods3. Results and Discussion3.1 Numerical Model Description3.2 Input and Target Dataset3.3 MARS Modelling3.4 GMDH Modelling3.5 Numerical Simulator and Machine Learning Computational Time4. ConclusionAcknowledgmentReferences
8. Improving Seismic Salt Mapping through Transfer Learning Using A Pre-trained Deep Convolutional Neural Network: A Case Study on Groningen Field
1. Introduction2. Method2.1 Collection and Description of Data2.2 Deep Convolutional Neural Network in Salt Mapping and Post-processing2.3 Transfer Learning Application2.4 Criteria for Model Evaluation3. Results and Discussion3.1 Calculated Salt Body Volume3.2 Semantic Segmentation – Transfer Learning Application3.3 Sensitivity Analysis of Model and Expert Interpretations4. ConclusionsData and Software AvailabilityAcknowledgementReferences
9. Super-Vertical-Resolution Reconstruction of Seismic Volume Using A Pre-trained Deep Convolutional Neural Network: A Case Study on Opunake Field
1. Introduction2. Brief Overview3. Methodology3.1 Regional Geological Overview of the Opunake Field3.2 Local Geological Overview of the Opunake Field3.3 Deep Convolutional Neural Network in Seismic Image Resolution3.4 Training and Testing Process3.5 Criteria for Model Evaluation4. Results and Discussion4.1 Conditioned Seismic Volume4.2 Model Evaluation5. ConclusionsData and Software AvailabilityAcknowledgementReferences
10. Petroleum Reservoir Characterisation A Review from Empirical to Computer-Based Applications
1. Introduction2. Empirical Models for Petrophysical Property Prediction2.1 Porosity and Permeability Prediction Models2.2 Saturation Prediction Models3. Fractal Analysis in Reservoir Characterisation4. Application of Artificial Intelligence in Petrophysical Property Prediction4.1 Artificial Neural Networks (ANNs)4.2 Support Vector Machine (SVM)5. Lithology and Facies Analysis5.1 AI Applications in Lithology and Facies Analysis6. Seismic Guided Petrophysical Property Prediction7. Hybrid Models of AI for Petrophysical Property Prediction8. Summary9. Challenges and Perspectives9.1 AI Perspective9.2 Rock Physics Perspective10. ConclusionsReferences
11. Artificial Lift Design for Future Inflow and Outflow Performance for Jubilee Oilfield: Using Historical Production Data and Artificial Neural Network Models
1. Introduction2. Methodology2.1 Artificial Lift Screening Techniques2.2 Inflow Performance Relationship Production Forecast2.3 Outflow Performance Relationship Production Forecast2.4 PROSPER Procedure for Well Model Set-Up2.5 Artificial Neural Networks3. Results and Discussion3.1 Production and Well Data of the Study Area3.2 Artificial Lift Screening3.3 PROSPER Simulation Results3.4 Gas Lift Results3.5 ANN Results3.6 Discussion4. ConclusionsAcknowledgmentReferences
12. Modelling Two-phase Flow Parameters Utilizing Machine-learning Methodology
1. Introduction2. Data Sources and Existing Correlations3. Methodology4. Results and Discussions4.1 Data Pre-processing4.2 Model Development and Evaluation5. Comparison between ML Algorithms and Existing Correlations6. Conclusions and RecommendationsReferences
Index

Content preview from Data Science and Machine Learning Applications in Subsurface Engineering

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

Longtong Dafyak* and Buddhika Hewakandamby

University of Nottingham, UK.

1. Introduction

Two-phase flow is predominant in natural occurring and industrial processes; from water droplets entrained in the air to domestic water distribution lines, combustion engines, power generation plants, amongst others. In the exploration industry, gas-liquid flow in pipes is a standard practice due to the coexistence of these fluids in the subsurface (McCain, 1994; Soloveichik et al., 2022). Furthermore, pipelines are still the safest and most economical means of transporting fluids over long distances (Green and Jackson, ...

Become an O’Reilly member and get unlimited access to this title plus top books and audiobooks from O’Reilly and nearly 200 top publishers, thousands of courses curated by job role, 150+ live events each month,
and much more.

Read now

Unlock full access

More than 5,000 organizations count on O’Reilly

O’Reilly covers everything we've got, with content to help us build a world-class technology community, upgrade the capabilities and competencies of our teams, and improve overall team performance as well as their engagement.

Julian F.

Head of Cybersecurity

I wanted to learn C and C++, but it didn't click for me until I picked up an O'Reilly book. When I went on the O’Reilly platform, I was astonished to find all the books there, plus live events and sandboxes so you could play around with the technology.

Addison B.

Field Engineer

I’ve been on the O’Reilly platform for more than eight years. I use a couple of learning platforms, but I'm on O'Reilly more than anybody else. When you're there, you start learning. I'm never disappointed.

Amir M.

Data Platform Tech Lead

I'm always learning. So when I got on to O'Reilly, I was like a kid in a candy store. There are playlists. There are answers. There's on-demand training. It's worth its weight in gold, in terms of what it allows me to do.

Mark W.

Embedded Software Engineer

Publisher Resources

ISBN: 9781003860228

Cloud Computing

Data Engineering

Data Science

AI & ML

Programming Languages

Software Architecture

IT/Ops

Security

Design

Business

Soft Skills

Data Science and Machine Learning Applications in Subsurface Engineering

by Daniel Asante Otchere

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

1. Introduction

Become an O’Reilly member and get unlimited access to this title plus top books and audiobooks from O’Reilly and nearly 200 top publishers, thousands of courses curated by job role, 150+ live events each month,
and much more.