Enhancing Petrophysical Studies with Machine Learning: A Field Case Study on Permeability Prediction in Heterogeneous Reservoirs

TL;DR

This study compares machine learning algorithms to predict permeability in heterogeneous reservoirs, demonstrating their effectiveness in enhancing petrophysical analysis and reservoir performance predictions.

Contribution

It introduces a comparative analysis of ANN, RFC, and SVM for permeability prediction using conventional logs and core data in a field case.

Findings

Machine learning algorithms effectively predict permeability logs.

FZI rock typing enhances understanding of reservoir quality.

ML methods improve reservoir simulation accuracy.

Abstract

This field case study aims to address the challenge of accurately predicting petrophysical properties in heterogeneous reservoir formations, which can significantly impact reservoir performance predictions. The study employed three machine learning algorithms, namely Artificial Neural Network (ANN), Random Forest Classifier (RFC), and Support Vector Machine (SVM), to predict permeability log from conventional logs and match it with core data. The primary objective of this study was to compare the effectiveness of the three machine learning algorithms in predicting permeability and determine the optimal prediction method. The study utilized the Flow Zone Indicator (FZI) rock typing technique to understand the factors influencing reservoir quality. The findings will be used to improve reservoir simulation and locate future wells more accurately. The study concluded that the FZI approach and machine learning algorithms are effective in predicting permeability log and improving reservoir performance predictions.