Semester

Fall

Date of Graduation

2023

Document Type

Thesis

Degree Type

MS

College

Statler College of Engineering and Mineral Resources

Department

Petroleum and Natural Gas Engineering

Committee Chair

Shahab Mohaghegh

Committee Member

Kashy Aminian

Committee Member

Samuel Ameri

Abstract

In this study, we developed a novel approach to generate synthetic well logs using backpropagation neural networks through the use of an open source software development tool. Our method predicts essential well logs such as neutron porosity, sonic, photoelectric, and resistivity, which are crucial in various stages of oil and gas exploration and development, as they help determine reservoir characteristics. Our approach involves sequentially predicting well logs, using the outputs of one prediction model as inputs for subsequent models to generate comprehensive and coherent sets of well logs. We trained and tested our models using 16 wells from a single field, and the resulting synthetic well logs demonstrated an acceptable degree of accuracy and consistency with the actual logs, thus supporting the efficacy of our approach. This research not only opens up new avenues for enhancing the efficiency of hydrocarbon exploration but also contributes to the growing body of knowledge in the field of AI and ML applications in the oil and gas industry. This work also demonstrates the capabilities of open source tools for developing software and for oil and gas applications.

Download

Share

COinS