Semester
Spring
Date of Graduation
2022
Document Type
Dissertation
Degree Type
PhD
College
Statler College of Engineering and Mineral Resources
Department
Petroleum and Natural Gas Engineering
Committee Chair
Shahab Mohaghegh
Committee Co-Chair
Samuel Ameri
Committee Member
Samuel Ameri
Committee Member
Kashy Aminian
Committee Member
Hassan Amini
Committee Member
Mehrdad Zamirian
Committee Member
Scott Reeves
Abstract
Over the last two decades, there has been advances in downhole monitoring in oil and gas wells with the use of Fiber-Optic sensing technology such as the Distributed Temperature Sensing (DTS). Unlike a conventional production log that provides only snapshots of the well performance, DTS provides continuous temperature measurements along the entire wellbore.
Whether by fluid extraction or injection, oil and gas production changes reservoir conditions, and continuous monitoring of downhole conditions is highly desirable. This research study presents a tool for real-time quantification of production from individual perforation clusters in a multi-stage shale well using Artificial Intelligence and Machine Learning. The technique presented provides continuous production log on demand thereby providing opportunities for the optimization of completions design and hydraulic fracture treatments of future planned wells. A Fiber-Optic sensing enabled horizontal well MIP-3H in the Marcellus Shale has been selected for this work. MIP-3H is a 28-stage horizontal well drilled in July 2015, as part of a Department of Energy (DOE)-sponsored project - Marcellus Shale Energy & Environment Laboratory (MSEEL). A one-day conventional production logging operation has been performed on MIP-3H using a flow scanner while the installed Fiber-Optic DTS unit has collected temperature measurements every three hours along the well since completion. An ensemble of machine learning models has been developed using as input the DTS measurements taken during the production logging operation, details of mechanical logs, completions design and hydraulic fracture treatments data of the well to develop the real-time shale gas production monitoring tool.
Recommended Citation
Aboaba, Ayodeji Luke, "Machine Learning Based Real-Time Quantification of Production from Individual Clusters in Shale Wells" (2022). Graduate Theses, Dissertations, and Problem Reports. 11269.
https://researchrepository.wvu.edu/etd/11269