Back to search

West Virginia University

Hydraulic Fracturing Treatment Optimization Using Machine Learning

Abstract

dc:description.abstract

Friction reducers are chemicals used in hydraulic fracturing to reduce friction between fracturing fluid and the wellbore walls, helping to overcome tubular drag at high flow rates. High viscosity friction reducers are increasingly used due to operational and economic benefits, but their optimal concentration for each stage of fracturing is not well studied. As a result, oil and gas companies often use more friction reducers than necessary to ensure designed injection rates are achieved and to avoid screening out, resulting in excess use of FR and economic losses. The primary goal of this Thesis is to fully comprehend and quantify the performance of the Hydraulic Fracturing Friction Reducer in a wide range of concentrations used in the completion of eight horizontal Marcellus Shale wells, as well as to optimize the amount of friction reducer required to complete the job and reduce the cost associated with it. Several machine learning approaches have been employed and it is going to be discussed with its approach, and data from BOGGESS wells have been evaluated to optimize the amount of friction reducer. Finally, an economic analysis will determine the project's net present value (NPV) and accumulated savings of FR cost per stage. Data collected from 1500 wells stimulated in Marcellus Shale. The data were reviewed to define the problem statement of using too much FR concentration. However, due to confidentiality agreement, data from Boggess pads from the MSEEL project including Boggess 1H, 3H, 5H, 9H, and 17H will be used. The collected data was the one second reading for the completion process for each stage from MSEEL project website.

Degree

thesis:*
Name thesis:degree_name
MS
Level thesis:degree_level
Thesis
Discipline thesis:degree_discipline
Petroleum and Natural Gas Engineering

Author and committee

dc:creator, dc:contributor.*
Author dc:creator
  • Johar, Abdullah
Contributors dc:contributor
  • Ebrahim Fathi
  • Samuel Ameri
  • Kashy Aminian

Subjects

dc:subject × 7

Identifiers

dc:identifier.*

Chain of custody

source
Harvested from
West Virginia University
Base URL
researchrepository.wvu.edu/do/oai/
Last updated
2026-11-19
Source record
OAI-PMH GetRecord
citation

Johar, Abdullah. Hydraulic Fracturing Treatment Optimization Using Machine Learning. Thesis thesis, https://doi.org/10.33915/etd.11697