Engineering Commons^™

Machine Learning Assisted Framework For Advanced Subsurface Fracture Mapping And Well Interference Quantification, Mohammad Faiq Adenan

Graduate Theses, Dissertations, and Problem Reports

The oil and gas industry has historically spent significant amount of capital to acquire large volumes of analog and digital data often left unused due to lack of digital awareness. It has instead relied on individual expertise and numerical modelling for reservoir development, characterization, and simulation, which is extremely time consuming and expensive and inevitably invites significant human bias and error into the equation. One of the major questions that has significant impact in unconventional reservoir development (e.g., completion design, production, and well spacing optimization), CO2 sequestration in geological formations (e.g., well and reservoir integrity), and engineered geothermal systems (e.g., …

The Effect Of Different Fracturing Fluids On The Productivity Of Multi-Staged Fractured Marcellus Shale Horizontal Wells, Vida Gyaubea Matey-Korley

Graduate Theses, Dissertations, and Problem Reports

While hydraulic fracturing has undeniably improved the production from oil and gas reservoirs, this technology is not without limitations. The primary hurdles lie in the areas of proppant transport, fluid rheology, and stress management. Despite the extensive research conducted in this domain, there remains a considerable amount of work to be done for comprehensive solutions that account for the complex interactions among fracturing fluid, proppant distribution, and geomechanical conditions. Achieving this will then make room for a holistic and efficient hydraulic fracturing strategy.

This study addresses the above-mentioned problem by examining the impact of fluid type on proppant transport and …

Leveraging Artificial Intelligence And Geomechanical Data For Accurate Shear Stress Prediction In Co2 Sequestration Within Saline Aquifers (Smart Proxy Modeling), Munirah Alawadh

Graduate Theses, Dissertations, and Problem Reports

This research builds upon the success of a previous project that used a Smart Proxy Model (SPM) to predict pressure and saturation in Carbon Capture and Storage (CCS) operations into saline aquifers. The Smart Proxy Model is a data-driven machine learning model that can replicate the output of a sophisticated numerical simulation model for each time step in a short amount of time, using Artificial Intelligence (AI) and large volumes of subsurface data. This study aims to develop the Smart Proxy Model further by incorporating geomechanical datadriven techniques to predict shear stress by using a neural network, specifically through supervised …

Comparative Analysis Of Artificial Intelligence And Numerical Reservoir Simulation In Marcellus Shale Wells, Arya Maher Sattari

Graduate Theses, Dissertations, and Problem Reports

This dissertation addresses the limitations of conventional numerical reservoir simulation techniques in the context of unconventional shale plays and proposes the use of data-driven artificial intelligence (AI) models as a promising alternative. Traditional methods, while providing valuable insights, often rely on simplifying assumptions and are constrained by time, resources, and data quality. The research leverages AI models to handle the complexities of shale behavior more effectively, facilitating accurate predictions and optimizations with less resource expenditure.

Two specific methodologies are investigated for this purpose: traditional numerical reservoir simulations using Computer Modelling Group's GEM reservoir simulation software, and an AI-based Shale Analytics …

An Artificial Neural Network Approach To Predicting Formation Stress In Multi-Stage Fractured Marcellus Shale Horizontal Wells Based On Drilling Operations Data, Moudhi Alawadh

Graduate Theses, Dissertations, and Problem Reports

The distribution of the anisotropic minimum horizontal stress, both in horizontal and vertical directions, is necessary for effective hydraulic fracture treatment design in Marcellus Shale horizontal wells. Typically, the minimum horizontal stress can be estimated sonic logs. However, sonic log data is not commonly available for the horizontal Marcellus shale wells due to the complexity and cost. The objective of this research is to predict the anisotropic minimum horizontal stress by utilizing drilling parameters including depth, weight-on-bit (WOB), revolution per minute (RPM), standpipe pressure, torque, pump flow rate, and the rate of penetration (ROP). More specifically, artificial neural network (ANN) …