The principal aim of this investigation is to probe Artificial Intelligence (AI) techniques to foretell and regulate the complex phenomenon of simultaneous coning. Simulating the coning behavior is a costly and time-consuming method. As a result, a ready-made correlation that serves as a rapid estimate is necessary. This inquiry harnesses sophisticated AI models including Artificial neural network (ANN) to develop a robust empirical correlation for critical oil flow using the most efficacious parameters for managing coning. The study presents a 3D reservoir simulation model that has been tested for a variety of fracture characteristics, reservoir, and fluid properties including conductivity, permeability, density, permeability anisotropy, and viscosity. The newly proposed correlation is dimensionless, i.e., it applies to all vertically fractured wells in tight oil reservoirs, furnishing considerable benefits to the oil and gas sector.

Keywords:
fluid dynamics, geologist, upstream oil & gas, neural network, artificial intelligence, pvt measurement, petroleum geology, machine learning, fracture conductivity, international
Subjects:
Hydraulic Fracturing, Reservoir Characterization, Fluid Characterization, Reservoir Fluid Dynamics, Reservoir Simulation, Information Management and Systems, Phase behavior and PVT measurements, Flow in porous media, Artificial intelligence, Neural networks
This content is only available via PDF.
Copyright 2023, Society of Exploration Geophysicists and the American Association of Petroleum Geologists
You can access this article if you purchase or spend a download.