Evaluating Machine Learning Techniques for Carbonate Formation Permeability Prediction Using Well Log Data

Abstract

Machine learning has a significant advantage for many difficulties in the oil and gas industry, especially when it comes to resolving complex challenges in reservoir characterization. Permeability is one of the most difficult petrophysical parameters to predict using conventional logging techniques. Clarifications of the work flow methodology are presented alongside comprehensive models in this study. The purpose of this study is to provide a more robust technique for predicting permeability; previous studies on the Bazirgan field have attempted to do so, but their estimates have been vague, and the methods they give are obsolete and do not make any concessions to the real or rigid in order to solve the permeability computation. To verify the reliability of training data for zone-by-zone modeling, we split the scenario into two scenarios and applied them to seven wells' worth of data. Moreover, all wellbore intervals were processed, for instance, all five units of Mishrif formation. According to the findings, the more information we have, the more accurate our forecasting model becomes. Multi-resolution graph-based clustering has demonstrated its forecasting stability in two instances by comparing it to the other five machine learning models.

Advanced Machine Learning application for Permeability Prediction for (M) Formation in an Iraqi Oil Field

“…A part of artificial intelligence (AI) is machine learning. The oil and gas industry has become more dependent on machine learning to reservoir characterization activities, forecast future production, drilling, stimulation and formation assessment [8]. Machine learning encompasses both supervised and unsupervised learning approaches.…”

Electrical facies of the Asmari Formation in the Mansouri oilfield, an application of multi-resolution graph-based and artificial neural network clustering methods

“…Eventually, the experimental results illustrated that the adaptive multi-resolution graph-based clustering algorithm for electrifying analysis also outperformed the original MRGC approach on clustering and propagation prediction with higher efficiency and stability 34,43,44 . Recently, the electrifies predicted using the MRGC approach to generate rock mechanical properties such as Young's modulus, Poisson's ratio, unconfirmed compressive strength, and internal friction coefficient 5,45,46 . Kianoush 47 estimated an ANN based model of formation Pressure for the Azadegan hydrocarbon Reservoir, SW Iran.…”

An Overview of How the Petrophysical Properties of Rock Influenced After Being Exposed to Cryogenic Fluid

“…Some common examples of cryogenic fracturing fluids include liquid nitrogen (-196 °C) and liquid helium (-268 °C) (State, Polytechnic and Kingdom, 2010;Li et al, 2022;Qu et al, 2023). These cryogenic liquids are known for their low temperatures, which can cause thermal shock in rock formations, leading to changes in their physical properties such as density, porosity, permeability, and elastic properties (Khalil and Emadi, 2020;Memon et al, 2020;Wang et al, 2022a;Alameedy et al, 2023b). This can result in the formation of fractures, improving the flow of fluids, such as oil and gas, in the reservoir.…”