Introduction The accurate characterization of the lithology porosity is critical for geological interpretation and decision making in petroleum exploration. For this, wireline logging (including sonic, neutron porosity, and density, among other logs) is often used for the characterization of geophysical data performed as a function of wellbore depth. The common practice in the oil and gas industry is to perform the wireline logging for every new well, which is a lengthy and expensive operation. Therefore, the objective of this study is to use the historical logging data and surface drilling parameters to derive machine-learning (ML) models able to identify the different lithology classifications. Methodology We used historical logging data and surface drilling parameters to derive ML models to predict the following lithology classification: 1) porous gas, 2) porous wet, 3) tight sand, and 4) shaly sand. These models can predict these classifications without running wireline logs in the new wells. In this approach, the four lithology classifications are defined from the sonic, neutron porosity, gamma-ray, and density logs from historical data and are considered as the learning target/labels for the ML model. Therefore, the ML model learns the relationship between the surface drilling parameters and mud weight with their respective lithology classification. Finally, the model is capable of being executed in real-time, improving crew decision making. Results The results obtained from a stratified 5-fold cross-validation technique demonstrated that the random forest model was able to learn from the data with an accurate classification for the four lithology porosity categories. The derived ML model obtained an average of 89.66% and 89.20% for precision and recall, respectively. Novelty Although many studies have suggested the use of ML to imputing logging data, the inputs of these models are the data from other logs. Conversely, our proposed approach utilizes the wireline logging data only during the training of the model for assigning the porosity classification as labels. As such, the model learns the relationship between drilling parameters and the associated labels. This approach not only simplifies the learning of the ML but eliminates the need to run wireline logging in new wells, considerably reducing time and costs.
There are many reservoir simulation applications for multiphase flow in porous media where hysteresis or path-dependence of both relative permeability and capillary pressure functions are crucial to capture. The formation of a residual non-wetting phase saturation due to capillary trapping in a hysteretic manner carries significant implications to some major petroleum development processes such as EOR or water-alternating-gas (WAG), as well as environmental processes, such as geologic CO2 storage. In this paper, we focus on accurately quantifying how much of the injected CO2 gets trapped underground due to relative permeability hysteresis only and the most efficient way to model this physical phenomenon. Over the years, multiple methods for implementing hysteresis into reservoir simulators were introduced to capture the trapping phenomenon. However, these complex methods created numerical difficulties especially when flow reversal happens, creating nonlinear solver convergence issues due to discontinuous derivatives. A new technique has been introduced recently with a claim of smoother behavior and better non-linear solver performance. The main goal of this study is to assess this new technique by looking at both nonlinear solver performance as well as the method accuracy compared to previous standard models. Here, three models are implemented in an implicit state-of-the-art simulator especially developed for this study. This is equipped with nonlinear-convergence-enhancing techniques such as Appleyard saturation chopping and different upstream weighting. The hysteresis models are implemented for relative permeability of the non-wetting phase only and has been ignored in the wetting phase, and the study also neglects the capillary pressure hysteresis. The paper presents the theoretical background of the models and their implementations as well as the significance of accounting for hysteresis in such applications. Then, simulation results and numerical analyses are presented for a 1D gravity segregation case in a hypothetical CO2 storage setting. The results show that the new model proved to offer a better numerical handle of the hysteresis in reservoir simulation. This improvement is particularly significant in normal moderate CFL number scenarios, while in the very low or very high scenarios, the improvement is modest. All models can produce similar results if their relative permeability curves have been fitted well. It is important to keep in mind that even though the numerical differences are not huge in this simple test case, these results show indication of where difficulties can arise from when this simple test case is taken into more complicated settings. Capturing the accurate physics for such processes, namely underground CO2 storage, is vital as studies show that this accounts for a great deal of the CO2 trapped underground; however, this may be a difficult task for most commercial simulators. In this work, we analyze different models to capture such physics and introduce new way with enhanced efficiency compared to existing techniques as evident by numerical analysis results.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.