Latest technological developments and applications made optimal control methods usage in optimal well placement in intelligent fields practical and beneficial to increase the production. Effective usage of these methods strongly depends on the detailed evaluation of the economic view and performance in reservoirs that have high uncertainty, particularly. There are several methods of optimization of well placement ranging from classical reservoir engineering to derivative-free and hybrid methods. TNO's Olympus model used globally as a benchmark model in ISAAP-2 Challenge in used. Geological modeling software is coupled with the commercial full-physics reservoir simulator as well as the optimization software in order to produce different geological realizations to represent the geological uncertainty and run the simulation model with differing inputs of optimization and uncertainty in a loop. Results are outlined in detail in a comparative way including comparison to the previous study to illustrate the challenges and benefits of smart wells and optimization of placement of them in intelligent fields. Results indicate that classical reservoir engineering principles still prove useful in the beginning of the optimization process. Then, derivative-free and hybrid methods introduce significant improvement on economics. There are certain challenges in CPU requirements however the state-of-the-art facilities provided significant reduction in runtimes along with the help of the hybrid methods where proxies are built and used for faster runtimes. Despite higher initial capital expenses, smart wells provide significant advantages in recovery and economics compared to that of the conventional wells where these is less control on the production/injection at the layer level. Literature lacks a comprehensive study that takes into account the optimization of well placement in smart fields focusing on smart wells and the all major available methods for optimization. This study closes that gap providing a strong reference building on top of the previous study extending it to intelligent fields which are becoming very common and useful in oil and gas industry in conventional and unconventional applications.
Machine learning models have worked as a robust tool in forecasting and optimization processes for wells in conventional, data-rich reservoirs. In unconventional reservoirs however, given the large ranges of uncertainty, purely data-driven, machine learning models have not yet proven to be repeatable and scalable. In such cases, integrating physics-based reservoir simulation methods along with machine learning techniques can be used as a solution to alleviate these limitations. The objective of this study is to provide an overview along with examples of implementing this integrated approach for the purpose of forecasting Estimated Ultimate Recovery (EUR) in shale reservoirs. This study is solely based on synthetic data. To generate data for one section of a reservoir, a full-physics reservoir simulator has been used. Simulated data from this section is used to train a machine learning model, which provides EUR as the output. Production from another section of the field with a different range of reservoir properties is then forecasted using a physics-based model. Using the earlier trained model, production forecasting for this section of the reservoir is then carried out to illustrate the integrated approach to EUR forecasting for a section of the reservoir that is not data rich. The integrated approach, or hybrid modeling, production forecasting for different sections of the reservoir that were data-starved, are illustrated. Using the physics-based model, the uncertainty in EUR predictions made by the machine learning model has been reduced and a more accurate forecasting has been attained. This method is primarily applicable in reservoirs, such as unconventionals, where one section of the field that has been developed has a substantial amount of data, whereas, the other section of the field will be data starved. The hybrid model was consistently able to forecast EUR at an acceptable level of accuracy, thereby, highlighting the benefits of this type of an integrated approach. This study advances the application of repeatable and scalable hybrid models in unconventional reservoirs and highlights its benefits as compared to using either physics-based or machine-learning based models separately.
EUR (Estimated Ultimate Recovery) forecasting in unconventional fields has been a tough process sourced by its physics involved in the production mechanism of such systems which makes it hard to model or forecast. Machine learning (ML) based EUR prediction becomes very challenging because of the operational issues and the quality of the data in historical production. Geology-driven EUR forecasting, once established, offers EUR forecasting solutions that is not affected by operational issues such as shut-ins. This study illustrates the overall methodology in intelligent fields with real-time data flow and model update that enables optimization of well placement in addition to EUR forecasting for individual wells. A synthetic but realistic model which demonstrates the physics is utilized to generate input data for training the ML model where the spatially-distributed geological parameters including but not limited to porosity, permeability, saturation have been used to describe the production values and ultimately the EUR. The completion is given where the formation characteristics vary in the field that lead to location-dependent production performance leading to well placement optimization based on EUR forecasting from the geological parameters. The algorithm not only predicts the EUR of an individual well and makes decision for the optimum well locations. As the training model includes data of interfering wells, the model is capable of capturing the pattern in the well interference. Even though a synthetic but realistic reservoir model is constructed to generate the data for the aim of assisting the ML model, in practice, it is not an easy task to (1) obtain the input parameters to build a robust reservoir simulation model and (2) understanding and modeling of physics of fluid flow and production in unconventionals is a complex and time-consuming task to build real models. Thus, data-driven approaches like this help to speed up reservoir management and development decisions with reasonable approximations compared to numerical models and solutions. Application of machine learning in intelligent fields is also explained where the models are dynamically-updated and trained with the new data. Geology-driven EUR forecasting has been applied and relatively-new in the industry. In. this study, we are extending it to optimize well placement in intelligent fields in unconventionals beyond other existing studies in the literature.
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.
customersupport@researchsolutions.com
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
This site is protected by reCAPTCHA and the Google Privacy Policy and Terms of Service apply.
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.