History matching is the process of adjusting uncertain reservoir parameters until an acceptable match with the measured production data is obtained. Complexity and insufficient knowledge of reservoir characteristics makes this process timeconsuming with high computational cost. In the recent years, many efforts mainly referred as assisted history matching have attempted to make this process faster; nevertheless, the degree of success of these techniques continues to be a subject for debate.This study aims to examine the application of a unique pattern recognition technology to improve the time and efforts required for completing a successful history matching project. The pattern recognition capabilities of Artificial Intelligence and Data Mining (AI&DM) are used to develop Surrogate Reservoir Model (SRM) for utilization as the engine to drive the history matching process. SRM is an intelligent prototype of the full-field reservoir simulation model that runs in fractions of a second. SRM is built using a handful of geological realizations.In this study, a synthetic reservoir model of a heterogeneous oilfield with 24 production wells and 30 years of production history was used as the ground truth (the subject and the goal of the history match). An SRM was created to accurately represent this reservoir model. The history matching process for this field was performed using the SRM and by tuning static data (Permeability). The result of this study demonstrates the capabilities of SRM for fast track and accurate reproduction of the numerical model results. Speed and accuracy make SRM a fast and effective tool for assisted history matching.
Smart Fields are distinguished with two characteristics: Big Data and Real-Time access. A small smart field with only ten wells can generate more than a billion data points every year. This data is streamed in real-time while being stored in data historians. The challenge for operating a smart field is to be able to process this massive amount of information in ways that can be useful in reservoir management and relevant operations. In this paper we introduce a technology for processing and utilization of data generated in a smart field. The project is a CO2 storage demonstration at Citronelle Dome, Alabama and the objective is to use smart field technology to build a real-time, long-term, CO2 Intelligent Leakage Detection System (ILDS). The main concern for geologic CO2 sequestration is the capability of the underground carbon dioxide storage to confine and sustain the injected CO2 for very long time. If a leakage from a geological sink occurs, it is crucial to find the approximate location and amount of the leak in order to take on proper remediation activity. To help accommodate CO2 leak detection, two PDGs (Permanent Down-hole Gauges) have been installed in the observation well. A reservoir simulation model for CO2 sequestration at Citronelle Dome was developed. Multiple scenarios of CO2 leakage are modeled and high frequency pressure data from the PDGs in the observation well are collected. The complexity of the pressure signal behavior and the reservoir model makes the use of inverse solution of analytical models impractical. Therefore an alternate solution is developed for the ILDS, based on Machine Learning. High Frequency Data Streams are processed in real-time, summarized (by Descriptive Statistics) and transformed into a format appropriate for pattern recognition technology. Successful detection of location and amount of CO2 leaking from the reservoir using the real-time data streams demonstrates the power of pattern recognition and machine learning as a reservoir and operational management tool for smart fields.
Unconventional hydrocarbon resources are going to play an important role in the US energy strategy. Conventional tools and techniques that are used for analysis of unconventional resources include decline curve analysis, type curve matching and sometimes (in the case of prolific assets) reservoir simulation. These methods have not been completely successful due to the fact that fluid flow in unconventional reservoirs does not follow the same physical principles that supports mentioned analytical and numerical methods. Application of an innovative technology, Top-Down Modeling (TDM), is proposed for the analyses of unconventional resources. This technology is completely data-driven, incorporating field measurements (drilling data, well logs, cores, well tests, production history, etc.) to build comprehensive full field reservoir models. In this study, a Top-Down Model (TDM) was developed for a field in Weld County, Colorado, producing from Niobrara. The TDM was built using data from more than 145 wells. Well logs, production history, well design parameters and dynamic production constrains are the main data attributes that were used to perform data driven analysis. The workflow for Top-Down Modeling included generating a high-level geological model followed by reservoir delineation based on regional productivity, reserve and recovery estimation, field wide pattern recognition (based on fuzzy set theory), Key Performance Indicator (KPI) analysis (which estimates the degree of influence of each parameter on the field production), and finally history matching the production data from individual wells and production forecasting. The results of production analysis by Top-Down Modeling can provide insightful guidelines for better planning and decision making.
Water is injected in the hydrocarbon reservoir to serve two purposes, to maintain reservoir pressure and to displace oil as production proceeds in the reservoir. In recent years, smart wells coupled with reservoir simulation models are used to improve the results of water injection performance. High frequency data (pressure, flow rate, etc.) that is a product of the smart wells provide the basis for a closed-loop, fast track updating of the dynamic reservoir models. While high frequency updating of the reservoir model remains a challenge, there are emerging technologies that can make such objectives achievable. An integrated approach that combines analytical and numerical solutions with artificial intelligence and data mining is proposed to ultimately achieve the closed-loop, fast track updating system. This study is the first step in that direction. In this work the ability of analytical solutions to calculate reservoir water saturation profiles from field water cut data are investigated. Different flow regimes and reservoir geometries are considered during this study. Diffuse, segregated and capillary influenced flow models are analyzed in both one and two dimensional water injection using a commercial numerical simulator. Different analytical formulations are applied for each flow regime in order to reproduce simulation production data. For each model a specific relative permeability relation is assigned and tuned with the aim of matching water breakthrough time and water cut history. An accurate match is achieved between water saturation profiles generated by the analytical models and the results by the reservoir simulator. The influence of simple reservoir heterogeneity on the robustness of the analytical models is studied.
Carbon Capture and Storage (CCS) has been gaining support and popularity as one of the most viable CO2 emission mitigation methods. In order to assure underground CO2 storage safety and reduce leakage risk, different CO2 Monitoring techniques must be utilized. In-zone reservoir pressure, which is transmitted by Permanent Down-hole Gauges (PDG), is a widely used monitoring parameter that can provide important indications when CO2 migration/leakage occurs. As part of a monitoring package, a Real-Time Intelligent CO2 Leakage Detection System (RT-ILDS) was developed for CO2 storage project at Citronelle Dome, Alabama. This system, which is designed based on Pattern Recognition Technology and Smart Wells, is able to identify the location and amount of the CO2 leakage at the reservoir level using real-time pressure data from PDGs. In this work, history matched reservoir simulation model (based on 11 months of actual injection/pressure data) was used for CO2 leakage modeling study. High frequency real time pressure streams were processed with a novel technique to form a new data driven RT-ILDS which was able to detect leakage characteristics in a short time(less than a day). RT- ILDS also demonstrated high precision in quantifying leakage characteristics subject to complex rate behaviors. Finally the performance of RT- ILDS was examined under different conditions as multiple well leakage, availability of additional monitoring well, uncertainty in the reservoir model, CO2 leakage through the cap rock and multi-well leakage. The objective of this study was to proof the concept and feasibility of using real time pressure data from PDGs in order to notice occurrence of leakage and identify its characteristics as location and rate in a real CO2 storage project by utilizing data mining techniques.
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.