The effectiveness of secondary and tertiary recovery projects depends heavily on the operator's understanding of the fluid flow characteristics within the reservoir. 3D geo-cellular models and finite element/difference-based simulators may be used to investigate reservoir dynamics, but the approach generally entails a computationally expensive and time-consuming workflow. This paper presents a workflow that integrates rapid analytical method and data-analytics technique to quickly analyze fluid flow and reservoir characteristics for producing near "real-time" results. This fast-track workflow guides reservoir operations including injection fluid allocation, well performance monitoring, surveillance, and optimization, and delivers solutions to the operator using a website application on a cloud-based environment. This web-based system employs a continuity governing equation (Capacitance Resistance Modelling, CRM) to analyze inter-well communication using only injection and production data. The analytic initially matches production history to determine a potential time response between injectors and producers, and simultaneously calculates the connectivity between each pair of wells. Based on the inter-well relationships described by the connectivity network, the workflow facilitates what-if scenarios. This workflow is suitable to study the impact of different injection plans, constraints, and events on production estimation, performance monitoring, anomaly alerts, flood breakthrough, injection fluid supply, and equipment constraints. The system also allows automatic injection re-design based on different number of injection wells to guide injection allocation and drainage volume management for flood optimization solutions. A field located in the Midland basin was analyzed to optimize flood recovery efficiency and apply surveillance assistance. The unit consists of 11 injectors and 22 producers. After optimization, a solution delivering a 30% incremental oil production over an 18-month period was derived. The analysis also predicted several instances of early water breakthrough and high water cut, and subsequent mitigation options. This system couples established waterflood analytics, CRM and modern data-analytics, with a web-based deliverable to provide operators with near "real-time" surveillance and operational optimizations.
Liu, Guoxiang (Baker Hughes a GE Company) | Stephenson, Hayley (Baker Hughes a GE Company) | Shahkarami, Alireza (Baker Hughes a GE Company) | Murrell, Glen (Baker Hughes a GE Company) | Klenner, Robert (Energy & Environmental Research Center, University of North Dakota) | Iyer, Naresh (GE Global Research) | Barr, Brian (GE Global Research) | Virani, Nurali (GE Global Research)
Optimization problems, such as optimal well-spacing or completion design, can be resolved rapidly via surrogate proxy models, and these models can be built using either data-based or physics-based methods. Each approach has its strengths and weaknesses with respect to management of uncertainty, data quality or validation. This paper explores how data- and physics-based proxy models can be used together to create a workflow that combines the strengths of each approach and delivers an improved representation of the overall system. This paper presents use cases that display reduced simulation computational costs and/or reduced uncertainty in the outcomes of the models. A Bayesian calibration technique is used to improve predictability by combining numerical simulations with data regressions. Discrepancies between observations and surrogate outcomes are then observed to calibrate the model and improve the prediction quality and further reduce uncertainty. Furthermore, Gaussian Process Regression is used to locate global minima/maxima, with a minimal number of samples. To demonstrate the methodology, a reservoir model involving two wells in a drill space unit (DSU) in the Bakken Formation was constructed using publicly available data. This reservoir model was tuned by history matching the production data for the two wells. A data-based regression model was constructed based on machine learning technologies using the same dataset. Both models were coupled in a system to build a hybrid model to test the proposed process of data and physics coupling for completion optimization and uncertainty reduction. Subsequently, Gaussian Process Model was used to explore optimization scenarios outside of the data region of confidence and to exploit the hybrid model to further reduce uncertainty and prediction. Overall, both the computation time to identify optimal completion scenarios and uncertainty were reduced. This technique creates a robust framework to improve operational efficiency and drive completion optimization in an optimal timeframe. The hybrid modeling workflow has also been piloted in other applications such as completion design, well placement and optimization, parent-child well interference analysis, and well performance analysis.
Klenner, Rob (Baker Hughes a GE Company) | Liu, Guoxiang (Baker Hughes a GE Company) | Stephenson, Hayley (Baker Hughes a GE Company) | Murrell, Glen (Baker Hughes a GE Company) | Iyer, Naresh (GE Global Research) | Virani, Nurali (GE Global Research) | Charuvaka, Anveshi (GE Global Research)
Frac hits are a form of fracture-driven interference (FDI) that occur when newly drilled wells communicate with existing wells during completion, and which may negatively or positively affect production. An analytics and machine-learning approach is presented to characterize and aid understanding of the root causes of frac hits. The approach was applied to a field data set and indicated that frac hits can be quantitatively attributed to operational or subsurface parameters such as spacing or depletion. The novel approach analyzed a 10-well pad comprising two ‘parent’ producers and eight ‘child’ infills. The analysis included the following data types: microseismic, completion, surface and bottomhole pressure, tracers, production, and petrophysical logs. The method followed a three-step process: 1) use analytics to assess interference during the hydraulic fracturing and during production, 2) catalogue or extract feature engineering attributes for each stage (offset distance, petrophysics, completion, and depletion) and 3) apply machine-learning techniques to identify which attributes (operations or subsurface) are significant in the causation and/or enhancement of inter-well communication. Information fusion with multi-modal data was also used to determine the probability of well-to-well communication. The data fusion technique integrated multiple sensor data to obtain a lower detection error probability and a higher reliability by using data from multiple sources. The results showed that the infill wells completed in closest proximity to the depleted parents exhibit strong communication. The machine-learning classification creates rules that enable better understanding of control variables to improve operational efficiency. Furthermore, the methodology lends a framework that enables the development of visualization, continuous learning, and real-time application to mitigate communication during completions.
Sorensen, James A. (Energy & Environmental Research Center) | Braunberger, Jason R. (Energy & Environmental Research Center) | Liu, Guoxiang (Energy & Environmental Research Center) | Smith, Steven A. (Energy & Environmental Research Center) | Hawthorne, Steven A. (Energy & Environmental Research Center) | Steadman, Edward N. (Energy & Environmental Research Center) | Harju, John A. (Energy & Environmental Research Center)
The Bakken petroleum system is an unconventional oil resource with over 300 billion barrels (Bbbl) of oil in place. However, primary recovery is typically below 10%. To improve Bakken recovery factors, many companies are considering the use of carbon dioxide (CO2) for enhanced oil recovery (EOR). Since 2012, a research program to evaluate the potential for CO2-based EOR in the Bakken and attendant storage of CO2 for greenhouse gas emission mitigation has been conducted by the Energy & Environmental Research Center (EERC) with broad-based financial support from producers, service companies, government organizations, and CO2 suppliers. The ultimate goal of the program is to provide stakeholders with new knowledge that can be applied toward the design and execution of a pilot injection and production test in a Bakken reservoir. From 2012 to 2014, program activities were conducted on samples of key Bakken lithofacies, including the shales, from several wells. These resulted in the generation of reservoir characterization data (e.g., core analyses, well logs, oil analyses, etc.) and laboratory experimental data on CO2 permeation and hydrocarbon mobility. Detailed evaluations of porosity and permeability, including naturally occurring microfractures that will serve as key pathways for CO2 migration, were conducted using several techniques, including focused ion beam scanning electron microscopy, dual-energy x-ray computerized tomography (CT) and micro-CT scanning, ultraviolet fluorescence, and standard optical microscopy. Data generated from laboratory-scale CO2 penetration and hydrocarbon extraction experiments indicate that diffusion is a primary mechanism driving fluid mobility. Fluid mobility rates within the matrix were also quantified for each key lithofacies. The characterization and experimental data were incorporated into modeling efforts, including simulations of a variety of injection and production schemes. The best-case simulation results showed over 50% improvement in oil production. While the production response was predicted to be delayed compared to EOR in a conventional reservoir, patience may be rewarded by substantial increases in the estimated ultimate recoveries of Bakken wells. Application of the findings to the U.S. Department of Energy methodology for estimating CO2 EOR and storage capacity suggests that 4 Bbbl to 7 Bbbl of incremental oil could be produced from the Bakken, resulting in a net storage of 1.9 to 3.2 billion tons of CO2.