Intelligent digital oilfield (iDOF) operations include the transfer, monitoring, visualization, analysis, and interpretation of real-time data. Enabling this process requires a significant investment to upgrade surface, subsurface, and well instrumentation and also the installation of a sophisticated infrastructure for data transmission and visualization. Once upgraded, the system then has the capability to transfer massive quantities of data, converting it into real information at the right time. The transformation of raw data into information is achieved through intelligent, automated work processes, which are referred to here as "smart flows," which assist engineers in their daily well surveillance activities, helping make them more productive and improve decision making. A major oil and gas operator in the Middle East has invested in such an infrastructure and is developing a set of smart flows for key activities and work flows for its production operations, with the ultimate goal of improved asset performance. The project includes a smart flow to monitor, diagnose, and optimize wells that include electric submersible pumps (ESP); 50% of the wells in this field use ESPs. The ESP smart flow includes leading-edge technologies, such as: variable speed drive controller, subsurface equipment and sensors, advanced diagnostics based on artificial-intelligence agents, analysis of sensors signals, and automatically identifying ESP optimum operating conditions. Using a steady-state nodal-analysis model combined with an artificial intelligent technique, the ESP smart flow is designed to provide rapid diagnostics and optimization in real time, generating actions, such as decreasing and increasing the pump frequency and choke setting. The ultimate benefit is to detect the signals that foresee unexpected well downtime and predict ESP system pump failures. The paper describes the main functionalities of the ESP smart flow as a powerful optimization tool that is capable of providing an interactive monitoring system that can assist operations personnel in managing ESP-operated wells.

Implementing asset-wide intelligent digital oilfield (iDOF) solutions, aiming to optimize oil and gas production system in an "intelligent" manner, requires integrating concepts from different disciplines, such as artificial intelligence. Neural network- (NN-) based models are a form of artificial intelligence, which is a branch of computer science that generates mathematical models that can be "trained" to determine relationships between inputs and outputs, recognize patterns, and perform reliable short-term predictions. NN models using real-time data are proven tools for short-term well production forecasting with acceptable accuracy. An oilfield is a hostile environment for even the most robust instrumentation. As a result, technical outages or anomalies can result in lost or poor quality data. Experience shows that many samples in a real-time database are frozen, missing, corrupted, or incorrect. This fact represents the biggest challenge to creating a reliable NN model. However, the models can be trained to correct or estimate missing real-time data. This paper presents a case study where nodal analysis was used to populate missing data used to train NN model, thus improving the reliability of the model. Because nodal analysis is not suitable for prediction, time-series analysis was used to assess the impact of historical events, and operational conditions were used to forecast trends. The NN trained with nodal analysis can cover a wide variability spectrum and, when trained with a time-lapse series, can predict short-term (30-day) production scenarios by changing highly correlated parameters, such as tubing head pressure (THP) or frequency (Freq). This paper describes training NNs using nodal analysis and time-series analysis to predict short-term water cut (WC or BS&W) and liquid flow rate. This technique was applied in over 20 wells with electronic submersible pumps (ESPs) and gas lifts (GLs). The NNs made robust estimates of production rate and an acceptable prediction trend for 30 days, even when confronted with flow meter instrumentation failure, lost signals, and out-of-calibration instruments. Hence, the NN served as a "virtual meter," providing instantaneous and accurate estimation of production data.

Surveillance and optimization of waterfloods in low-permeability carbonate reservoirs pose many challenges. Updating reservoir models is tedious and time-consuming, involving multiple data sources, model updates, and simulations. Technological challenges include large simulation models, waterflood complexities, and limited real-time data. Human challenges must be addressed as well, since waterflooding decisions affect multiple disciplines: reservoir engineers, production engineers, facilities engineers, IT, Operations, and asset managers. The ‘languages’ and interests of these disciplines are quite different; necessitating a workflow that satisfies the needs of all disciplines and integrates people, processes, and technology. This paper presents an innovative automated workflow to enable monitoring, diagnostics, forecasting, and optimization of waterflooding processes in days instead of weeks. This workflow seamlessly captures historical and monthly real-time data, updates simulation history, creates simulation restart prediction points, runs numerical simulations with optimization scenarios, selects the global optimum solution by scenario, and compares results so that multi-disciplinary teams can make reactive or proactive decisions to maximize short-term oil rates and long-term oil recovery, while honoring constraints on voidage replacement ratios, reservoir pressure, sweep efficiencies, production, and injection. The workflow automatically updates real-time production data in the simulator each month. A base case is run to recalculate waterflooding indicators. The process then starts a 24-month production forecast, running hundreds of scenarios under constrained optimization to achieve global optimization points. The optimizer changes control variables such as injection volumes, tubing head pressure, bottomhole pressure, and production allowable. The workflow ranks potential well decisions with important impacts on oil rate and water cut. The workflow uses an intuitive user interface incorporating the needs of multiple engineering and operations disciplines, and facilitates one common language while evaluating and optimizing waterfloods. This workflow has been implemented for a waterflood in a Middle East carbonate reservoir to help engineers evaluate the waterflood and make better, faster decisions.

Intelligent digital oilfield (iDOF) operations include the transfer, monitoring, visualization, analysis, and interpretation of real-time data. Enabling this process requires a significant investment to upgrade surface, subsurface, and well instrumentation and also the installation of a sophisticated infrastructure for data transmission and visualization. Once upgraded, the system then has the capability to transfer massive quantities of data, converting it into real information at the right time. The transformation of raw data into information is achieved through intelligent, automated work processes, which are referred to here as "smart flows," which assist engineers with key well operations and monitoring, helping make them more productive and improve decision making. A major oil and gas operator in the Middle East has invested in such an infrastructure and is developing a set of smart flows for key activities and work flows for its production operations, with the ultimate goal of improved asset performance. Well testing and production allocation are vital for identifying and resolving problem wells and for identifying candidate wells to optimize production and maximize a field's potential and asset value. But with traditional tools and methods, this work is time-consuming and requires many low-value tasks (data gathering, cleaning, etc.) leaving little time for the high-value analysis work. To expedite, prioritize, and simplify well testing and related analyses, the Well Performance Evaluation (WPE) smart flow has been developed. This paper presents and describes the WPE, how it works, and how it is delivering value today. WPE features advanced data visualization that includes interactive charts, enabling production engineers to execute well testing daily, select the most critical wells for testing based on an expert system, verify well test data with advanced data filtering and qualification technology, execute and fit updated nodal analysis models on demand, in seconds, to recommend the optimal well output, and provide recommended actions to operations personnel to increase production.

This paper outlines the visualization and collaboration attributes of an automated workflow that integrates the computerassisted history matching (AHM), quantification of inherent model uncertainty, and optimization on production-forecast decisions. The workflow belongs to the group of smart flows for integrated asset management installed at the North Kuwait Integrated Digital Field (KwIDF) collaboration center.The workflow is facilitated through four interactive user interfaces: Dashboard: displays history-match indices for water cut and visualizes maps of permeability, porosity, water and oil saturation, reservoir quality index, and reservoir pressure. Field and Well History Matching: displays well-level history matching and forecasting results filtered by water cut, bottomhole pressure (BHP), and liquid rate and visualizes the distributions of corresponding errors per simulated scenario. Dynamic Ranking: categorizes and ranks trends of forecasted oil recovery for history-matched models using multidimensional scaling and clustering techniques and visualizes identified P10, P50, and P90 models. Property Comparison: displays permeability maps for prior and history-matched models to identify the regions of improvement in terms of reservoir heterogeneity. Additionally, streamline trajectories colored by the time-of-flight provide excellent visualization of reservoir connectivity.The workflow was applied in the pilot area of a major Middle East carbonate reservoir in North Kuwait and performs complex history matching and production forecasting. The simulation model combines 49 wells in 5 waterflood patterns to match 50 years of oil production, 12 years of water injection, and 8 years of forecasting.The differentiator of this workflow is that it is unique in direct interfacing between the geomodeling application and reservoir simulator and in updating of high-resolution models with no upscaling. It delivers an optimized reservoir model for waterflood management and automatically updates the model quarterly with production, completion, and geological information. This allows engineers to improve the reservoir characterization and identify the areas that require more data capture.