Asset management success is accomplished when the integrated production system is operating close to its intended potential. Continuous awareness of wells and facility conditions are key factor in the realization of designed capacity. In contrast, unknown status and conditions can severely limit production capacity. The rise of instrumentation technologies over the last four decades have created new opportunities to understand well and reservoir behavior. However, despite of being proved as a cost-effective surveillance initiative, remote monitoring is still not adopted in over 60% of oil and gas fields around the world. Understanding the value of data through machine learning techniques is the basis for establishing a robust surveillance strategy. The objective of this paper is to develop a data-driven approach, enabled by Artificial Intelligence (AI) methodologies including machine learning (ML), to find optimal operating envelope for gas-lift wells. The process involves building ML models for generating instantaneous predictions of multiphase flow rates and other quantities of interest, such as GOR, WCT, using real-time sensor data at the surface, historical performance, and sporadic test data. Additionally, forecasting models were developed for generating short-term (30 days) forecast of cumulative oil, water, gas, and liquid production, multiphase flow rates, WCT, GOR, and reservoir pressure. Using time-series forecasting models, a sensitivity analysis was performed to generate short-term well response for a selected number of combinations of choke settings, and gas injection rates. Sensitivity analysis provides 2D maps of well response highlight an operating envelope, which are proposed to be combined with physical and operational constraints to arrive at optimal operating conditions, which may effortlessly add 2.5% net profit from optimum gas-lift alocation. The results of this work show encouraging results, and demonstrate value that AI-enabled methodologies can provide in instrumented wells by enabling automated workflows for virtual metering, production allocation, short-term production forecasting, and deriving optimal operating conditions. The developed AI methodology has tremendous potential of integration in an end-to-end workflow of autonomous well control by utilizing available data to produce easy to update ML models, with little to no human intervention.

Production planning and performance management imply diverse challenges, mainly when dealing at corporate level in an integrated operating company. Production forecast considers technical capacities, available capacities, and operationally agreed target capacities. Such complex process may hinder taking advantage of market opportunities at the right time. Proactive scenario management and information visibility across the organization are key for success. This paper intends to share the lessons learned while rolling out a countrywide integrated capacity model solution supporting corporate production planning and performance management. The rollout processes aimed at digitizing the monthly and yearly production forecasting. In addition, these processes shall enable formulating proactive scenarios for avoiding shortfalls, maximizing gas throughput, production ramp up, and minimizing operating cost from existing capacity. Abu Dhabi's Integrated Capacity Model is an integrated production planning and optimization system relying on a large-scale subsurface-to-surface integrated asset model system; in this paper, we focus on the incremental progress of the challenges derived from the various rollout efforts. The rollout of such a complex solution relies on basic tenets for managing the change across a large organization. The first tactic is about continuous stakeholder engagement through value demonstration and capabilities building. Engagement is achieved by continuously providing information about proactive shortfall and opportunity identification within the installed asset capacity. Monthly asset reviews provide the basis for user interaction and initiate the basis for establishing ad-hoc production maximization scenarios. Establishing a data governance and performance metrics were also key for embedding the solution in the business processes. The solution delivers tangible and intangible value. From the tangible point of view, it contributes to production efficiency gains by compensating during specific proactively identified shortfalls and after-the-fact events. As a result, our solution has been instrumental in deriving cost reduction scenarios and profitability gains due to optimum GOR management. In addition, the system use has reported various intangible gains in terms of better data utilization, enhanced corporate database quality and reduced overall human load in managing production capacity. The solution described in the paper implements a simpler way the production planning and performance management at corporate level in a large integrated operating company. The in-house developed tool and its implementation is a novel approach in terms of integration, complexity, and practical application to the fields in Abu Dhabi.

Petroleum Engineers are usually responsible for 50-200 wells. The wells in highly instrumented fields generate 10-20 measurements every few seconds. This makes it difficult to be on top of every well, every day. This challenge carries a significant opportunity cost, therefore the surveillance process requires automation by implementing surveillance-by-exception. Faster identification of problems is great, but not enough unless the required activities are executed in a timely manner. The ability to execute quickly and safely requires a well-structured coordination effort between the different disciplines involved in field operations. In line with ADNOC Digital Transformation strategy, the solution described in this paper intends to couple surveillance by exception (a Petroleum Engineering workflow) with field operations execution (a multi-disciplinary set of workflows in the field). The integration is achieved by creating a simple yet robust action tracking system, and feeding it automatically with new opportunities, so that it is kept up to date. Automatic diagnosis becomes opportunities. Opportunities become activities. Activities are assigned, executed and closed. All activities are tracked on a high level, which provides insights and visibility to all parties on who is doing what, when and how to close the opportunity. The surveillance by exception engine consumes real time measurements from the historian. It then runs a set of soft sensors using full physics, reduced order models, proxy and data driven machine learning models, which utilize most of the measurements. The measured and calculated values are then fed to an expert system, which automatically diagnoses the wells and creates tickets with recommendations to the production engineer. The engineer reviews the ticket and forwards to field operations for execution. The log of activities enables a direct measure of operational effectiveness. This paper describes the philosophy of the system, how it works, lessons learned and the results of implementation across 6 oilfields and 600+ wells in Abu Dhabi.