Automated Reservoir Management Workflows to Identify Candidates and Rank Opportunities for Production Enhancement and Cost Optimization in a Giant Field in Offshore Abu Dhabi

Abstract

As the field matures and overall field production decline, an accelerated and advanced selection of existing wells for workovers and sidetracks would be critical to meet with the increasing demand for production. Traditionally, an intensive effort is required to identify the right candidates and to ensure the technical and economic success of well interventions, infill-drilling locations and sidetrack locations. An advanced workflow is developed to automate the repetitive and less added value tasks such as data gathering and validation. The data set included historical production performance, static and dynamic reservoir and fluid properties, events and issues encountered within the evaluated wells and regions. The proposed solution allowed an integrated assessment of production enhancement opportunities through various consistent analytic computations, as well as machine learning techniques including Bayesian networks and time-series forecasting models. The automated process generates a comprehensive list of future well interventions including sidetrack candidates, infill-drilling locations and behind casing opportunities with an advanced scoring system and several technical (production performance and reserves) and financial KPIs (i.e. net present value and unit technical cost). Several dashboards built and adjusted with the involvement of various company departments. Lastly, highly ranked opportunities are incorporated into the business plan in accordance to field development targets as well as the availability technical resources (rigs, materials, well availability). The developed solution was tested and validated in a giant mature carbonate field with over 700 well strings in Offshore Abu Dhabi. The solution identified 20 times more feasible opportunities than the typical multidisciplinary team review in 75% less time duration. The automated workflows considered re-evaluating and selecting prime candidates with a reduced risk of failure, therefore improving the technical and economic value by 34%. The workflows are scheduled on daily basis giving a time-dependent assessment and expert monitoring system, which can also notify the operator when problems encountered. Instead of computationally heavy traditional numerical simulation models, the assessment of a large number of well count can be done within hours instead of months. The combination of physics and machine learning based models lead to the development of automated workflows to rank and determine the best candidates via a successful cost optimization and production enhancement.