Data-Driven Well Candidate Recognition Solution. Case Study in a Digital Oil Field in Abu Dhabi

Abstract

Abstract Well Candidate Recognition (WCR) data analytics solution was developed to expedite the process of identifying unhealthy wells that may require rig/rigless interventions based on data integration, automation, and advanced data-driven models. The solution expedites well performance review process to pinpoint candidates for stimulation, N2 lift, Gas lift conversion, Water/Gas shutoff, etc. It provides a flexible visualization platform to highlight hidden well performance insight, prioritizing well intervention activities. Before the solution was in place, a time-consuming well performance review's process was performed well by well bases. All petroleum engineers were involved in the process that takes months to compile a solid list of opportunities for production enhancement. In addition, each engineer utilized their own process to assess well performance using partially company best recommended practices. It was notice that most expensive field activities were the ones with lowest success performance indicators, pushing the asset to review, standardize and automate the process of well intervention candidate's selection. The solution enforced best reservoir management practices for reservoir/well surveillance and optimization, identifying opportunities to align reservoir management goals with short term production optimization and sustainable reservoir development, adopting new data driven technologies for improving reservoir recovery/management for cost rationalization. The implementation of this solution permitted to identify 20 hidden opportunities for production improvement to support production target achievement with an actual gain of 20MBOPD. On the other hand, all well interventions were successful executed with and avg. success factor of 103%, exceeding in most cases the expected gain, compared with previous years avg. success factor of 32%. The substantial increment in the success factor of the most expensive field activities had a favorable impact over asset UTC. WCR's Dashboards leveraged legacy data, models and smart field capabilities, using advance visualization feature to identifying unhealthy wells, that may require rig/rigless intervention based on best reservoir management practices, providing an efficient/automated well performance review saving 70% of the petroleum engineer's time. Opportunities are assessed and ranked based on expected gain via intelligent action tracking system to ensure action completion and production contribution, perusing higher recovery while delivering consistent results. It also offers: GIS Map capability to identify localized poor properties or issues; pressure data and automated well model update to identify high drawdown (Skin), reservoir pressure decline and actual well capacity with automated peer comparison to support production optimization workflow; ability for quick Identification of erroneous data loaded in official data sources; well intervention dashboard to assess success of actual/previous Rig/Rigless jobs.