Optimizing Large Scale Well Portfolios in Three Giant Middle Eastern Fields: A Data Driven Approach to Enhancing Production and Efficiency Through Proactive Opportunity Screening and Intervention Planning

N. Reddicharla, K. Alnaqbi, A. Tawheed, K. S. Almatrooshi, M. Taha, S. Ramatullayev

Abstract

The upstream industry has spent the last decade instrumenting its wells and facilities, and the result is a steady stream of production, pressure, and surveillance data that grows faster than any team can read it. In large mature carbonate assets this creates a strange imbalance. The data needed to spot the next good intervention almost always exists somewhere, yet the process of finding, screening, and maturing that opportunity still depends on a handful of experienced engineers working through wells one at a time. Reviews that should take days often stretch into weeks, and by the time a candidate is agreed the production it was meant to protect has already been deferred. The scale only sharpens the point. A giant onshore field can hold a large and constantly shifting inventory of candidates, and the subset that is genuinely worth acting on this month is small, moves around, and rarely announces itself. Well Portfolio Optimization, referred to here as WPO, was built to close that gap. It is an automated advisory system that continuously scans the full well stock, both active and inactive, and surfaces the interventions most likely to add value. Rather than replacing the reservoir or production engineer, it does the heavy lifting of screening and ranking so that scarce petrotechnical effort is spent on judgement rather than on data gathering. The system draws on subsurface data, production history, and engineering rules, and combines them inside a single framework that prioritizes candidates by production potential, economics, and probability of success. This paper describes the thinking behind WPO, the elements that make up the solution, the workflows that run on top of it, and how a data driven screening philosophy differs from the physics driven studies engineers are used to. It also shares early field experience from deployment across three giant onshore fields, and it is candid about where the approach still needs a human in the loop.

Source: semanticscholar

Read the AI summary and key takeaways for traders on WOBR Quant Research.