In the S-Field operations office, a daily battle ensues in the quest to increase production and maximize profitsfrom waterflooding. One of the main control mechanisms applied to optimize the waterflooded reservoirs isby controlling the water injection and pumping rates of producers to balance patterns, maximize sweep, andmaintain reservoir pressure. The reservoir surveillance team has been using a simple spreadsheet analyticalapproach that was quite limiting as the number of injection patterns increased, and the flood matured, leadingto a water breakthrough. There was a need for a more sophisticated approach that could leverage artificialintelligence (AI) technology, especially since the entire asset was undergoing significant digitalization ofits operations.

This paper presents various innovations in bringing real applications of AI for waterflood management.This includes innovations in business processes, application of design thinking methodology, agiledevelopment, and AI. The AI waterflood management solution combines cloud technologies, bigdata processing, data analytics, machine learning algorithms, robotics, sensors and monitoring system,automation, edge gateways, and augmented and virtual reality (AR/VR).

Design thinking principles and a human-centric approach within an agile innovation framework wereutilized for rapid prototyping and deployment. A waterflood management framework that addressed thebusiness's operational, tactical, and strategic aspects created the backdrop for designing the solutionarchitecture. New injector-producer modeling techniques that leveraged AI and were fit-for-purpose forreservoir surveillance and production engineers were prototyped. An interactive pattern flood managementtool, adapted from streamline simulation-based waterflood analysis methods, was developed for injectionpattern analysis and intelligent optimization workflow.

Field pilot testing for over a year proved that the prototype could reliably detect injector-productioninteractions and recommend operating set points in relevant time. Reduced time to decision, improvedanalysis efficiency and reliability of short-term forecasts, reduced field visits and health-safety-environment(HSE) exposure, and finally ease-of-use has been experienced. The learnings from this project are beingleveraged to develop a deployable solution and move the needle toward autonomous waterflood operations.