Rapid and Efficient Waterflood Optimization Using Augmented AI Approach in a Complex Offshore Field

Waterfloods are amongst the most widely implemented methods for oil field development. Despite their vast implementation, operational bottlenecks such as lack of surveillance and optimization tools to guide fast paced decisions render most of these sub-optimal. This paper presents a novel machine-learning, reduced-physics approach to optimize an exceptionally complex off-shore waterflood in the Gulf of Suez. Leveraging a hybrid data-driven and physics approach, the water flooding scheme in Nezzezat reservoir was optimized to improve reservoir voidage replacement, increase oil production, and reduce water production by identifying potential in wells. As a by-product of the study, a better understanding of the complex fault system was also achieved. Including the geological understanding and its uncertainty is one of the key elements that must be preserved. All geological attributes, along with production rates are used to solve for pressure and inter-well communication. This is later supplemented by machine-learning algorithm to solve for the fractional flow of inter-well connections. Combining the inter-well connectivity and fractional flow, an optimization was performed to reach the best possible conditions for oil gains and water-cut reduction. A global optimization is possible thanks to the low computational demand of this approach, as thousands to millions of realizations must be run to reach the best solution while satisfying all constraints. This is all done in a fraction of the time it takes to run a traditional reservoir simulation. For the present case, the paper will present the underlying physics and data-driven algorithms, along with the blind tests performed to validate the results. In addition to the method's inner workings, the paper will focus more on the results to guide operational decisions. This is inclusive of all the complex constraints of an offshore field, as well as the best reservoir management practices, when reaching optimal production and injection rates for each well. An increase in production was achieved with some reduction in water-cut, while honoring well and platform level limitations. While these represent the gains for a particular month, optimization scenarios can be run weekly or monthly to capture the dynamic nature of the problem and any operational limitations that might arise. The ability to update the models and run optimization scenarios effortlessly allows pro-active operational decisions to maximize the value of the asset. The approach followed in this paper solves for the critical physics of the problem and supplements the remaining with machine learning algorithms. This novel and extremely practical approach facilitate the decision making to operate the field optimally.