"Reducing the costs and uncertainty of Deepwater Developments: Using oilfield big data to predict reservoir, field, and well performance in the deepwater fields”

Development of assets in new frontiers can be quite costly, especially in deep-water and ultra-deep waters. These developments have many uncertainties, and each has an associated risk to both operations and project economics. Leveraging the fact that a significant amount of information has been (and continues to be) gathered in public and/or private domains for many of these assets/wells, Advantek built a data-mining framework for establishing whether reservoir and production performance could have been accurately predicted during various stages of deep-water development (“Pre-Discovery,” to “Exploration,” through to “Mature Fields”). The final results of this work were incorporated into a selection/prediction software tool and database for decision support for Advantek's E&P clients. The work helps establish priority for data acquisition and the value of that data values throughout asset development, and resulted in one of the largest privately held databases of GoM well information. Subsequently, rigorous data mining techniques were used to determine the most prominent attributes governing the performance of reservoirs at each stage of development.