Abstract
This paper presents a unique E&P knowledge management system which has been widely accepted and applied by upstream petroleum industry. This knowledge management system started in mid-1990s and consists of standard static and dynamic knowledge base, comprehensive evaluation reports, and fit-for-purpose analytics tools applicable to the entire E&P lifecycle. Emphasis is placed on illustrating the breadth and depth of the E&P knowledge and advanced analytics in terms of their capturing and applications in field development and production.
This knowledge base consists of >1600 reservoirs from around the world, each containing ~400 reservoir-level static parameters and a set of dynamic performance data. The static parameter covers reservoir characteristics, fluid properties, original in-place volume, EUR, recovery factor, production-related data (such as well spacing, well pattern, well EUR et al.), reservoir management practices, and key IORs/EORs and their incremental recovery. The knowledge extraction process involves collecting, reviewing, and synthesizing geologic, reservoir engineering and production data on a representative sample of global reservoirs. The reliable, coherent, high-quality knowledge base provides a foundation for the development of primary recovery index using supervised machine learning. Insights and intelligence derived from this knowledge base are critical to decision-making for both initial or early field development and production stages. The development application includes, but not limited to: (1) quantifying in-place volume, EUR, and recovery factor; (2) characterizing possible production performance and uncertainties and obtaining a conceptual production performance curve; (3) validating development plan options; and (4) benchmarking reservoir simulation results. The production application includes: (1) benchmarking production performance; (2) identifying upside potential and improved oil recovery opportunities; (3) finding best practices and lessons learned in reservoir management and secondary recovery practice; and (4) screening EOR methods, calibrating potential incremental recovery and characterizing EOR process performance.
Lack of knowledge standardization and absence of coherence of data from various data sources are the main challenges facing industry's data-driven application. The knowledge management system presented in this study provides the most reliable knowledge base, advanced analytics tools, and practical application workflow to help the upstream industry become more efficient in applying collective human intelligence.
A Framework for a Knowledge Management System in a Cloud Computing Environment Using a Knowledge Engineering Approach
