Editorial for the special issue: Artificial Intelligence and Data Mining

Editorial for the special issue: Artificial Intelligence and Data Mining

Journal of Natural Gas Science and Engineering 3 (2011) 665–666 Contents lists available at SciVerse ScienceDirect Journal of Natural Gas Science an...

74KB Sizes 1 Downloads 92 Views

Journal of Natural Gas Science and Engineering 3 (2011) 665–666

Contents lists available at SciVerse ScienceDirect

Journal of Natural Gas Science and Engineering journal homepage: www.elsevier.com/locate/jngse

Editorial for the special issue: Artificial Intelligence and Data Mining

Application of Artificial Intelligence and Data Mining in the Exploration and Production industry has come a long way since the first articles started appearing in SPE (Society of Petroleum Engineers) conferences in early 1990s. We are happy to report that a Technical Section at SPE is now dedicated to this technology and its advancement in the E&P industry. The Technical Section is called Data to Action (D2A) and it was inaugurated in SPE’s annual technical conference in Denver on October 30, 2011. In this special issue of Journal of Natural Gas Science and Engineering a series of technical articles are presented that provide a snap shot of where our industry stands as far as application of Artificial Intelligence and Data Mining is concerned. This special issue includes eight articles that cover a wide variety of topics from reservoir simulation and modeling hydraulic fracturing and planning. In “Development of universal proxy models for screening and optimization of cyclic pressure pulsing in naturally fractured reservoirs ” Emre Artun discusses a high-performance screening/optimization workflow to narrow the ranges of possible scenarios to be modeled using conventional simulation for the cyclic pressure pulsing process. The workflow starts with creating a knowledge base with simulations for a wide range reservoir characteristics and design schemes. Neural-network based proxy models are trained with the knowledge base. The genetic algorithm is used to search for the optimum design scenario by evaluating the objective function via proxy model. Proxy models predicted critical performance indicators such as cumulative oil production, and oil flow rates within high levels of accuracy. In “Application of Case-Based Reasoning for Well Fracturing Planning and Execution ” Andrei Popa presents a soft computing method to deal with uncertainty, approximate reasoning and exploitation of the domain knowledge. This paper provides a general framework of case-base reasoning along with a review of the four-step cycle that characterizes the technology (retrieve, reuse, revise and retrain), followed by a specific application to well fracture treatment design, planning and execution. The proposed methodology extracts the relevant historical information recorded during field job execution, utilizes a rule-based system to make adaptations, and then suggests the most appropriate solution for new well fracturing candidates. In “Reservoir Simulation and Modeling Based on Pattern Recognition” Shahab D. Mohaghegh presents a new class of reservoir simulation models that are developed based on the pattern recognition technologies collectively known as Artificial Intelligence and Data Mining (AI&DM). The workflows developed based on this new class of reservoir simulation and modeling tools break new ground 1875-5100/$ – see front matter Ó 2011 Published by Elsevier B.V. doi:10.1016/j.jngse.2011.11.001

in modeling fluid flow through porous media by providing a completely new and different angle on reservoir simulation and modeling. The philosophy behind this modeling approach and its major commonalities and differences with numerical and analytical models are explored and two different categories of such models are explained through case studies. In “Fuzzy Upscaling in Reservoir Simulation: An Improved Alternative to Conventional Techniques” Vida Gholami presents development of a new upscaling methodology based on fuzzy set theory. She concludes that Fuzzy rock typing is a new upscaling methodology where the inherent uncertainties and vagueness associated with rock typing procedure are accounted for during the development of the geological model that is used in the dynamic modeling. In “Computational Intelligence for Deep-water Reservoir Environments Interpretation” Tina Yu proposes a deposition-based stratigraphic interpretation framework for deepwater reservoir characterization. This interpretation process is labor intensive and can produce different results depending on the stratigrapher who performs the analysis. To relieve stratigrapher’s workload and to produce more consistent results, Tina has developed a novel methodology to automate this process using various computational intelligence techniques. In “Validation of Production Data by using an AI-Based Classification Methodology; A Case in the Gulf of Mexico” Olivia Patricia Quiñónez-Gámez applies an AI-based methodology for identification of contaminated data to determine the quality of a set of production data of an oil field. To achieve this objective, fuzzy classification algorithm, neural network modeling is combined in an iterative process. The methodology was applied to a real case (offshore field en México) and the results are presented. In “An implementation of a Distributed Artificial Intelligence Architecture to the Integrated Production Management” Cesar E. Bravo proposes implementation of distributed artificial intelligence architecture, designed for the automated production management. The architecture comprises a standardized schema to access information sources, a production ontological framework and an intelligent workflow mechanism based on multi-agent systems and electronic institution. He them presents an oil production management case study in order to demonstrate the applicability of the proposed architecture. And finally, in “Ensemble methods for process monitoring in oil and gas industry operations” Roar Nybo a method to reduce uncertainty and increase confidence while aggregating the opinion of different experts. When the expert is a computer program, such aggregation is often referred to as an ensemble approach. In his

666

Editorial / Journal of Natural Gas Science and Engineering 3 (2011) 665–666

paper, Roar discusses this trend and develops an ensemble system for predicting the bottom-hole pressure during a managed pressure drilling operation. We see this special issue as a small step toward moving this technology into the mainstream of exploration and production industry. We believe the day when this technology is mature

enough to require its own independent journal in the E&P is fast approaching. Shahab D. Mohaghegh, Intelligent Solutions, Inc. and West Virginia University Rodolfo Gabriel Camacho Velazquez, PEMEX Karamat Behbahani, NIOC