Semantic Web Technologies for Smart-Oilfield Applications

Abstract

This article, written by Assistant Technology Editor Karen Bybee, contains highlights of paper SPE 112267, "Semantic Web Technologies for Smart Oil Field Applications," by Ramakrishna Soma, Amol Bakshi, and Viktor Prasanna, University of Southern California, and Will DaSie, SPE, and Birlie Bourgeois, Chevron Corporation, originally prepared for the 2008 SPE Intelligent Energy Conference and Exhibition, Amsterdam, 25-27 February. The paper has not been peer reviewed. In model-based oilfield operations, engineers rely on simulations to make important operational decisions on a daily basis. Generally, an engineer is an expert in only one aspect of oilfield modeling and trained to use only a few tools. Accessing information captured in models that are not in the area of expertise of the engineer and are created by different processes and people is not easy. The full-length paper examines the application of semantic Web technologies to address the problem of information represented differently across models. Introduction The work described in the full-length paper is part of the Integrated Asset Management (IAM) project at the Chevron-funded Center for Interactive Smart Oilfield Technologies at the University of Southern California. The current focus of the IAM project is to enable model-driven reservoir management. Consider a typical oilfield operation for a greenfield. Because little or no performance-related data for the field exist, the production engineer must rely on simulations for making the initial set of asset-development decisions. Different simulation models of the oil field including Earth, network, reservoir, and integrated-system (coupled)-simulation models are created. These simulation models are built and used at different times and locations, and by team members of different disciplines. A particular member of the team typically is an expert in a particular modeling and simulation technology and is familiar with certain software toolkits in that domain. This means that models, workflows, and results created with other software tools in other domains are not usable and accessible by that expert. As a result, the insights and understanding of a team member in one role are not used fully by someone in another role. These simulation models can be modified constantly as new data are produced in the oil field and interpreted by one or more members of the asset team. In this situation, changes made to the model(s) by one team member should be communicated immediately to other team members who may be using that model as the basis of scenario planning and forecasting, or who may need to modify their own models to match the updates.