You are being redirected because this document is part of your ASTM Compass® subscription.
This document is part of your ASTM Compass® subscription.
Oil Field Data Mining
For RefWorks, EndNote, ProCite, Reference Manager, Zoteo, and many others.
For Microsoft Word
Today, large volumes of data are collected in the oil and gas industry. Data collection starts even before drilling for oil and gas. Seismic survey used to be the process during which the largest volume of data in the exploration and production industry is collected. With the invention and continuous use of sensors and such processes as measurement while drilling, logging while drilling, and permanent downhole gauges for smart fields, large volumes of data are collected and stored during drilling and operation of the wells. The large percentage of the data that currently is collected in the oil field is never used for decision making. Oil field data mining is set to change this. Oil field data mining provides the means for making the most of the investment that has gone into collection and storage of the data. Oil field data mining is a set of tools and technologies used to extract information and knowledge from the collected data in the exploration and production industry. The main characteristics of oil field data mining is its use of data-driven solutions as opposed to deterministic approaches that have dominated the exploration and production industry for the past five decades. One of the most significant attributes of oil field data mining that distinguishes it from conventional statistical approaches (that recently have became popular) is its use of artificial intelligence. Artificial intelligence has been called by different names. It has been referred to as “virtual intelligence,” “computational intelligence,” and “soft computing.” Among these names, “artificial intelligence” is now used most often as an umbrella term. Artificial intelligence may be defined as a collection of analytic tools that attempts to imitate life. Artificial intelligence techniques exhibit an ability to learn and deal with new situations. Artificial neural networks, evolutionary programming, and fuzzy logic are among the technologies that are classified as artificial intelligence. These techniques possess one or more attributes of “reason,” such as generalization, discovery, association, and abstraction. In the past decade, artificial intelligence has matured to include a set of analytic tools that facilitate solving problems that were previously difficult or impossible to solve. The current trend is the integration of these tools as well as the use conventional statistics and deterministic solutions to build sophisticated systems that can solve challenging problems. Artificial intelligence is used in areas such as medical diagnosis, credit card fraud detection, bank loan approval, smart household appliances, subway systems, automatic transmissions, financial portfolio management, robot navigation systems, and many more. In the oil and gas industry, these tools have been used to solve problems related to pressure transient analysis, well log interpretation, reservoir characterization, and candidate well selection for stimulation, among other things.
data mining, artificial intelligence, neural networks, seismic, reservoir characterization
Mohaghegh, Shahab D.
West Virginia University, Morgantown, WV
Middle East Technical University, Mersin,