A Rough Set Based Rule Induction Approach to Geoscience Data

Abstract

Characterization and evaluation of (oil and gas) reservoirs is typically achieved using a combination of seismic and well data. It is therefore critical that the two data types are well calibrated to correct and account for the fact that seismic data are measured at a scale of tens of meters while well data at a scale of tens of centimeters. In addition, seismic data can be poorly processed; some well logs can be damaged, affected by mud filtrate invasion or completely missing. This research proposes an approach based on rough set theory for generating significant rules from a not consistent information system that consists of the preprocessed seismic and well log data collected from geological data using stratified random sampling method. It is often that Geosciences’ researches encountering inexact, uncertain, or vague data. Rough Set Theory (RST), originally put forward by Zdzislaw I. Pawlak, is a tool for dealing with uncertainty and vagueness. RST is very effective to address data mining tasks like rule extraction, clustering and classification. In RST the available data are used for performing the computations. RST works by utilizing the granularity structure of the data. Applying the RST on the data it generates a set of significant rules. These rules are likely to be supportive to the Geoscientists around the world to know the data behavior, which will enable them to know the dependency of the petro-physical properties obtained from well log and elastic properties which can be derived from seismic attributes and to improve the accuracy of the Data.