AUTHORS: Denis Ferraretti, Giacomo Gamberoni (IntelliWARE), Prof. Evelina Lamma e Chiara Turolla (ENDIF – Engineering Department in Ferrara), Raffaele Di Cuia (GEPlan Consulting).
YEAR: 2009
IDEAL Conference 2009 (Burgos, Spain)
Abstract.
In petroleum geology, exploration and production wells are often analyzed using image logs, because they provide a visual representation of the borehole surface and they are fundamental to retrieve information on bedding and rocks characteristics. In this paper, we present a novel approach for image log interpretation and extraction of the main features of the rock formation. This process led to the development of I2AM, a semiautomatic system that exploits image processing algorithms and artificial intelligence techniques to analyze and classify borehole images.
I2AM analyzes log images using several image processing algorithms in order to extract numerical values for each characteristic and then performs a hierarchical clustering over the data obtained. Using three cluster evaluation indexes, possibly combined, I2AM can evaluate clustering results and, performing an automatic index-driven search, supplies a classification of the image logs. In this paper, we show I2AM application to the image logs from one well which were processed using the proposed method to identify different rock types and which were compared with those identified by the geologist. Main advantages of this approach are that interpretation time reduces from days to hours and subjectivity errors are avoided.