Electrofacies Classification of Ponta Grossa Formation by Multi-Resolution Graph-Based Clustering (MRGC) and Self-Organizing Maps (SOM) Methods
Felipe Vasconcelos dos Passos, Marco Antonio Braga, Thiago Gonçalves Carelli, Josiane Branco Plantz
ABSTRACT
In Ponta Grossa Formation, devonian interval of Paraná Basin, Brazil, sampling restrictions are frequent, and lithological interpretations from gamma ray logs are common. However, no single log can discriminate lithology unambiguously. An alternative to reduce the uncertainty of these assessments is to perform multivariate analysis of well logs using data clustering methods. In this sense, this study aims to apply two different clustering algorithms, trained with gamma ray, sonic and resistivity logs. Five electrofacies were differentiated and validated by core data. It was found that one of the electrofacies identified by the model was not distinguished by macroscopic descriptions. However, the model developed is sufficiently accurate for lithological predictions.
Keywords: geophysical well logging, lithology prediction, Paraná Basin.