Order reprints

Application of Musical Information Retrieval (MIR) Techniques to Seismic Facies Classification. Examples in Hydrocarbon Exploration

Paolo Dell’Aversana Gianluca Gabbriellini Alfonso Iunio Marini Alfonso Amendola

*Corresponding author: Paolo Dell’Aversana paolo.dell’aversana@eni.com


In this paper, we introduce a novel approach for automatic pattern recognition and classification of geophysical data based on digital music technology. We import and apply in the geophysical domain the same approaches commonly used for Musical Information Retrieval (MIR). After accurate conversion from geophysical formats (example: SEG-Y) to musical formats (example: Musical Instrument Digital Interface, or briefly MIDI), we extract musical features from the converted data. These can be single-valued attributes, such as pitch and sound intensity, or multi-valued attributes, such as pitch histograms, melodic, harmonic and rhythmic paths. Using a real data set, we show that these musical features can be diagnostic for seismic facies classification in a complex exploration area. They can be complementary with respect to “conventional” seismic attributes. Using a supervised machine learning approach based on the k-Nearest Neighbors algorithm and on Automatic Neural Networks, we classify three gas-bearing channels. The good performance of our classification approach is confirmed by borehole data available in the same area.

Please supply your name and a valid email address you yourself

Fields marked*are required

Article URL   http://www.aimspress.com/geosciences/article/1159.html
Article ID   geosci-02-413
Editorial Email  
Your Name *
Your Email *
Quantity *

Copyright © AIMS Press All Rights Reserved