AIMS Geosciences, 2016, 2(4): 413-425. doi: 10.3934/geosci.2016.4.413

Research article

Export file:


  • RIS(for EndNote,Reference Manager,ProCite)
  • BibTex
  • Text


  • Citation Only
  • Citation and Abstract

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

Eni SpA, San Donato Milanese, Milan, Italy

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.
  Article Metrics
Download full text in PDF

Export Citation

Article outline

Copyright © AIMS Press All Rights Reserved