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; Paolo Dell’Aversana; Gianluca Gabbriellini; Alfonso Iunio Marini; Alfonso Amendola

doi:10.3934/geosci.2016.4.413

AIMS Geosciences

2016, Volume 2, Issue 4: 413-425. doi: 10.3934/geosci.2016.4.413

Previous Article Next Article

Research article

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

Eni SpA, San Donato Milanese, Milan, Italy

Received: 26 September 2016 Accepted: 02 December 2016 Published: 13 December 2016

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.
- Seismic facies classification,
- sonification,
- audio video display,
- spectral decomposition,
- pattern recognition,
- musical information retrieval,
- MIDI
Citation: Paolo Dell’Aversana, Gianluca Gabbriellini, Alfonso Iunio Marini, Alfonso Amendola. Application of Musical Information Retrieval (MIR) Techniques to Seismic Facies Classification. Examples in Hydrocarbon Exploration[J]. AIMS Geosciences, 2016, 2(4): 413-425. doi: 10.3934/geosci.2016.4.413

Related Papers:

Abstract

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.

References

[1]	Theodoridis and Koutroumbas (1998) Pattern Recognition, Academic Press, London.
[2]	Zhao T, Jayaram V, Roy A, et al (2015) A comparison of classification techniques for seismic facies recognition. Interpret 3: 29-58.
[3]	Duda RO, Hart PE, Stork DG (2001) Pattern classification. 2nd ed: John Wiley & Sons.
[4]	Dell’Aversana P (2013) Listening to geophysics: Audio processing tools for geophysical data analysis and interpretation. The Leading Edge 32: 980-987. doi: 10.1190/tle32080980.1
[5]	Dell’Aversana P (2014) A bridge between geophysics and digital music. Ap plications to hydrocarbon exploration. First Break 32: 51-56.
[6]	Dell’Aversana P, Gabbriellini G, Amendola A (2016) Sonification of geophysical data through time-frequency transforms. Geophys Prospect.
[7]	Stockwell RG, Mansinha L, Lowe RP (1996) Localization of the complex spectrum: the S Transform. IEEE Trans Signal Process 44: 998-1001. doi: 10.1109/78.492555
[8]	Wang A (2003) An industrial-strength Audio Search Algorithm, ISMIR, London: Shazam Entertainment Ltd.
[9]	Kiang MY (2003) A comparative assessment of classification methods. Decis Support Syst 35: 441-454.
[10]	McKay C (2004) Automatic Genre Classification of MIDI Recordings, Music Technology Area Department of Theory, Faculty of Music, McGill University, Montreal.
[11]	Aminzadeh F and de Groot P (2006) Neural Networks and Other Soft Computing Techniques with Applications in the Oil Industry, EAGE Publications.

Reader Comments

Your name:*

Email:*
© 2016 the Author(s), licensee AIMS Press. This is an open access article distributed under the terms of the Creative Commons Attribution License (http://creativecommons.org/licenses/by/4.0)