Seismic Facies Classification Using Digital Music Technology and Musical Information Retrieval Approaches

In this paper, we discuss a novel approach of pattern recognition, clustering and classification of seismic data based on techniques commonly applied in the domain of digital music and Musical Information Retrieval. Our workflow starts with accurate conversion of seismic data from SEGY to Musical Instrument Digital Interface (MIDI) format. Then we extract MIDI features from the converted data. These can be single-valued attributes related to instantaneous frequency and/or to the signal amplitude. Furthermore, we use multi-valued MIDI attributes that have no equivalent in the seismic domain, such as those related to melodic, harmonic and rhythmic patterns in the data. Finally, we apply multiple classification methods based on supervised and unsupervised approaches, with the final objective to classify the data into different seismic facies. We show the benefits of this cross-disciplinary approach through two different applications on two real seismic data sets.