At the 15th CISBGf (International Congress Of Brazilian Geophysics Society) that happened between July 31 and August 3 in Rio de Janeiro our principal researcher Aurélio Figueiredo gave a talk about “Mapping Seismic Horizons using Clustering-based Methodologies” during the Workshop on Computational Geophysics. A pioneer research in modern Machine Learning applied to Seismic Interpretation. This technique provides a dense set of seismic horizons and accelerate the interpretation of geological features like channels, faults, and salt boundaries. The following abstract and the result images show us more detail of this work.
The methods organize the seismic data according to a global and auto-adaptable criterion, and maps horizons using fixed seeds. In this work, we present significant improvements in the method presented by Figueiredo et al. (2014). Our approach uses the cosine of instantaneous phase attribute and applies Principal Component Analysis (PCA) on the original datasets of trace shapes, improving the quality of the original samples. Then, we propose a measurement to infer the quality of the clusters used to map the seismic horizons. Based on this measurement, we show that using the cosine of instantaneous phase attributes, and PCA greatly improves the performance of the horizon mapping algorithm.
Visit our website and see other publications and research results.
Follow us on Social Media!
#CISBGF2017 #MachineLearning #GPU #Oil&Gas #ComputationalGeophysics #IntelligentGeophysics #SeismicInterpretation