Metta Innovations @ 15th CISBGf “Mapping Seismic Horizons using Clustering-based Methodologies”

Geophysics

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.

Abstract

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.

Figure 1: Using the F3 Block, a time slice at 1244 milliseconds, in a complex region of the seismic data; the time slice in contrast with the mapped horizon; the complete mapped horizon; some horizons mapped using the method, showed in contrast with two orthogonal slices. Using cosine of instantaneous phase and PCA improves the mapping performance. Even difficult horizons are correctly mapped.

 

Figure 2. We present only the horizons that extend along all the seismic data. Various horizons are showed in contrast with two orthogonal slices. As we can see, the surfaces are correctly interrupted by any discontinuities present in the data. The mapped horizon follows the seismic signal with voxel precision.

 

Figure 3. The mapping procedure contours the seismic faults and channels present in the data. We apply the curvature attribute into the horizon surface. The curvature (Martins et al, 2012) values are high around the surface borders, attesting mapping quality; a sub area is presented to emphasize the correct interruptions around faults. A fault attribute known as MSA (Figueiredo, 2014) is applied over the horizon surface. The high values on the horizon borders points that the mapping procedure has stops accurately.

 

Visit our website and see other publications and research results.
www.mettainnovations.com.br

Follow us on Social Media!

 

#CISBGF2017 #MachineLearning #GPU #Oil&Gas #ComputationalGeophysics #IntelligentGeophysics #SeismicInterpretation

@SBGf @Petrobras

Nenhum comentário

Deixe uma resposta

O seu endereço de e-mail não será publicado. Campos obrigatórios são marcados com *

Geophysics
Metta Innovations @ 15th CISBGf “Noise Attenuation by Anisotropic Diffusion Preserving Structural Features”

At the 15th CISBGf (International Congress Of Brazilian Geophysics Society) that happened between July 31 and August 3 in Rio de Janeiro our researcher engineer Patrícia Pampanelli presented the work “Noise Attenuation by Anisotropic Diffusion Preserving Structural Features” during the Workshop on Computational Geophysics. In this work we can see how HPC …


Deprecated: Directive 'track_errors' is deprecated in Unknown on line 0