Home » Fault Detection Using Seismic Attributes and Visual Saliency

Fault Detection Using Seismic Attributes and Visual Saliency



Seismic faults are common geological structures formed by the transverse movement of rocks adjacent to each other that disrupts the horizon continuity. Their detection is crucial to indicate potential petroleum reservoirs and facilitate in bore-hole and well drilling. Seismic interpreters spend considerable efforts in locating faults after processing the seismic data. Due to the massive nature of seismic data, adopting manual interpretation is extremely time consuming and labor intensive. Therefore, intelligent computer algorithms that can perform this task effectively and efficiently is an active area of research.

In order to detect accurately faults in seismic inline sections, we propose a new bottomup saliency based approach using different seismic attributes such as coherence, curvature, dip, and gradient in parallel. Each attribute is calculated independently from the original seismic section. The saliency maps of aforementioned attributes are computed using covariance matrix, which are later combined to form a consolidated saliency map that highlights the seismic fault regions. The covariance matrix is used to characterize the seismic patches and captures local structures. By thresholding the variance maps and optimizing the binary points for curve fitting, the proposed workflow yields good results for faults labeling. The saliency map overlaid on the seismic inline section #256 from F3 block is shown in the top figure. The next figure highlights the faults in green color on two seismic inlines with the ground truth manually labeled in red. The experimental results shown in this paper illustrate that the proposed workflow highlights the fault regions and detected fault lines very precisely.


[Related Publications]

  1. A. Lawal, S. Al-Dharrab, M. Deriche, M. Shafiq, and G. AlRegib, “Fault detection using seismic attributes and visual saliency,” 86th SEG Annual Meeting, Dallas, Texas, USA, Oct. 16-21, 2016. [PDF] [PPT (Poster/Slide)] [Bib] [Code]
%d bloggers like this: