Quick Links


Connectivity constrained segmentation of geologic featuresNormal access

Authors: Z. Liu, C. Song, B. She, X. Yao and G. Hu
Journal name: Geophysical Prospecting
Issue: Vol 67, No 5, June 2019 pp. 1369 - 1378
DOI: 10.1111/1365-2478.12764
Organisations: Wiley
Language: English
Info: Article, PDF ( 1.48Mb )

Segmentation of geologic features plays a significant role in seismic interpretation. Based on the segmentation results, interpreters can readily recognize the shape and distribution of geologic features in three-dimensional space and conduct further quan-titative analysis. Usually, there are mainly two steps for the segmentation of geologic features: the first step is to extract seismic attributes that can highlight the occurrence of geologic features, and the second step is to apply the segmentation algorithm on the seismic attribute volumes. However, the occurrence of geologic features is not always corresponding to the anomaly value on the seismic attribute volumes and vice versa because of several factors, such as noise in the seismic data, the limited resolution of seismic images and the limited effectiveness of the seismic attribute. Therefore, the segmentation results, which are generated solely based on seismic attributes, are not sufficient to give an accurate depiction of geologic features. Aiming at this prob-lem, we introduce the connectivity constraint into the process of segmentation based the assumption that for one single geologic feature all of its components should be connected to each other. Benefiting from this global constraint, the segmentation results can precisely exclude the interference by false negatives on seismic attribute volumes. However, directly introducing the connectivity constraint into segmenta-tion would face the risk that the segmentation results would deteriorate significantly because of false positives with relatively large area when the connectivity constraints are enforced. Therefore, based on the seismic attribute that highlights the boundary of geologic feature, we further propose a post-processing technique, called pruning, to refine the segmentation results. By taking the segmentation of the channel as an example, we demonstrate that the proposed method is able to preserve the connec-tivity in the process of segmentation and generate better segmentation results on the field data.

Back to the article list