Robust salt-dome detection using the ranking of texture-based attributes

基于结构属性排序的稳定的盐丘探测（英文）

The accurate interpretation and analysis of seismic data heavily depends on the robustness of the algorithms used. We focus on the robust detection of salt domes from seismic surveys. We discuss a novel feature-ranking classification model for saltdome detection for seismic images using an optimal set of texture attributes. The proposed algorithm overcomes the limitations of existing texture attribute-based techniques, which heavily depend on the relevance of the attributes to the geological nature of salt domes and the number of attributes used for accurate detection. The algorithm combines the attributes from the Gray-Level Co-occurrence Matrix （GLCM）, the Gabor filters, and the eigenstructure of the covariance matrix with feature ranking using the information content. The top-ranked attributes are combined to form the optimal feature set, which ensures that the algorithm works well even in the absence of strong reflectors along the salt-dome boundaries. Contrary to existing salt-dome detection techniques, the proposed algorithm is robust and eomputationally efficient, and works with small-sized feature sets. I used the Netherlands F3 block to evaluate the performance of the proposed algorithm. The experimental results suggest that the proposed workflow based on information theory can detect salt domes with accuracy superior to existing salt-dome detection techniques.

地震数据的精确解释和分析非常依赖于所使用算法的稳定性。我们着重于盐丘地震勘探的稳定检测。我们讨论一个基于地震成像中最佳结构特征属性排序分类的盐丘探测新模型。该算法克服了现有的基于结构属性技术的局限性,因为该技术非常依赖于盐丘固有的地质属性与盐丘检测所用的属性数量。该算法综合了灰度共生矩阵(GLCM)属性,Gabor滤波器,以及含有使用属性特征排序信息协方差矩阵的本征结构等属性。将排序前列的属性组合起来形成一组最优的特征集,以保证算法即使在沿盐丘边界没有强反射层的情况下也能有效。与现有的盐丘检测技术相比,本文的算法稳定和计算高效,并能处理小尺度特征集。我用荷兰F3地块评价该算法的性能。实验结果表明,本文提出的基于信息理论的工作流程用于检测盐丘,其精度优于现有盐丘检测技术。