Fault enhancement using probabilistic neural networks and Laplacian of a Gaussian filter: A case study in the Great South Basin, New Zealand

Abstract

Fault identification is critical in defining the structural framework for exploration and reservoir characterization studies. Interpreters routinely use edge-sensitive attributes to accelerate the manual picking process, in which the actual choice of a particular edge-sensitive attribute varies with the seismic data quality and with the reflectivity response of the faulted geologic formations. The cyan-magenta-yellow (CMY) color blending provides an effective way to combine the information content of two or three edge-sensitive attributes when more than one attribute is sensitive to faults. We have evaluated whether combining the information content of more than three attributes using probabilistic neural networks (PNNs) provides any additional uplift. We use training data consisting of manually picked faults on a coarse grid of 3D seismic lines, and then, we use an exhaustive search PNN to identify the optimal set of attributes to create a fault probability volume for a 3D survey acquired over the Great South Basin, New Zealand. We construct a suite of candidate attributes using our understanding of the attribute response to faults seen in the data and examples extracted from the published literature to use the list as the analyzed attributes. Using a subset of picked faults as training data, we evaluate which suite of attributes and hyperparameters exhibits the highest validation on the remaining training data. When used together, we find that volume aberrancy magnitude, gray-level cooccurrence matrix (GLCM) homogeneity, GLCM entropy, Sobel filter similarity, and envelope best predict the faults for this data set. The PNN supervised classification creates a seismic image volume that exhibits fault probabilities providing a simple combination of multiple seismic attributes. We also find that applying a directional Laplacian of a Gaussian and skeletonization filters to the PNN fault volumes provides a superior result to simple CMY blending techniques.