A novel attention model for salient structure detection in seismic volumes

TL;DR

This paper introduces a novel 3D spectral and attention-based saliency detection algorithm for seismic data, effectively identifying subsurface structures and outperforming existing methods in seismic interpretation.

Contribution

The paper presents a new attention model combining 3D spectral analysis and directional center-surround comparisons tailored for seismic structure detection.

Findings

Effective detection of seismic structures in real datasets

Outperforms state-of-the-art saliency algorithms for seismic data

Handles subtle variations and relative motion in seismic volumes

Abstract

A new approach to seismic interpretation is proposed to leverage visual perception and human visual system modeling. Specifically, a saliency detection algorithm based on a novel attention model is proposed for identifying subsurface structures within seismic data volumes. The algorithm employs 3D-FFT and a multi-dimensional spectral projection, which decomposes local spectra into three distinct components, each depicting variations along different dimensions of the data. Subsequently, a novel directional center-surround attention model is proposed to incorporate directional comparisons around each voxel for saliency detection within each projected dimension. Next, the resulting saliency maps along each dimension are combined adaptively to yield a consolidated saliency map, which highlights various structures characterized by subtle variations and relative motion with respect to their neighboring sections. A priori information about the seismic data can be either embedded into the proposed attention model in the directional comparisons, or incorporated into the algorithm by specifying a template when combining saliency maps adaptively. Experimental results on two real seismic datasets from the North Sea, Netherlands and Great South Basin, New Zealand demonstrate the effectiveness of the proposed algorithm for detecting salient seismic structures of different natures and appearances in one shot, which differs significantly from traditional seismic interpretation algorithms. The results further demonstrate that the proposed method outperforms comparable state-of-the-art saliency detection algorithms for natural images and videos, which are inadequate for seismic imaging data.