Convolutional neural networks for fault interpretation in seismic images

We propose an automatic fault interpretation method by using convolutional neural networks (CNN). In this method, we construct a 7-layer CNN to first estimate fault orientations (dips and strikes) within small image patches that are extracted from a full seismic image. With the estimated fault orientations, we then construct anisotropic Gaussian functions that mainly extend along the estimated fault dips and strikes. We finally stack all the locally fault-oriented Gaussian functions to generate a fault probability image. Although trained by using only synthetic seismic images, the CNN model can accurately estimate fault orientations within real seismic images. The fault probability image, computed from the estimated fault orientations, displays cleaner, more accurate, and more continuous fault features than those in the conventional fault attribute images. Presentation Date: Tuesday, October 16, 2018 Start Time: 8:30:00 AM Location: 204B (Anaheim Convention Center) Presentation Type: Oral