Saliency-Map Guided Salt Prediction by a Multi-Channel Convolutional Neural Network

Abstract

One of the major challenges in seismic imaging is accurately delineating subsurface salt. Since a salt boundary has strong impedance compared with other sediments, we build a saliency map with intensity and orientation to create a pixel-level model for salt interpretation. In this abstract, we train a saliency-map as an additional attribute to combine with the original seismic to predict salt bodies. We also train a saliency-map to classify multiple geological facies in a multi-channel convolutional neural network with residual net architecture to help build subsurface velocity models. Two examples are shown which demonstrate that a saliency-map-plus-seismic model successfully improves the accuracy of salt prediction and reduces artifacts.