Semantic Segmentation of Seismic Images

TL;DR

This paper introduces a novel deep neural network architecture for seismic image segmentation that requires minimal training data and outperforms existing models, achieving over 99% mIOU on real seismic data.

Contribution

A new neural network design with transposed residual units and learned upscaling for efficient seismic image segmentation with limited data.

Findings

Achieves over 99% mean intersection over union (mIOU).

Outperforms Fully Convolutional Network and U-Net.

Produces masks closely matching human interpretation.

Abstract

Almost all work to understand Earth's subsurface on a large scale relies on the interpretation of seismic surveys by experts who segment the survey (usually a cube) into layers; a process that is very time demanding. In this paper, we present a new deep neural network architecture specially designed to semantically segment seismic images with a minimal amount of training data. To achieve this, we make use of a transposed residual unit that replaces the traditional dilated convolution for the decode block. Also, instead of using a predefined shape for up-scaling, our network learns all the steps to upscale the features from the encoder. We train our neural network using the Penobscot 3D dataset; a real seismic dataset acquired offshore Nova Scotia, Canada. We compare our approach with two well-known deep neural network topologies: Fully Convolutional Network and U-Net. In our experiments, we show that our approach can achieve more than 99 percent of the mean intersection over union (mIOU) metric, outperforming the existing topologies. Moreover, our qualitative results show that the obtained model can produce masks very close to human interpretation with very little discontinuity.