Semantic Segmentation of Seismic Images
This work addresses the problem of automating seismic image segmentation for geologists and researchers, offering a significant improvement in accuracy but is incremental as it builds on existing deep learning approaches.
The paper tackles the time-consuming task of expert-based seismic image segmentation by introducing a new deep neural network architecture that achieves over 99% mean intersection over union (mIOU), outperforming existing methods like Fully Convolutional Network and U-Net.
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.