Semi-Supervised Segmentation of Salt Bodies in Seismic Images using an Ensemble of Convolutional Neural Networks

Abstract

Seismic image analysis plays a crucial role in a wide range of industrial applications and has been receiving significant attention. One of the essential challenges of seismic imaging is detecting subsurface salt structure which is indispensable for identification of hydrocarbon reservoirs and drill path planning. Unfortunately, exact identification of large salt deposits is notoriously difficult and professional seismic imaging often requires expert human interpretation of salt bodies. Convolutional neural networks (CNNs) have been successfully applied in many fields, and several attempts have been made in the field of seismic imaging. But the high cost of manual annotations by geophysics experts and scarce publicly available labeled datasets hinder the performance of the existing CNN-based methods. In this work, we propose a semi-supervised method for segmentation (delineation) of salt bodies in seismic images which utilizes unlabeled data for multi-round self-training. To reduce error amplification during self-training we propose a scheme which uses an ensemble of CNNs. We show that our approach outperforms state-of-the-art on the TGS Salt Identification Challenge dataset and is ranked the first among the 3234 competing methods.

Accepted at GCPR 2019, Source code: https://github.com/ybabakhin/kaggle_salt_bes_phalanx

References in corpus (8)

• TernausNet: U-Net with VGG11 Encoder Pre-Trained on ImageNet for Image Segmentation
• Pyramid Attention Network for Semantic Segmentation
• Automatic Seismic Salt Interpretation with Deep Convolutional Neural Networks
• The Lovász-Softmax loss: A tractable surrogate for the optimization of the intersection-over-union measure in neural networks
• Deep Unsupervised Learning of Visual Similarities
• Automatic salt deposits segmentation: A deep learning approach
• Self-Supervised Relative Depth Learning for Urban Scene Understanding
• SFA-GTM: Seismic Facies Analysis Based on Generative Topographic Map and RBF

Cited by in corpus (4)

• Self-training with Noisy Student improves ImageNet classification
• Semi-Supervised Wide-Angle Portraits Correction by Multi-Scale Transformer
• A Benchmark on Tricks for Large-scale Image Retrieval
• Self-Supervised Delineation of Geological Structures using Orthogonal Latent Space Projection