Automatic salt deposits segmentation: A deep learning approach

TL;DR

This paper presents a deep learning approach for automatic salt deposit segmentation in seismic images, combining multiple advanced techniques to achieve top-tier performance in a Kaggle competition.

Contribution

The paper introduces a novel neural network architecture integrating several deep learning techniques for improved salt deposit segmentation in seismic data.

Findings

Achieved top 1% ranking in a Kaggle competition

Implemented a U-Net with ResNeXt-50 encoder and advanced modules

Demonstrated significant performance improvements over baseline methods

Abstract

One of the most important applications of seismic reflection is the hydrocarbon exploration which is closely related to salt deposits analysis. This problem is very important even nowadays due to it's non-linear nature. Taking into account the recent developments in deep learning networks TGS-NOPEC Geophysical Company hosted the Kaggle competition for salt deposits segmentation problem in seismic image data. In this paper, we demonstrate the great performance of several novel deep learning techniques merged into a single neural network which achieved the 27th place (top 1%) in the mentioned competition. Using a U-Net with ResNeXt-50 encoder pre-trained on ImageNet as our base architecture, we implemented Spatial-Channel Squeeze & Excitation, Lovasz loss, CoordConv and Hypercolumn methods. The source code for our solution is made publicly available at https://github.com/K-Mike/Automatic-salt-deposits-segmentation.