Binary Segmentation of Seismic Facies Using Encoder-Decoder Neural Networks

TL;DR

This paper introduces a deep neural network model, DNFS, for seismic facies segmentation that achieves high accuracy with fewer parameters, improving efficiency and detail in geological data interpretation.

Contribution

The paper presents a novel encoder-decoder neural network architecture, DNFS, specifically designed for seismic facies segmentation, outperforming existing models in detail and parameter efficiency.

Findings

DNFS achieves state-of-the-art segmentation accuracy.

DNFS uses fewer parameters than comparable models.

DNFS provides highly detailed seismic facies predictions.

Abstract

The interpretation of seismic data is vital for characterizing sediments' shape in areas of geological study. In seismic interpretation, deep learning becomes useful for reducing the dependence on handcrafted facies segmentation geometry and the time required to study geological areas. This work presents a Deep Neural Network for Facies Segmentation (DNFS) to obtain state-of-the-art results for seismic facies segmentation. DNFS is trained using a combination of cross-entropy and Jaccard loss functions. Our results show that DNFS obtains highly detailed predictions for seismic facies segmentation using fewer parameters than StNet and U-Net.