FaultSeg Swin-UNETR: Transformer-Based Self-Supervised Pretraining Model for Fault Recognition

TL;DR

This paper presents a transformer-based self-supervised pretraining approach for seismic fault recognition, leveraging unlabeled data and a refined Swin-UNETR model to improve accuracy and robustness in real seismic datasets.

Contribution

Introduces a novel self-supervised pretraining framework using Swin Transformer and SimMIM for seismic fault detection, enhancing performance on real data.

Findings

Achieves state-of-the-art results on Thebe dataset

Effective use of unlabeled seismic data for pretraining

Improved fault detection accuracy with multiscale decoding

Abstract

This paper introduces an approach to enhance seismic fault recognition through self-supervised pretraining. Seismic fault interpretation holds great significance in the fields of geophysics and geology. However, conventional methods for seismic fault recognition encounter various issues, including dependence on data quality and quantity, as well as susceptibility to interpreter subjectivity. Currently, automated fault recognition methods proposed based on small synthetic datasets experience performance degradation when applied to actual seismic data. To address these challenges, we have introduced the concept of self-supervised learning, utilizing a substantial amount of relatively easily obtainable unlabeled seismic data for pretraining. Specifically, we have employed the Swin Transformer model as the core network and employed the SimMIM pretraining task to capture unique features related to discontinuities in seismic data. During the fine-tuning phase, inspired by edge detection techniques, we have also refined the structure of the Swin-UNETR model, enabling multiscale decoding and fusion for more effective fault detection. Experimental results demonstrate that our proposed method attains state-of-the-art performance on the Thebe dataset, as measured by the OIS and ODS metrics.