An Efficient Self-supervised Seismic Data Reconstruction Method Based on Self-Consistency Learning

TL;DR

This paper introduces a self-supervised seismic data reconstruction method that leverages self-consistency learning, requiring no extra datasets and using a lightweight network to achieve high-quality results in complex exploration scenarios.

Contribution

The study presents a novel self-supervised learning approach with a lightweight network that effectively reconstructs seismic data without needing additional datasets or supervision.

Findings

Achieves high-quality seismic data reconstruction on public datasets.

Requires only 188,849 parameters, demonstrating efficiency.

Outperforms existing methods in stability and accuracy.

Abstract

Seismic exploration remains the most critical method for characterizing subsurface structures in geophysics. However, complex surface conditions often cause a non-uniform distribution of seismic receivers along survey lines, leading to irregularly acquired seismic data, which affects subsequent processing and inversion. Prior deep learning-based seismic data reconstruction methods typically rely on datasets for supervised training. While some existing methods avoid extra data, they lack effective constraints on reconstructed data, leading to unstable performance. In this study, we propose a self-supervised self-consistency learning strategy with a lightweight network for seismic data reconstruction. Our method requires no extra datasets, and it leverages inter-component correlations in seismic data to design a loss function, optimizing a network with only 188,849 learnable parameters. Validated on two public seismic datasets, results demonstrate our approach yields high-quality reconstruction, providing significant value for large-scale and complex seismic exploration tasks.