Self-supervised surface-related multiple suppression with multidimensional convolution

TL;DR

This paper introduces a self-supervised learning method using multidimensional convolution to suppress surface-related multiples in seismic data, eliminating the need for labeled data and improving imaging quality.

Contribution

The proposed framework is the first to apply self-supervised learning with multidimensional convolution for multiple suppression in seismic data.

Findings

Effectively suppresses surface-related multiples in numerical tests.

Preserves primary reflections and reduces imaging artifacts.

Enhances seismic imaging quality through improved data processing.

Abstract

Surface-related multiples pose significant challenges in seismic data processing, often obscuring primary reflections and reducing imaging quality. Traditional methods rely on computationally expensive algorithms, the prior knowledge of subsurface model, or accurate wavelet estimation, while supervised learning approaches require clean labels, which are impractical for real data. Thus, we propose a self-supervised learning framework for surface-related multiple suppression, leveraging multi-dimensional convolution to generate multiples from the observed data and a two-stage training strategy comprising a warm-up and an iterative data refinement stage, so the network learns to remove the multiples. The framework eliminates the need for labeled data by iteratively refining predictions using multiples augmented inputs and pseudo-labels. Numerical examples demonstrate that the proposed method effectively suppresses surface-related multiples while preserving primary reflections. Migration results confirm its ability to reduce artifacts and improve imaging quality.