Adaptive Self-Supervised Surface-Related Multiple Suppression

TL;DR

This paper introduces an adaptive self-supervised learning approach for surface-related multiple suppression in seismic data, jointly optimizing a learnable scaling factor and loss weights to enhance robustness and imaging quality.

Contribution

It proposes a novel adaptive SSL framework that automatically learns amplitude scaling and balances loss terms, eliminating manual tuning and improving multiple suppression performance.

Findings

Robust suppression of surface-related multiples demonstrated on synthetic and field data.

Improved subsurface imaging quality confirmed by migration results.

The method automatically adapts to amplitude variations without manual parameter tuning.

Abstract

Effective suppression of surface-related multiples is essential to prevent imaging artifacts and erroneous structural interpretations. While conventional approaches rely on accurate priors or subsurface model knowledge, and supervised learning methods require labeled data that are impractical to obtain for real seismic data. To overcome these limitations, a recently proposed self-supervised learning (SSL) framework integrates multi-dimensional convolution (MDC) for multiple generation with a two-stage training strategy, eliminating the need for both prior knowledge and labeled data. However, their approach requires manual selection of a scaling factor to match the amplitudes between the MDC-generated multiples and the true multiples, thus introducing subjectivity and limiting its practical applicability. In this study, we propose an adaptive SSL method that treats the scaling factor as a learnable parameter, jointly optimized with the network weights in a unified single-stage training pipeline. This dynamic scaling implicitly introduces amplitude diversity into the training data, acting as an implicit regularizer that improves the network's robustness to amplitude variations of surface-related multiples. We further design a composite loss function with homoscedastic uncertainty-based adaptive weighting, which automatically balances the contributions of multiple loss terms without manual tuning. Synthetic and field data examples demonstrate that our method robustly and effectively suppresses surface-related multiples while preserving primary reflections, with migration results confirming improved subsurface imaging quality.