Deploying Self-Supervised Learning for Real Seismic Data Denoising

TL;DR

This study evaluates the Noisy-as-Clean self-supervised learning method for real seismic data denoising, highlighting its effectiveness and limitations compared to supervised approaches.

Contribution

It demonstrates the deployment and assessment of NaC SSL method on real seismic data, revealing the importance of noise characteristics and data properties.

Findings

AWGN noise is inadequate for seismic data denoising with NaC

Performance depends on noise compatibility and data characteristics

NaC improves denoising without requiring clean reference data

Abstract

Self-supervised learning (SSL) has emerged as a promising approach to seismic data denoising as it does not require clean reference data. In this work, the deployment of the Noisy-as-Clean (NaC) method was evaluated for real seismic data denoising under controlled conditions. Two independent seismic acquisitions, each comprising noisy and filtered data, were organized into four real datasets. The NaC SSL method was adapted to add real noise to the noisy input, controlled by a parameter. An experimental protocol with ten experiments was designed to compare different strategies for deploying the NaC SSL method with the supervised learning baseline, using identical network topology and hyperparameters. The models were evaluated in terms of denoising performance, computational cost, and generalization capability. The results show that the synthetic additive white Gaussian noise (AWGN) is inadequate for the denoising of seismic data within the NaC method, and performance strongly depends on the compatibility between the injected and actual noise characteristics. Furthermore, both the characteristics of the seismic data and the noise level influence the performance of the model. Self-supervised fine-tuning on test data has improved SSL performance, whereas no such gain was observed for fine-tuning of supervised models. Finally, NaC has shown to be a simple, effective, and model-independent method that offers a feasible solution for the denoising of real seismic data.