Skip to Main Content
Skip Nav Destination
GEOREF RECORD

Trace-wise coherent noise suppression via a self-supervised blind-trace deep-learning scheme

Sixiu Liu, Claire Birnie and Tariq Alkhalifah
Trace-wise coherent noise suppression via a self-supervised blind-trace deep-learning scheme
Geophysics (December 2023) 88 (6): V459-V472

Abstract

Seismic data denoising via supervised deep learning is effective and popular but requires noise-free labels, which are rarely available. Blind-spot networks circumvent this requirement by training directly on noisy data and have been demonstrated to be a powerful suppressor of random noise. In this work, we expand the methodology of blind-spot networks to create a blind-trace network that successfully removes trace-wise coherent noise. An extensive synthetic analysis illustrates the denoising procedure's robustness to varying noise levels and varying numbers of noisy traces within shot gathers. It is demonstrated that the network can accurately learn to suppress the noise when up to 60% of the original traces are noisy. Furthermore, our procedure is implemented on the Stratton 3D field data set and demonstrates the restoration of the previously corrupted direct arrivals. In addition to trace-wise noise suppression, we adapt the blind-spot networks to the successful suppression of colored Gaussian noise, which exhibits varying coherent properties in time and spatial axes. Our adaptation of the blind-spot networks paves the way for its use in other applications, such as the suppression of coherent noise arising from wellsite activity, passing vessels, or nearby industrial activity.


ISSN: 0016-8033
EISSN: 1942-2156
Coden: GPYSA7
Serial Title: Geophysics
Serial Volume: 88
Serial Issue: 6
Title: Trace-wise coherent noise suppression via a self-supervised blind-trace deep-learning scheme
Affiliation: King Abdullah University of Science and Technology, Thuwal, Saudi Arabia
Pages: V459-V472
Published: 202312
Text Language: English
Publisher: Society of Exploration Geophysicists, Tulsa, OK, United States
References: 62
Accession Number: 2024-004126
Categories: Applied geophysics
Document Type: Serial
Bibliographic Level: Analytic
Illustration Description: illus. incl. 2 tables
N25°45'00" - N36°30'00", W106°30'00" - W93°30'00"
Country of Publication: United States
Secondary Affiliation: GeoRef, Copyright 2024, American Geosciences Institute. Reference includes data from GeoScienceWorld, Alexandria, VA, United States. Reference includes data supplied by Society of Exploration Geophysicists, Tulsa, OK, United States
Update Code: 2024
Close Modal

or Create an Account

Close Modal
Close Modal