Journal article icon

Journal article

DAS-N2N: machine learning distributed acoustic sensing (DAS) signal denoising without clean data

Abstract:

This paper presents a weakly supervised machine learning method, which we call DAS-N2N, for suppressing strong random noise in distributed acoustic sensing (DAS) recordings. DAS-N2N requires no manually produced labels (i.e. pre-determined examples of clean event signals or sections of noise) for training and aims to map random noise processes to a chosen summary statistic, such as the distribution mean, median or mode, whilst retaining the true underlying signal. This is achieved by ...

Expand abstract
Publication status:
Published
Peer review status:
Peer reviewed

Actions


Access Document


Files:
Publisher copy:
10.1093/gji/ggad460

Authors


More by this author
Institution:
University of Oxford
Division:
MPLS
Department:
Earth Sciences
Oxford college:
St Cross College
Role:
Author
ORCID:
0000-0002-1486-3945
Publisher:
Oxford University Press
Journal:
Geophysical Journal International More from this journal
Volume:
236
Issue:
2
Pages:
1026-1041
Publication date:
2023-11-28
Acceptance date:
2023-11-15
DOI:
EISSN:
1365-246X
ISSN:
0956-540X
Language:
English
Keywords:
Pubs id:
1571232
Local pid:
pubs:1571232
Deposit date:
2023-11-27

Terms of use


Views and Downloads






If you are the owner of this record, you can report an update to it here: Report update to this record

TO TOP