Noisy-as-Clean SSL denoises real seismic data effectively when injected noise matches actual noise statistics, providing a practical alternative to supervised methods that require clean references.
The potential of self-supervised networks for random noise suppression in seismic data.Artificial Intelligence in Geosciences, 2:47–59, December 2021
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
physics.geo-ph 1years
2026 1verdicts
UNVERDICTED 1roles
background 1polarities
background 1representative citing papers
citing papers explorer
-
Deploying Self-Supervised Learning for Real Seismic Data Denoising
Noisy-as-Clean SSL denoises real seismic data effectively when injected noise matches actual noise statistics, providing a practical alternative to supervised methods that require clean references.