A Review of Deep-learning-based Seismic Data Denoising and Its Promising Paradigm Shift to Foundation Models
Abstract
Denoising is a long-standing and widely-concerned topic in seismic data processing, for it can significantly increase the signal-to-noise ratio of seismic data. Numerous deep learning (DL) methods have shown promising denoising performance, but most of them are task-specific and focus on a certain type of seismic background noise. The real condition that seismic datasets are often contaminated by various types of noises motivates us to explore a well-generalized and versatile DL model for seismic data denoising. Recently, in the fields of computer vision and natural language processing, foundation models (FMs) pre-trained on vast datasets demonstrate outstanding adaptability and generality across diverse downstream tasks. This paradigm offers a promising path to address the challenges faced by task-specific DL denoising models, such as poor generalization, retraining from scratch for different noise, and the lack of labeled data. We first provide a brief review of traditional seismic denoising methods, followed by a comprehensive review of existing DL-based denoising methods categorized by noise type. Furthermore, we conduct a case study on a dedicated seismic denoising foundation model termed SeisDeFM. This is the first study in geophysical research to develop and validate a seismic denoising foundation model on pre-stack gathers with diverse noise conditions. Experimental results demonstrate that, compared with task-specific DL baselines, SeisDeFM achieves superior denoising performance and cross-noise generalization by the advantages of sufficient pre-training and appropriate downstream adaptation, and it effectively preserves weak reflection events while suppressing complex noise in pre-stack seismic data.
Related
- Parameter-Efficient Adaptation of Pre-Trained Vision Foundation Models for Active and Passive Seismic Data Denoising
- 3D seismic salt dome segmentation using a hybrid UNet with global attention, denoising pretraining, and discriminative transfer learning
- Fault-conditioned Seismic Image Generation using Denoising Diffusion Probabilistic Modeling and Neural Style Transfer
- Xaurora: Generative Weather Forecasting with Denoising Stochastic Interpolants from a Foundation Model Prior
- Deep Learning Denoising of Real SWOT Sea Surface Height Observations
BibTeX
@misc{dong2026review,
title = {{A Review of Deep-learning-based Seismic Data Denoising and Its Promising Paradigm Shift to Foundation Models}},
author = {Xintong Dong and Zhengyi Yuan and Changxin Wei and Wenshuo Yu and Shiqi Dong and Jun Lin},
howpublished = {arXiv},
year = {2026},
month = sep,
doi = {10.48550/arxiv.2609.34530},
eprint = {2609.34530},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2609.34530},
}
RIS
TY - UNPB
TI - A Review of Deep-learning-based Seismic Data Denoising and Its Promising Paradigm Shift to Foundation Models
AU - Xintong Dong
AU - Zhengyi Yuan
AU - Changxin Wei
AU - Wenshuo Yu
AU - Shiqi Dong
AU - Jun Lin
PY - 2026
DA - 2026/09/28
PB - arXiv
DO - 10.48550/arxiv.2609.34530
UR - https://arxiv.org/abs/2609.34530
AB - Denoising is a long-standing and widely-concerned topic in seismic data processing, for it can significantly increase the signal-to-noise ratio of seismic data. Numerous deep learning (DL) methods have shown promising denoising performance, but most of them are task-specific and focus on a certain type of seismic background noise. The real condition that seismic datasets are often contaminated by various types of noises motivates us to explore a well-generalized and versatile DL model for seismic data denoising. Recently, in the fields of computer vision and natural language processing, foundation models (FMs) pre-trained on vast datasets demonstrate outstanding adaptability and generality across diverse downstream tasks. This paradigm offers a promising path to address the challenges faced by task-specific DL denoising models, such as poor generalization, retraining from scratch for different noise, and the lack of labeled data. We first provide a brief review of traditional seismic denoising methods, followed by a comprehensive review of existing DL-based denoising methods categorized by noise type. Furthermore, we conduct a case study on a dedicated seismic denoising foundation model termed SeisDeFM. This is the first study in geophysical research to develop and validate a seismic denoising foundation model on pre-stack gathers with diverse noise conditions. Experimental results demonstrate that, compared with task-specific DL baselines, SeisDeFM achieves superior denoising performance and cross-noise generalization by the advantages of sufficient pre-training and appropriate downstream adaptation, and it effectively preserves weak reflection events while suppressing complex noise in pre-stack seismic data.
ER -