Research on Seismic Signal Denoising Model Based on DnCNN Network

Addressing the noise in seismic signals, a prevalent challenge within seismic signal processing, has been the focus of extensive research. Conventional algorithms for seismic signal denoising often fall short due to their reliance on manually determined feature functions and threshold parameters. Th...

Full description

Saved in:
Bibliographic Details
Main Authors: Li Duan, Jianxian Cai, Li Wang, Yan Shi
Format: Article
Language:English
Published: MDPI AG 2025-02-01
Series:Applied Sciences
Subjects:
Online Access:https://www.mdpi.com/2076-3417/15/4/2083
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849718789681184768
author Li Duan
Jianxian Cai
Li Wang
Yan Shi
author_facet Li Duan
Jianxian Cai
Li Wang
Yan Shi
author_sort Li Duan
collection DOAJ
description Addressing the noise in seismic signals, a prevalent challenge within seismic signal processing, has been the focus of extensive research. Conventional algorithms for seismic signal denoising often fall short due to their reliance on manually determined feature functions and threshold parameters. These limitations hinder effective noise removal, resulting in suboptimal signal-to-noise ratios (SNRs) and post-denoising waveform distortion. To address these shortcomings, this study introduces a novel denoising approach leveraging a DnCNN network. The DnCNN framework, which integrates batch normalization with residual learning, is adept at swiftly identifying and eliminating noise from seismic signals through its residual learning capabilities. To assess the efficacy of this DnCNN-based model, it was rigorously tested against a curated test set and benchmarked against other denoising techniques, including wavelet thresholding, empirical mode decomposition, and convolutional auto-encoders. The findings demonstrate that the DnCNN model not only significantly enhances the SNR and correlation coefficient of the processed seismic signals but also achieves superior noise reduction performance.
format Article
id doaj-art-706f4effcf73485190b0cffc3b62b5a3
institution DOAJ
issn 2076-3417
language English
publishDate 2025-02-01
publisher MDPI AG
record_format Article
series Applied Sciences
spelling doaj-art-706f4effcf73485190b0cffc3b62b5a32025-08-20T03:12:16ZengMDPI AGApplied Sciences2076-34172025-02-01154208310.3390/app15042083Research on Seismic Signal Denoising Model Based on DnCNN NetworkLi Duan0Jianxian Cai1Li Wang2Yan Shi3College of Electronic Science and Control Engineering, Institute of Disaster Prevention, Langfang 065201, ChinaCollege of Electronic Science and Control Engineering, Institute of Disaster Prevention, Langfang 065201, ChinaCollege of Electronic Science and Control Engineering, Institute of Disaster Prevention, Langfang 065201, ChinaCollege of Electronic Science and Control Engineering, Institute of Disaster Prevention, Langfang 065201, ChinaAddressing the noise in seismic signals, a prevalent challenge within seismic signal processing, has been the focus of extensive research. Conventional algorithms for seismic signal denoising often fall short due to their reliance on manually determined feature functions and threshold parameters. These limitations hinder effective noise removal, resulting in suboptimal signal-to-noise ratios (SNRs) and post-denoising waveform distortion. To address these shortcomings, this study introduces a novel denoising approach leveraging a DnCNN network. The DnCNN framework, which integrates batch normalization with residual learning, is adept at swiftly identifying and eliminating noise from seismic signals through its residual learning capabilities. To assess the efficacy of this DnCNN-based model, it was rigorously tested against a curated test set and benchmarked against other denoising techniques, including wavelet thresholding, empirical mode decomposition, and convolutional auto-encoders. The findings demonstrate that the DnCNN model not only significantly enhances the SNR and correlation coefficient of the processed seismic signals but also achieves superior noise reduction performance.https://www.mdpi.com/2076-3417/15/4/2083CNN (convolutional neural network)residual dense modulesignal noise reductionSNR (signal-to-noise ratio)
spellingShingle Li Duan
Jianxian Cai
Li Wang
Yan Shi
Research on Seismic Signal Denoising Model Based on DnCNN Network
Applied Sciences
CNN (convolutional neural network)
residual dense module
signal noise reduction
SNR (signal-to-noise ratio)
title Research on Seismic Signal Denoising Model Based on DnCNN Network
title_full Research on Seismic Signal Denoising Model Based on DnCNN Network
title_fullStr Research on Seismic Signal Denoising Model Based on DnCNN Network
title_full_unstemmed Research on Seismic Signal Denoising Model Based on DnCNN Network
title_short Research on Seismic Signal Denoising Model Based on DnCNN Network
title_sort research on seismic signal denoising model based on dncnn network
topic CNN (convolutional neural network)
residual dense module
signal noise reduction
SNR (signal-to-noise ratio)
url https://www.mdpi.com/2076-3417/15/4/2083
work_keys_str_mv AT liduan researchonseismicsignaldenoisingmodelbasedondncnnnetwork
AT jianxiancai researchonseismicsignaldenoisingmodelbasedondncnnnetwork
AT liwang researchonseismicsignaldenoisingmodelbasedondncnnnetwork
AT yanshi researchonseismicsignaldenoisingmodelbasedondncnnnetwork