Identification of Environmental Noise Traces in Seismic Recordings Using Vision Transformer and Mel-Spectrogram

Environmental noise is inevitable during seismic data acquisition, with major sources including heavy machinery, rivers, wind, and other environmental factors. During field data acquisition, it is important to assess the impact of environmental noise and evaluate data quality. In subsequent seismic...

Full description

Saved in:
Bibliographic Details
Main Authors: Qianlong Ding, Shuangquan Chen, Jinsong Shen, Borui Wang
Format: Article
Language:English
Published: MDPI AG 2025-08-01
Series:Applied Sciences
Subjects:
Online Access:https://www.mdpi.com/2076-3417/15/15/8586
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849239888690413568
author Qianlong Ding
Shuangquan Chen
Jinsong Shen
Borui Wang
author_facet Qianlong Ding
Shuangquan Chen
Jinsong Shen
Borui Wang
author_sort Qianlong Ding
collection DOAJ
description Environmental noise is inevitable during seismic data acquisition, with major sources including heavy machinery, rivers, wind, and other environmental factors. During field data acquisition, it is important to assess the impact of environmental noise and evaluate data quality. In subsequent seismic data processing, these noise components also need to be eliminated. Accurate identification of noise traces facilitates rapid quality control (QC) during fieldwork and provides a reliable basis for targeted noise attenuation. Conventional environmental noise identification primarily relies on amplitude differences. However, in seismic data, high-amplitude signals are not necessarily caused by environmental noise. For example, surface waves or traces near the shot point may also exhibit high amplitudes. Therefore, relying solely on amplitude-based criteria has certain limitations. To improve noise identification accuracy, we use the Mel-spectrogram to extract features from seismic data and construct the dataset. Compared to raw time-series signals, the Mel-spectrogram more clearly reveals energy variations and frequency differences, helping to identify noise traces more accurately. We then employ a Vision Transformer (ViT) network to train a model for identifying noise in seismic data. Tests on synthetic and field data show that the proposed method performs well in identifying noise. Moreover, a denoising case based on synthetic data further confirms its general applicability, making it a promising tool in seismic data QC and processing workflows.
format Article
id doaj-art-7b5adf674b9745e6ad8a1b3cdcfddbb1
institution Kabale University
issn 2076-3417
language English
publishDate 2025-08-01
publisher MDPI AG
record_format Article
series Applied Sciences
spelling doaj-art-7b5adf674b9745e6ad8a1b3cdcfddbb12025-08-20T04:00:49ZengMDPI AGApplied Sciences2076-34172025-08-011515858610.3390/app15158586Identification of Environmental Noise Traces in Seismic Recordings Using Vision Transformer and Mel-SpectrogramQianlong Ding0Shuangquan Chen1Jinsong Shen2Borui Wang3College of Geophysics, China University of Petroleum (Beijing), Beijing 102249, ChinaCollege of Geophysics, China University of Petroleum (Beijing), Beijing 102249, ChinaCollege of Geophysics, China University of Petroleum (Beijing), Beijing 102249, ChinaSinopec Geophysical Corporation Southern Branch, Chengdu 610213, ChinaEnvironmental noise is inevitable during seismic data acquisition, with major sources including heavy machinery, rivers, wind, and other environmental factors. During field data acquisition, it is important to assess the impact of environmental noise and evaluate data quality. In subsequent seismic data processing, these noise components also need to be eliminated. Accurate identification of noise traces facilitates rapid quality control (QC) during fieldwork and provides a reliable basis for targeted noise attenuation. Conventional environmental noise identification primarily relies on amplitude differences. However, in seismic data, high-amplitude signals are not necessarily caused by environmental noise. For example, surface waves or traces near the shot point may also exhibit high amplitudes. Therefore, relying solely on amplitude-based criteria has certain limitations. To improve noise identification accuracy, we use the Mel-spectrogram to extract features from seismic data and construct the dataset. Compared to raw time-series signals, the Mel-spectrogram more clearly reveals energy variations and frequency differences, helping to identify noise traces more accurately. We then employ a Vision Transformer (ViT) network to train a model for identifying noise in seismic data. Tests on synthetic and field data show that the proposed method performs well in identifying noise. Moreover, a denoising case based on synthetic data further confirms its general applicability, making it a promising tool in seismic data QC and processing workflows.https://www.mdpi.com/2076-3417/15/15/8586automated noise identificationnoise attenuationMel-spectrogramseismic data quality controldeep learning
spellingShingle Qianlong Ding
Shuangquan Chen
Jinsong Shen
Borui Wang
Identification of Environmental Noise Traces in Seismic Recordings Using Vision Transformer and Mel-Spectrogram
Applied Sciences
automated noise identification
noise attenuation
Mel-spectrogram
seismic data quality control
deep learning
title Identification of Environmental Noise Traces in Seismic Recordings Using Vision Transformer and Mel-Spectrogram
title_full Identification of Environmental Noise Traces in Seismic Recordings Using Vision Transformer and Mel-Spectrogram
title_fullStr Identification of Environmental Noise Traces in Seismic Recordings Using Vision Transformer and Mel-Spectrogram
title_full_unstemmed Identification of Environmental Noise Traces in Seismic Recordings Using Vision Transformer and Mel-Spectrogram
title_short Identification of Environmental Noise Traces in Seismic Recordings Using Vision Transformer and Mel-Spectrogram
title_sort identification of environmental noise traces in seismic recordings using vision transformer and mel spectrogram
topic automated noise identification
noise attenuation
Mel-spectrogram
seismic data quality control
deep learning
url https://www.mdpi.com/2076-3417/15/15/8586
work_keys_str_mv AT qianlongding identificationofenvironmentalnoisetracesinseismicrecordingsusingvisiontransformerandmelspectrogram
AT shuangquanchen identificationofenvironmentalnoisetracesinseismicrecordingsusingvisiontransformerandmelspectrogram
AT jinsongshen identificationofenvironmentalnoisetracesinseismicrecordingsusingvisiontransformerandmelspectrogram
AT boruiwang identificationofenvironmentalnoisetracesinseismicrecordingsusingvisiontransformerandmelspectrogram