Multiple noise reduction for distributed acoustic sensing data processing through densely connected residual convolutional networks

被引:1
|
作者
Huang, Tianye [1 ]
Li, Aopeng [1 ]
Li, Desheng [1 ]
Zhang, Jing [1 ]
Li, Xiang [1 ]
Xiong, Liangming [2 ]
Tu, Jie [3 ]
Sun, Wufeng [3 ]
Hu, Xiangyun [1 ]
机构
[1] China Univ Geosci Wuhan, Sch Mech Engn & Elect Informat, Wuhan 430074, Peoples R China
[2] Yangtze Opt Fibre & Cable Joint Stock Ltd Co, Wuhan 430000, Peoples R China
[3] Opt Valley Technol Co Ltd, Wuhan 430070, Peoples R China
基金
中国国家自然科学基金;
关键词
Distributed acoustic sensing; Seismic survey; Supervised learning; Encoding and decoding; SINGULAR-VALUE DECOMPOSITION; MODE DECOMPOSITION; TEMPERATURE; STRAIN;
D O I
10.1016/j.jappgeo.2024.105464
中图分类号
P [天文学、地球科学];
学科分类号
07 ;
摘要
Distributed acoustic sensor (DAS), which utilizes the entire optical fiber as the sensing medium, provides distinct advantages of high resolution, dynamic monitoring, and resistance to high temperatures. This technology finds diverse applications in the seismic exploration, oil survey, and submarine cable monitoring industries. However, DAS signals are susceptible to various kinds of noise, such as horizontal noise, erratic noise, random noise, and so on, which significantly degrade the SNR. This low SNR is likely to affect some subsequent analyses, such as inversion and interpretation. The mixed noises feature of the DAS data poses a serious challenge for SNR enhancement. To address this issue, we develop a supervised learning-based densely connected residual convolutional denoising network (DCRCDNet), which leverages both encoding and decoding processes to extract features and reconstruct DAS data. The design of dense connectivity and residual blocks allow the network to extract both shallow and deep features. The network is trained using both synthetic and field data to obtain the optimal network parameters. Testing on synthetic data demonstrates that DCRCDNet improves the signal-tonoise ratio (SNR) from -10.21 dB to 15.61 dB. The test results from both synthetic and field data indicate that, compared to traditional filtering methods and other deep learning approaches, this network effectively suppresses noise in DAS signals. Consequently, DCRCDNet shows great potential in reconstructing DAS signals from hidden noise, suppressing strong and mixed noise, and extracting hidden signals.
引用
收藏
页数:11
相关论文
共 50 条
  • [41] Noise suppression of distributed acoustic sensing vertical seismic profile data based on time–frequency analysis
    Dan Shao
    Tonglin Li
    Liguo Han
    Yue Li
    Acta Geophysica, 2022, 70 : 1539 - 1549
  • [42] Distributed sensing and data collection via broken ad hoc wireless connected networks of mobile robots
    Winfield, AFT
    DISTRIBUTED AUTONOMOUS ROBOTIC SYSTEMS, 2000, : 273 - 282
  • [43] Noise suppression of distributed acoustic sensing vertical seismic profile data based on time-frequency analysis
    Shao, Dan
    Li, Tonglin
    Han, Liguo
    Li, Yue
    ACTA GEOPHYSICA, 2022, 70 (04) : 1539 - 1549
  • [44] Exposure Time Simulation Thanks to the LIP (Logarithmic Image Processing) Model with Noise Reduction by Deep Convolutional Neural Networks
    Carre, M.
    Jourlin, M.
    PROCEEDINGS OF THE 2ND INTERNATIONAL CONFERENCE ON ADVANCES IN SIGNAL PROCESSING AND ARTIFICIAL INTELLIGENCE, ASPAI' 2020, 2020, : 46 - 49
  • [45] Single binding of data and model parallelisms to parallelize convolutional neural networks through multiple machines
    Jin, Hai
    Qamar, Saqib
    Zheng, Ran
    Ahmad, Parvez
    JOURNAL OF INTELLIGENT & FUZZY SYSTEMS, 2018, 35 (05) : 5449 - 5466
  • [46] Spectral Imagery Tensor Decomposition for Semantic Segmentation of Remote Sensing Data through Fully Convolutional Networks
    Lopez, Josue
    Torres, Deni
    Santos, Stewart
    Atzberger, Clement
    REMOTE SENSING, 2020, 12 (03)
  • [47] 62 km COTDR for Long-Distance Distributed Temperature Sensing with a Noise-Reduction Signal Processing Method
    Song, Muping
    Wu, Ying
    Zhu, Weiji
    Zhuang, Shouwang
    Wang, Yixuan
    2018 ASIA COMMUNICATIONS AND PHOTONICS CONFERENCE (ACP), 2018,
  • [48] Convolutional neural network-based classification of microseismic events originating in a stimulated reservoir from distributed acoustic sensing data
    Liu, Youfang
    Huff, Owen
    Luo, Bin
    Jin, Ge
    Simmons, James
    GEOPHYSICAL PROSPECTING, 2022, 70 (05) : 904 - 920
  • [49] Siamese network based noise elimination of artificial seismic data recorded by distributed fiber-optic acoustic sensing
    Shao Jie
    Wang YiBo
    Liang Xing
    Xue QingFeng
    Liang EnMao
    Shi ShuYou
    CHINESE JOURNAL OF GEOPHYSICS-CHINESE EDITION, 2022, 65 (09): : 3599 - 3609
  • [50] Classification and Localization of Fracture-Hit Events in Low-Frequency Distributed Acoustic Sensing Strain Rate with Convolutional Neural Networks
    Chen, Mengyuan
    Tang, Jin
    Zhu, Ding
    Hill, Alfred
    SPE JOURNAL, 2022, 27 (02): : 1341 - 1353