Abstract
Seismic exploration is an essential way for stratigraphic information acquisition and resource exploitation. However, the unique near surface conditions of the desert region in northwest China pose a special problem. On the one hand, compared with Gaussian noise, desert noise concentrates in the low-frequency band, which is seriously overlapped with those of the effective signals; On the other hand, its nonstationary, nonlinear, and non-Gaussian characteristics seriously affect the accuracy of weak signal recovery and increase the difficulty of noise suppression. In the collected field data, effective signals are often submerged by the intense low-frequency noise. Considering that traditional denoising methods have some limitations on this kind of noise, a new multi-scale dense connection feature fusion (MS-DCFF) denoising convolution neural network is presented in this paper. This denoising network can adaptively learn the potential features of effective signals through multi-scale feature fusion techniques and increase the degree of information exchange by utilizing the dense connections between different blocks. Moreover, we construct relatively complete training dataset containing an effective signal dataset and a noise dataset for desert low-frequency noise suppression, thereby boosting the feasibility of the network for desert noise suppression. Both simulation and field data prove that the superior performance of the proposed MS-DCFF in the aspect of low-frequency noise (mainly includes random noise and surface waves) suppression and effective signal recovery, compared with band-pass filtering, f-x filtering, and DnCNNs.
This is a preview of subscription content, log in via an institution to check access.
Similar content being viewed by others
Data availability
Because of the data confidentiality, the experimental code is not published.
Code availability
Because of the data confidentiality, the experimental code is not published.
References
Bekara M, van der Baan M (2009) Random and coherent noise attenuation by empirical mode decomposition. Geophysics 74(5):V89–V98
Cao S, Chen X (2005) The second-generation wavelet transform and its application in denoising of seismic data. Appl Geophys 2(2):70–74
Chang Y, Yan L, Liu L, Fang H, Zhong S (2019) Infrared Aerothermal Nonuniform Correction via Deep Multiscale Residual Network. IEEE Geosci Remote Sens Lett 16(7):1120–1124
Dong X, Li Y (2020) Denoising the optical fiber seismic data by using convolutional adversarial network based on loss balance. IEEE T Geosci Remote 1–11. https://doi.org/10.1109/TGRS.2020.3036065
Dong XT, Li Y, Yang BJ (2019) Desert low-frequency noise suppression by using adaptive DnCNNs based on the determination of high-order statistic. Geophys J Int 219(2):1281–1299
Harris PE, White RE (1997) Improving the performance of f-x prediction filtering at low signal-to-noise ratios. Geophys Prospect 45(2):269–302
Hongying L, Bingjie C, Zhongmin S, Tianji X (2013) Gas and water reservoir differentiation by time-frequency analysis: a case study in southwest China. Acta Geod Geophys 48(4):439–450
Ioffe S and Szegedy C (2015) Batch normalization: Accelerating deep network training by reducing internal covariate shift. In: 32nd International Conference on Machine Learning.
Jiang X, Wang N, Xin J, Yang X, Yu Y, Gao X (2020) Image super-resolution via multi-view information fusion networks. Neurocomput (Amsterdam) 402:29–37
Kaur H, Fomel S, Pham N (2020) Seismic ground-roll noise attenuation using deep learning. Geophys Prospect 68(7):2064–2077
Kong D, Peng Z, Fan H, He Y (2016) Seismic random noise attenuation using directional total variation in the shearlet domain. J Seism Explor 25(4):321–338
Langston CA, Mousavi SM (2019) Separating signal from noise and from other signal using nonlinear thresholding and scale-time windowing of continuous wavelet transforms. B Seismol Soc Am 109(5):1691–1700
Li M, Li Y, Wu N, Tian Y, Wang T (2020) Desert seismic random noise reduction framework based on improved PSO-SVM. Acta Geod Geophys 55(1):101–117
Li Y, Li L, Zhang C (2019) Desert seismic signal denoising by 2D compact variational mode decomposition. J Geophys Eng 16(6):1048–1060
Lin T, Dollar P, Girshick R, He KM, Hariharan B, Belongie S (2017) Feature Pyramid Networks for Object Detection. In: Proceedings in 30th IEEE Conference on Computer Vision and Pattern Recognition
Liu W, Anguelov D, Erhan D, Szegedy C, Reed S, Fu CY, Berg AC (2016) SSD: single shot multibox detector lecture notes in computer science. Springer, Cham
Mousavi SM, Langston CA, Horton SP (2016) Automatic microseismic denoising and onset detection using the synchrosqueezed continuous wavelet transform. Geophysics 81(4):V341–V355
Mousavi SM, Langston CA (2016) Hybrid seismic denoising using higher-order statistics and improved wavelet block thresholding. B Seismol Soc Am 106(4):1380–1393
Mousavi SM, Langston CA (2017) Automatic noise-removal/signal-removal based on general cross-validation thresholding in synchrosqueezed domain and its application on earthquake data. Geophysics 82(4):V211–V227
Mousavi SM, Zhu W, Ellsworth W, Beroza G (2019) Unsupervised clustering of seismic signals using deep convolutional autoencoders. IEEE Geosci Remote Sens Lett 16(11):1693–1697
Nah S, Kim TH, Lee KM (2017) Deep Multi-scale Convolutional Neural Network for Dynamic Scene Deblurring. In: Proceedings in 30th IEEE Conference on Computer Vision and Pattern Recognition
Sun X, Li Y (2020) Application of adaptive iterative low-rank algorithm based on transform domain in desert seismic signal analysis. Acta Geod Geophys 55(1):151–162
Wang F, Chen S (2019) Residual learning of deep convolutional neural network for seismic random noise attenuation. IEEE Geosci Remote Sens Lett 16(8):1314–1318
Yang H, Long Y, Lin J, Zhang F, Chen ZB (2017) A seismic interpolation and denoising method with curvelet transform matching filter. Acta Geophys 65(5):1029–1042
Yin S, Wang Y, Yang Y (2019) A novel residual dense pyramid network for image dehazing. Entropy (Basel, Switzerland) 21(11):1123
Yuan Y, Si X, Zheng Y (2020) Ground-roll attenuation using generative adversarial networks. Geophysics 85(4):WA255–WA267
Zhang C, Li Y, Lin HB, Yang BJ, Wu N (2015) Adaptive threshold based Shearlet transform noise attenuation method for surface microseismic data. In: 77th EAGE Conference & Exhibition
Zhang J, Tao D (2020) 2019;) FAMED-Net: a fast and accurate multi-scale end-to-end dehazing network. IEEE Trans Image Process 29:72–84
Zhao Y, Li Y, Dong X, Yang B (2019) Low-frequency noise suppression method based on improved DnCNN in desert seismic data. IEEE Geosci Remote Sens Lett 16(5):811–815
Zhu W, Mousavi SM, Beroza GC (2019) Seismic signal denoising and decomposition using deep neural networks. IEEE T Geosci Remote 57(11):9476–9488
Acknowledgments
This research is financially supported by the National Natural Science Foundations of China (grant nos. 41730422 and 41974143).
Funding
This work was supported by the National Natural Science Foundations of China (Grant numbers 41730422 and 41974143).
Author information
Authors and Affiliations
Contributions
Conceptualization: Yue Li; Methodology and analysis: Zhen Zhao; Writing—original draft preparation: Yanan Tian; Writing—review and editing: Qiankun Feng.
Corresponding author
Ethics declarations
Conflict of interest
The authors have no relevant financial or non-financial interests to disclose.
Rights and permissions
About this article
Cite this article
Li, Y., Zhao, Z., Tian, Y. et al. Multi-scale DCFF network: a new desert low-frequency noise suppression method. Acta Geod Geophys 56, 357–371 (2021). https://doi.org/10.1007/s40328-021-00339-3
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s40328-021-00339-3