Skip to main content

Advertisement

SpringerLink
Log in

Deep Learning with Fully Convolutional and Dense Connection Framework for Ground Roll Attenuation

  • Published:
Surveys in Geophysics Aims and scope Submit manuscript

Abstract

Ground roll could seriously mask the useful reflection signals and decrease the signal-to-noise ratio (S/N) of seismic data, thereby affecting the subsequent seismic data processing. It is challenging for traditional methods to effectively extract high-fidelity reflection signals when ground roll noise and low-frequency reflection signals overlap in the frequency domain. We propose a fully convolutional framework with dense connections to attenuate ground roll (GRDNet) in land seismic data. GRDNet mainly consists of four blocks, which are convolutional, dense, transition down, and transition up blocks. The dense block consists of several convolution blocks to extract the waveform features of the seismic data. The short-long connection in the dense block and the skip connection in the encoder-decoder not only reuses the features extracted by the previous layer but also adds constraints other than the loss function to each convolution block. The well-trained network is tested on one synthetic data and two real land seismic datasets containing strong ground roll with linear and hyperbolic moveouts, respectively. Three traditional and two state-of-the-art deep learning (DL) methods are used as benchmarks to compare denoising performance with GRDNet. The testing results show that the proposed method can effectively attenuate the ground roll in seismic data and preserve useful reflection signals.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5
Fig. 6
Fig. 7
Fig. 8
Fig. 9
Fig. 10
Fig. 11
Fig. 12
Fig. 13
Fig. 14
Fig. 15
Fig. 16
Fig. 17
Fig. 18
Fig. 19
Fig. 20
Fig. 21
Fig. 22
Fig. 23
Fig. 24
Fig. 25
Fig. 26

Similar content being viewed by others

Data Availability

Data associated with this research are available and can be obtained by contacting the corresponding author.

Code Availability

Code associated with this research are available and can be obtained by contacting the corresponding author.

References

  • Arik SO, Jun H, Diamos G (2019) Fast Spectrogram inversion using multi-head convolutional neural networks. IEEE Signal Process Lett 26:94–98

    Article  Google Scholar 

  • Biswas R, Sen MK, Das V et al (2019) Prestack and poststack inversion using a physics-guided convolutional neural network. Interpetation 7:SE161–SE174

    Article  Google Scholar 

  • Chaudhary A (2020) A visual guide to self-labelling images. arXiv preprint arXiv:1502.03167

  • Chen S, Cao S, Sun Y et al (2022) Seismic time-frequency analysis via time-varying filtering based empirical mode decomposition method. J Appl Geophys 204(104):731

    Google Scholar 

  • Chen W, Chen Y, Liu W (2016) Ground roll attenuation using improved ccomplete ensemble empirical mode decomposition. J Seism Explorat 25:485–495

    Google Scholar 

  • Chen W, Yang L, Zha B et al (2020) Deep learning reservoir porosity prediction based on multilayer long short-term memory network. Geophysics 85:WA213–WA225

    Article  Google Scholar 

  • Chen Y (2021) Nonstationary local time-frequency transform. Geophysics 86:V245–V254

    Article  Google Scholar 

  • Chen Y, Jiao S, Ma J et al (2015) Ground-Roll noise attenuation using a simple and effective approach based on local band-limited orthogonalization. IEEE Geosci Remote Sens Lett 12:2316–2320

    Article  Google Scholar 

  • Chen Y, Zhang G, Bai M et al (2019) Automatic waveform classification and arrival picking based on convolutional neural network. Earth Space Sci 6:1244–1261

    Article  Google Scholar 

  • Colombo D, Turkoglu E, Li W et al (2021) Physics-driven deep-learning inversion with application to transient electromagnetics. Geophysics 86:E209–E224

    Article  Google Scholar 

  • Deighan AJ, Watts DR (1997) Ground-roll suppression using the wavelet transform. Geophysics 62:1896–1903

    Article  Google Scholar 

  • Fang J, Zhou H, Li YE et al (2021) Data-driven low-frequency signal recovery using deep-learning predictions in full-waveform inversion. Geophysics 85:A37–A43

    Article  Google Scholar 

  • Fomel S (2002) Applications of plane-wave destruction filters. Geophysics 67:1946–1960

    Article  Google Scholar 

  • Fomel S (2013) Seismic data decomposition into spectral components using regularized nonstationary autoregression. Geophysics 78:O69–O76

    Article  Google Scholar 

  • Foti S, Sambuelli L, Socco L, et al (2002) Spatial sampling issues in FK analysis of surface waves. Presented at the symposium on the application of geophysics to engineering and environmental problems. Las Vegas, Nevada, February 10–14

  • Gao H, Yuan H, Wang Z et al (2020) Pixel transposed convolutional networks. IEEE Trans Patt Analy Mach Intell 42:1218–1227

    Google Scholar 

  • Gelisli K, Karsli H (1998) F-K filtering using the Hartley transform. J Seism Explorat 7:101–107

    Google Scholar 

  • Glorot X, Bordes A, Bengio Y (2011) Deep sparse rectifier neural networks. J Mach Learn Res 15:315–323

    Google Scholar 

  • Halliday D (2011) Adaptive interferometry for ground-roll suppression. Lead Edge 30(5):532–537

    Article  Google Scholar 

  • He K, Zhang X, Ren S et al (2015) Delving deep into rectifiers: surpassing human-level performance on imagenet classification. IEEE Int Conf Comput Vis 20:1026–1034

    Google Scholar 

  • Henley DC (2003) Coherent noise attenuation in the radial trace domain. Geophysics 68:1408–1416

    Article  Google Scholar 

  • Hosseini SA, Javaherian A, Hassani H et al (2015) Adaptive attenuation of aliased ground roll using the shearlet transform. J Appl Geophys 112:190–205

    Article  Google Scholar 

  • Huang G, Liu Z, Maaten LVD, et al. (2017) Densely connected convolutional networks. In: IEEE conference on computer vision and pattern recognition pp 2261–2269

  • Ioffe S, Szegedy C (2015) Batch normalization: accelerating deep network training by reducing internal covariate shift. arXiv preprint arXiv:1502.03167

  • Ji Y, Kragh E, Bagaini C (2010) Noise attenuation methods for point-receiver land seismic data. 80th SEG Annual International Meeting, Expanded Abstracts, 29:3545–3549

  • Jia Z, Lu W (2020) Blind separation of ground-roll using interband morphological similarity and pattern coding. IEEE Trans Geosci Remote Sens 58:7166–7177

    Article  Google Scholar 

  • Jiang X, Liu S, Dai X et al. (2022) Deep metric learning based on meta-mining strategy with semiglobal information. IEEE Trans Neural Networks Learn Syst. https://doi.org/10.1109/TNNLS.2022.3202571

    Article  Google Scholar 

  • Jiao S, Chen Y, Bai M et al (2015) Ground roll attenuation using non-stationary matching filtering. J Geophys Eng 12:922

    Article  Google Scholar 

  • Jones IF, Levy S (1987) Signal-to-noise ratio enhancement in multi-channel seismic data via the Karhunen-Loeve transform. Geophys Prospect 35:12–32

    Article  Google Scholar 

  • de Jonge T, Vinje V, Poole G et al (2022) Debubbling seismic data using a generalized neural network. Geophysics 87(1):V1–V14

    Article  Google Scholar 

  • Karsli H, Bayrak Y (2004) Using the wiener-levinson algorithm to suppress ground-roll. J Appl Geophys 55:187–197

    Article  Google Scholar 

  • Kaur H, Fomel S, Pham N (2020) Seismic ground-roll noise attenuation using deep learning. Geophys Prospect 68:2064–2077

    Article  Google Scholar 

  • Kingma DP, Ba J (2014) Adam: a method for stochastic optimization. arXiv preprint arXiv::14126980

  • Krizhevsky A, Sutskever I, Hinton GE (2017) Imagenet classification with deep convolutional neural networks. Commun ACM 69:84–90

    Article  Google Scholar 

  • Li H, Yang W, Yong X (2018) Deep learning for ground–roll noise attenuation. 75th Annual International Meeting, SEG, Expanded Abstracts pp 1981–1985

  • Li H, Chen D, Chang D (2019) Ground-roll noise attenuation based on convolutional neural network. In: 76th annual international meeting, SEG, expanded abstracts pp 1981–1985

  • Li S, Liu B, Ren Y et al (2020) Deep-learning inversion of seismic data. IEEE Trans Geosci Remote Sens 58:2135–2149

    Article  Google Scholar 

  • Li Y, Wang H, Dong X (2020) The denoising of desert seismic data based on cycle-GAN with unpaired data training. IEEE Geosci Remote Sens Lett 18:2016–2020

    Article  Google Scholar 

  • Liu G, Chen X, Du J et al (2012) Random noise attenuation using f-x regularized nonstationary autoregression. Geophysics 77(2):V61–V69

    Article  Google Scholar 

  • Liu X (1999) Ground roll suppression using the Karhunen-Loeve transform. Geophysics 64:564–566

    Article  Google Scholar 

  • Liu Y, Fomel S (2012) Seismic data analysis using local time-frequency decomposition. Geophys Prospect 61:516–525

    Article  Google Scholar 

  • Liu Z, Chen Y, Ma J (2018) Ground roll attenuation by synchrosqueezed curvelet transform. J Appl Geophys 151:246–262

    Article  Google Scholar 

  • Mousavi SM, Ellsworth WL, Zhu W et al (2020) Earthquake transformer-an attentive deep-learning model for simultaneous earthquake detection and phase picking. Nature Commun 11:3952

    Article  Google Scholar 

  • Naghizadeh M, Sacchi M (2018) Ground-roll attenuation using curvelet downscaling. Geophysics 83:V185–V195

    Article  Google Scholar 

  • Oliveira DAB, Semin DG, Zaytsev S (2020) Self-supervised ground roll noise attenuation using self-labeling and paired data synthesis. IEEE Trans Geosci Remote Sens 59(8):7147–7159

    Article  Google Scholar 

  • Pham N, Li W (2022) Physics-constrained deep learning for ground roll attenuation. Geophysics 87:V15–V27

    Article  Google Scholar 

  • Rango R (1989) Suppression of ground roll by windowing in two domains. First Break 7:55–63

    Google Scholar 

  • Saad OM, Chen Y (2020) Deep denoising autoencoder for seismic random noise attenuation. Geophysics 85:V367–V376

    Article  Google Scholar 

  • Saatcilar R, Canitez N (1988) A method of ground-roll elimination. Geophysics 53:894–902

    Article  Google Scholar 

  • Salamon J, Bello JP (2017) Deep convolutional neural networks and data augmentation for environmental sound classification. IEEE Signal Process Lett 24:279–283

    Article  Google Scholar 

  • Siahkoohi A, Louboutin M, Herrmann FJ (2019) The importance of transfer learning in seismic modeling and imaging. Geophysics 84:A47–A52

    Article  Google Scholar 

  • Srivastava N, Hinton G, Krizhevsky A et al (2014) Dropout: a simple way to prevent neural networks from overfitting. J Mach Learn Res 15:1929–1958

    Google Scholar 

  • Strobbia C, Zarkhidze A, May R, et al (2011) Model-based coherent noise attenuation for complex dispersive waves. In: 68th annual international meeting, SEG, expanded abstracts pp 3571–3575

  • Tenorio L (2001) Modeling non-Gaussian reflectivities: Generalizing Wiener-Levinson deconvolution. Geophysics 66:1913–1920

  • Verma S, Guo S, Ha T et al (2016) Highly aliased ground-roll suppression using a 3D multiwindow Karhunen-Loeve filter: application to a legacy Mississippi Lime survey. Geophysics 81:V79–V88

    Article  Google Scholar 

  • Wang C, Huang X, Li KY, Jensen F (2023) Removing multiple types of noise of distributed acoustic sensing seismic data using attention-guided denoising convolutional neural network. Front Earth Sci. https://doi.org/10.3389/feart.2022.986,470

    Article  Google Scholar 

  • Wang H, Chen W, Huang W et al (2021) Nonstationary predictive filtering for seismic random noise suppression-A tutorial. Geophysics 86(3):W21–W30

    Article  Google Scholar 

  • Wang W, Gao J, Chen W et al (2012) Data adaptive ground-roll attenuation via sparsity promotion. J Appl Geophys 83:19–28

    Article  Google Scholar 

  • Wu H, Zhang B, Li F et al (2019) Semiautomatic first-arrival picking of microseismic events by using the pixel-wise convolutional image segmentation method. Geophysics 84:V143–V155

    Article  Google Scholar 

  • Wu X, Geng Z, Shi Y et al (2020) Building realistic structure models to train convolutional neural networks for seismic structural interpretation. Geophysics 85(4):WA27–WA39

    Article  Google Scholar 

  • Yang L, Chen W, Wang H et al (2021) Deep learning seismic random noise attenuation via improved residual convolutional neural network. IEEE Trans Geosci Remote Sens 59:7968–7981

    Article  Google Scholar 

  • Yang L, Wang S, Wang S et al (2021) Unsupervised 3-D random noise attenuation using deep skip autoencoder. IEEE Trans Geosci Remote Sens. https://doi.org/10.1109/TGRS.2021.3100,455

    Article  Google Scholar 

  • Yuan Y, Si X, Zheng Y (2020) Ground-roll attenuation using generative adversarial networks. Geophysics 85:255–267

    Article  Google Scholar 

  • Zheng J, Yin X, Zhang G et al (2010) The surface wave suppression using the second generation curvelet transform. Appl Geophys 7:325–335

    Article  Google Scholar 

  • Zhou Y, Yang J, Wang H et al (2021) Statistics-guided dictionary learning for automatic coherent noise suppression. IEEE Trans Geosci Remote Sens. https://doi.org/10.1109/TGRS.2020.3039,738

    Article  Google Scholar 

Download references

Acknowledgements

This work was supported in part by the National Key R &D Program of China under Grant 2019YFC0312003, in part by the Strategic Cooperation Technology Projects of CNPC and CUPB under Grant ZLZX2020-03, and in part by the R &D Department of China National Petroleum Corporation (Investigations on fundamental experiments and advanced theoretical methods in geophysical prospecting applications) under Grant 2022DQ0604-04.

Funding

This work was supported in part by the National Key R &D Program of China under Grant 2019YFC0312003, in part by the Strategic Cooperation Technology Projects of CNPC and CUPB under Grant ZLZX2020-03, and in part by the R &D Department of China National Petroleum Corporation (Investigations on fundamental experiments and advanced theoretical methods in geophysical prospecting applications) under Grant 2022DQ0604-04.

Author information

Authors and Affiliations

  1. State Key Laboratory of Petroleum Resources and Prospecting, China University of Petroleum (Beijing), Beijing, 102249, Beijing, China

    Liuqing Yang, Shoudong Wang, Xiaohong Chen & Wanli Cheng

  2. National Engineering Laboratory of Offshore Oil Exploration, China University of Petroleum (Beijing), Beijing, 102249, Beijing, China

    Liuqing Yang, Shoudong Wang, Xiaohong Chen & Wanli Cheng

  3. ENSN Lab, Seismology Department, National Research Institute of Astronomy and Geophysics (NRIAG), Helwan, 11731, Egypt

    Omar M. Saad

  4. Bureau of Economic Geology, John A. and Katherine G. Jackson School of Geosciences, The University of Texas at Austin, Austin, 78712, TX, USA

    Yangkang Chen

Authors
  1. Liuqing Yang
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Shoudong Wang
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Xiaohong Chen
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Omar M. Saad
    View author publications

    You can also search for this author in PubMed Google Scholar

  5. Wanli Cheng
    View author publications

    You can also search for this author in PubMed Google Scholar

  6. Yangkang Chen
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Shoudong Wang.

Ethics declarations

Conflict of interest

Not applicable.

Ethics Approval

Not applicable.

Additional information

Publisher's Note

Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Rights and permissions

Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Yang, L., Wang, S., Chen, X. et al. Deep Learning with Fully Convolutional and Dense Connection Framework for Ground Roll Attenuation. Surv Geophys 44, 1919–1952 (2023). https://doi.org/10.1007/s10712-023-09779-8

Download citation

  • Received:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s10712-023-09779-8

Keywords

Search

Navigation