Abstract
High-frequency surface-wave methods have been widely used for surveying near-surface shear-wave velocities. A key step in high-frequency surface-wave methods is to acquire dispersion curves in the frequency–velocity domain. The traditional way to acquire the dispersion curves is to identify the dispersion energy and manually pick phase velocities by following energy peaks at different frequencies. A large number of dispersion curves need to be extracted for inversion, especially for surveys with long two-dimensional sections or large three-dimensional (3D) coverages. Human–machine interaction-based dispersion curves extraction, however, is still common, which is time-consuming. We developed a deep learning model, termed Dispersion Curves Network (DCNet), that can rapidly extract dispersion curves from dispersion images by treating dispersion curves extraction as an instance segmentation task. The accuracy of the dispersion curves extracted by our DCNet model is demonstrated by theoretical data. We used a 3D field application of ambient seismic noise to demonstrate the effectiveness and robustness of our method. The real-world results showed that the accuracy of the dispersion curves extracted from the field data using our method can achieve human-level performance and our method can meet the requirement of geoengineering surveys in rapidly extracting massive dispersion curves of surface waves.
Similar content being viewed by others
References
Abadi M, Barham P, Chen J, Chen Z, Davis A, Devin M et al (2016) TensorFlow: a system for large-scale machine learning. In: Proceedings of the 12th USENIX symposium on operating systems design and implementation, pp 265–283
Badrinarayanan V, Kendall A, Cipolla R (2017) SegNet: a deep convolutional encoder-decoder architecture for image segmentation. IEEE Trans Pattern Anal Mach Intell 39(12):2481–2495
Bai M, Urtasun R (2017) Deep watershed transform for instance segmentation. arXiv:1802.05591v1 [cs.CV]. https://arxiv.org/abs/1802.05591
Bensen GD, Ritzwoller MH, Barmin MP, Levshin AL, Lin F, Moschetti MP, Shaoiro NM, Yang Y (2007) Processing seismic ambient noise data to obtain reliable broad-band surface wave dispersion measurements. Geophys J Int 169:1239–1260
Boaga J, Vignoli G, Cassiani G (2011) Shear wave profiles from surface wave inversion: the impact of uncertainty on seismic site response analysis. J Geophys Eng 8(2):162–174
Bohlen T, Kugler S, Klein G, Theilen F (2004) 1.5D inversion of lateral variation of Scholte wave dispersion. Geophysics 69(2):330–344
Boiero D, Socco LV (2010) Retrieving lateral variations from surface wave dispersion curves. Geophys Prospect 58(6):977–996
Caruana R (1997) Multitask learning. Mach Learn 28(1):41–75
Chen H, Sun K, Tian Z, Shen C, Huang Y, Yan Y (2020) BlendMask: top-down meets bottom-up for instance segmentation. arXiv:2001.00309v1 [cs.CV]. https://arxiv.org/abs/2001.00309
Cheng F, Xia J, Xu Y, Xu Z, Pan Y (2015) A new passive seismic method based on seismic interferometry and multichannel analysis of surface waves. J Appl Geophys 117:126–135
Cheng F, Xia J, Luo Y, Xu Z, Wang L, Shen C, Liu R, Pan Y, Mi B, Hu Y (2016) Multichannel analysis of passive surface waves based on cross-correlations. Geophysics 81(5):EN57–EN66
Cheng F, Xia J, Xu Z, Mi B (2018a) Frequency-wavenumber (FK)-based data selection in high-frequency passive surface wave survey. Surv Geophys 39(4):661–682
Cheng F, Xia J, Xu Z, Hu Y, Mi B (2018b) Automated data selection in the Tau-p domain: application to passive surface wave imaging. Surv Geophys 40(5):1211–1228
Dai J, He K, Sun J (2015) Instance-aware semantic segmentation via multi-task network cascades. arXiv:1512.04412v1 [cs.CV]. https://arxiv.org/abs/1512.04412
Dai T, Hu Y, Ning L, Cheng F, Pang J (2018a) Effects due to aliasing on the surface-wave extraction and suppression in frequency-velocity domain. J Appl Geophys 158:71–81
Dai T, Xia J, Ning L (2018b) Extracting dispersion curves using semantic segmentation of fully convolutional networks. In: Proceeding of 8th international conference on environmental and engineering geophysics, pp 150–155
Daley T, Freifeld B, Ajo-Frankline J, Dou S, Pevzner R, Shulakova V, Kashikar S, Miller D, Götz J, Henninges J, Lüth S (2013) Field testing of fiber-optic distributed acoustic sensing (DAS) for subsurface seismic monitoring. Lead Edge 32(6):699–706
De Brabandere B, Neven D, Van Gool L (2017) Semantic instance segmentation with a discriminative loss function. arXiv:1708.02551v1 [cs.CV]. https://arxiv.org/abs/1708.02551
Ester M, Kriegel HP, Sander J, Xu X (1996) A density-based algorithm for discovering clusters in large spatial databases with noise. In: Proceedings of 2nd international conference on knowledge discovery and data mining (KDD-96)
Evgeniou T, Pontil M (2004) Regularized multi-task learning. In: Proceedings of the 10th ACM SIGKDD international conference on knowledge discovery and data mining, pp 109–117
Foti S, Parolai S, Albarello D, Picozzi M (2011) Application of surface-wave methods for seismic site characterization. Surv Geophys 32:777–825
Groos JC, Bussat S, Ritter JRR (2012) Performance of different processing schemes in seismic noise cross-correlations. Geophys J Int 188:498–512
He K, Gkioxari G, Dollár P, Girshick R (2017) Mask R-CNN. arXiv:1703.06870 [cs.CV]. https://arxiv.org/abs/1703.06870
Howard AG (2013) Some improvements on deep convolutional neural network based image classification. arXiv:1312.5402 [cs.CV]. https://arxiv.org/abs/1312.5402
Hu Y, Wang L, Cheng F, Luo Y, Shen C, Mi B (2016) Ground-roll noise extraction and suppression using high-resolution linear Radon transform. J Appl Geophys 128:8–17
Ikeda T, Tsuji T (2015) Advanced surface-wave analysis for 3D ocean bottom cable data to detect localized heterogeneity in shallow geological formation of a CO2 storage site. Int J Greenhouse Gas Control 39:107–118
Ikeda T, Tsuji T, Matsuoka T (2013) Window-controlled CMP cross-correlation analysis for surface waves in laterally heterogeneous media. Geophysics 78(6):EN96–EN105
Ivanov J, Miller RD, Lacombe P, Johnson CD, Lane JW (2006) Delineating a shallow fault zone and dipping bedrock strata using multi-channel analysis of surface waves with a land streamer. Geophysics 71(5):A39–A42
Kingma DP, Ba J (2014) Adam: a method for stochastic optimization. arXiv:1412.6980 [cs.LG]. https://arxiv.org/abs/1412.6980
Lawrence JF, Denolle M, Seats KJ, Prieto G (2013) A numeric evaluation of attenuation from ambient noise correlation functions. J Geophys Res Solid Earth 188(12):6134–6145
LeCun Y, Bengio Y, Hinton G (2015) Deep learning. Nature 521(7553):436–444
Long J, Shelhamer E, Darrell T (2015) Fully convolutional networks for semantic segmentation. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 3431–3440
Louie JN (2001) Faster, better: shear-wave velocity to 100 meters depth from refraction microtremor arrays. Bull Seismol Soc Am 91(2):347–364
Luo Y, Xia J, Liu J, Liu Q, Xu S (2007) Joint inversion of high-frequency surface waves with fundamental and higher modes. J Appl Geophys 62(4):375–384
Luo Y, Xia J, Miller RD, Xu Y, Liu J, Liu Q (2008) Rayleigh-wave dispersive energy imaging using a high-resolution linear Radon transform. Pure Apply Geophys 165(5):903–922
Luo Y, Xia J, Miller RD, Xu Y, Liu J, Liu Q (2009a) Rayleigh-wave mode separation by high-resolution linear Radon transform. Geophys J Int 179(1):254–264
Luo Y, Xia J, Liu J, Xu Y, Liu Q (2009b) Research on the middle-of receiver-spread assumption of the MASW method. Soil Dyn Earthq Eng 29:71–79
Luo Y, Xia J, Xu Y, Zeng C, Liu J (2010) Finite-difference modeling and dispersion analysis of high-frequency Love waves for near-surface applications. Pure Appl Geophys 167:1525–1536
Mao B, Han L, Feng Q, Yin Y (2019) Subsurface velocity inversion from deep learning-based data assimilation. J Appl Geophys 167:172–179
McMechan GA, Yedlin MJ (1981) Analysis of dispersive waves by wave field transformation. Geophysics 46:869–874
Mi B, Xia J, Shen C, Wang L, Hu Y, Cheng F (2017) Horizontal resolution of multichannel analysis of surface waves. Geophysics 82(3):EN51–EN66
Mi B, Xia J, Bradford JH, Shen C (2020) Estimating near-surface shear-wave-velocity structures via multichannel analysis of Rayleigh and Love waves: an experiment at the Boise Hydrogeophysical research site. Surv Geophys. https://doi.org/10.1007/s10712-019-09582-4
Neven D, De Brabandere B, Georgoulis S, Proesmans M, Van Gool L (2018) Towards end-to-end lane detection: an instance segmentation approach. arXiv:1802.05591 [cs.CV]. https://arxiv.org/abs/1802.05591
Ning ILC, Sava P (2018) High-resolution multicomponent distributed acoustic sensing. Geophys Prospect 66(6):1111–1122
Okada H (2003) Microtremor survey method. Geophysical Monograph Series, vol 12. Society of Exploration Geophysicists, Tulsa
Ovcharenko O, Kazei V, Kalita M, Peter D, Alkhalifah T (2019) Deep learning for low-frequency extrapolation from multi-offset seismic data. Geophysics 84(6):R1001–R1013
Pan Y, Xia J, Xu Y, Gao L (2016a) Multichannel analysis of Love waves in a 3D seismic acquisition system. Geophysics 81:EN67–EN74
Pan Y, Xia J, Xu Y, Xu Z, Cheng F, Xu H, Gao L (2016b) Delineating shallow S-wave velocity structure using multiple ambient-noise surface-wave methods: an example from western Junggar, China. Bull Seismol Soc Am 106(2):327–336
Pan Y, Schaneng S, Steinweg T, Bohlen T (2018) Estimating S-wave velocities from 3D 9-component shallow seismic data using local Rayleigh-wave dispersion curves—a field study. J Appl Geophys 159:532–539
Pan Y, Gao L, Bohlen T (2019) High-resolution characterization of near-surface structures by surface-wave inversions: from dispersion curve to full waveform. Surv Geophys 40:167–195
Pang J, Cheng F, Shen C, Dai T, Ning L, Zhang K (2019) Automatic passive data selection in time domain for imaging near-surface surface waves. J Appl Geophys 162:108–117
Park CB, Miller RD (2008) Roadside passive multichannel analysis of surface waves (MASW). J Eng Environ Geophys 13(1):1–11
Park CB, Miller M, Xia J (1998) Imaging dispersion curves of surface waves on multi-channel record. In: Society of Exploration and Geophysics (SEG), 68th Annual Meeting, New Orleans, Louisiana, pp 1377–1380
Paszke A, Chaurasia A, Kim S, Culurciello E (2016) ENet: a deep neural network architecture for real-time semantic segmentation. arXiv:1606.02147 [cs.CV]. http://arxiv.org/abs/1606.02147
Perol T, Gharbi M, Denolle M (2018) Convolutional neural network for earthquake detection and location. Sci Adv 4(2):e1700578
Pilz M, Parolai S, Bindi D (2013) Three-dimensional passive imaging of complex seismic fault systems: evidence of surface traces of the Issyk-Ata fault (Kyrgyzstan). Geophys J Int 194:1955–1965
Ren M, Zemel RS (2017) End-to-end instance segmentation with recurrent attention. arXiv:1605.09410 [cs.CV]. http://arxiv.org/abs/1605.09410
Romera-Paredes B, Torr PHS (2016) Recurrent instance segmentation. arXiv:1511.08250 [cs.CV]. http://arxiv.org/abs/1511.08250
Ruder S (2017) An overview of multi-task learning in deep neural networks. arXiv:1706.05098 [cs.CV]. http://arxiv.org/abs/1706.05098
Ryden N, Park CB (2006) Fast simulated annealing inversion of surface waves on pavement using phase-velocity spectra. Geophysics 71(4):R49–R58
Schwab FA, Knopoff L (1972) Fast surface wave and free mode computations. In: Bolt BA (ed) Methods in computational physics. Academic Press, New York, pp 87–180
Shen C (2014) Automatically picking dispersion curves in high-frequency surface-wave method. Master Thesis, China University of Geosciences (Wuhan), Wuhan, Hubei, China
Shen C, Wang A, Wang L, Xu Z, Cheng F (2015) Resolution equivalence of dispersion-imaging methods for noise-free high-frequency surface-wave data. J Appl Geophys 122:167–171
Simonyan K, Zisserman A (2014) Very deep convolutional networks for large-scale image recognition. arXiv:1409.1556 [Cs]. http://arxiv.org/abs/1409.1556
Socco LV, Boiero D (2008) Improved Monte Carlo inversion of surface wave data. Geophys Prospect 56(3):357–371
Socco LV, Foti S, Boiero D (2010) Surface-wave analysis for building near-surface velocity models—established approaches and new perspectives. Geophysics 75(5):A83–A102
Song X, Zeng X, Thurber C, Wang HF (2019) Imaging shallow structure with active-source surface wave signal recorded by distributed acoustic sensing arrays. Earthq Sci 31:208–214
Taipodia J, Dey A, Gaj S, Baglari D (2020) Quantification of the resolution of dispersion image in active MASW survey and automated extraction of dispersion curve. Comput Geosci 135:104360. https://doi.org/10.1016/j.cageo.2019.104360
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
Wang J, Xiao Z, Liu C, Zhao D, Yao Z (2019) Deep learning for picking seismic arrival times. J Geophys Res Solid Earth. https://doi.org/10.1029/2019JB017536
Wu X, Liang L, Shi Y, Geng Z, Fomel S (2019) Multitask learning for local seismic image processing: fault detection, structure-oriented smoothing with edge-preserving, and seismic normal estimation by using a single convolutional neural network. Geophys J Int 219:2097–2109
Xia J (2014) Estimation of near-surface shear-wave velocities and quality factors using multichannel analysis of surface-wave methods. J Appl Geophys 103:140–151
Xia J, Miller RD, Park CB (1999) Estimation of near-surface shear-wave velocity by inversion of Rayleigh wave. Geophysics 64(3):691–700
Xia J, Miller RD, Park CB, Hunter JA, Harris JB, Ivanov J (2002) Comparing shear-wave velocity profiles from multichannel analysis of surface wave with borehole measurements. Soil Dyn Earthq Eng 22(3):181–190
Xia J, Miller RD, Park CB, Tian G (2003) Inversion of high frequency surface waves with fundamental and higher modes. J Appl Geophys 52(1):45–57
Xia J, Xu Y, Miller RD (2007) Generating image of dispersive energy by frequency decomposition and slant stacking. Pure Apply Geophys 164(5):941–956
Xia J, Xu Y, Luo Y, Miller RD, Cakir R, Zeng C (2012) Advantages of using Multichannel Analysis of Love Waves (MALW) to estimate near-surface shear-wave velocity. Surv Geophys 33:841–860
Yang F, Ma J (2019) Deep-learning inversion: a next-generation seismic velocity model building method. Geophysics 84(4):R583–R599
Yilmaz Ö (1987) Seismic data processing. Society of Exploration Geophysicists, Tulsa, p 526
Yin X, Xu H, Wang L, Hu Y, Shen C, Sun S (2016) Improving horizontal resolution of high-frequency surface-wave methods using travel-time tomography. J Appl Geophys 126:42–51
Zachary ER, Men-Andrin M, Egill H, Thomas HH (2018) Generalized seismic phase detection with deep learning. Bull Seismol Soc Am 108(5A):2894–2901
Zeng C, Xia J, Miller RD, Tsoflias GP (2011) Application of the multiaxial perfectly matched layer to near-surface seismic modeling with Rayleigh waves. Geophysics 76(3):T43–T52
Zhang Z, Alkhalifah T (2019a) Wave-equation Rayleigh-wave dispersion inversion using fundamental and higher modes. Geophysics 84(4):EN57–EN65
Zhang Z, Alkhalifah T (2019b) Regularized elastic full waveform inversion using deep learning. Geophysics 84(5):R741–R751
Zhang G, Wang Z, Chen Y (2018) Deep learning for seismic lithology prediction. Geophys J Int 215:1368–1387
Zhang Z, Alajami M, Alkhalifah T (2020) Wave-equation dispersion spectrum inversion for near-surface characterization using fiber-optics acquisition. Geophys J Int 222:907–918
Zhou C, Xi C, Pang J, Liu Y (2018) Ambient noise data selection based on the asymmetry of cross-correlation functions for near surface applications. J Appl Geophys 159:803–813
Acknowledgements
The authors would like to thank associate editor Yu Jeffrey Gu and two anonymous reviewers for their constructive comments and suggestions. This study is supported by the National Natural Science Foundation of China (NSFC) under Grant No. 41774115 and Nanjing Center of China Geological Survey under Grant No. DD20190281. The authors appreciate Binbin Mi, Jingyin Pang, Changjiang Zhou, Hongyu Zhang, and Xinhua Chen for their help in field data collection. The authors also appreciate Xiaojun Chang of Nanjing Center of China Geological Survey for their assistance in field data collection and providing borehole data.
Author information
Authors and Affiliations
Corresponding author
Additional information
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
About this article
Cite this article
Dai, T., Xia, J., Ning, L. et al. Deep Learning for Extracting Dispersion Curves. Surv Geophys 42, 69–95 (2021). https://doi.org/10.1007/s10712-020-09615-3
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s10712-020-09615-3