中文版 | English
题名

基于深度学习的频散曲线自动拾取

其他题名
AUTOMATIC PICKING OF DISPERSION CURVES BASED ON DEEP LEARNING
姓名
姓名拼音
SONG Weibin
学号
11930823
学位类型
博士
学位专业
0801 力学
学科门类/专业学位类别
08 工学
导师
陈晓非
导师单位
地球与空间科学系
论文答辩日期
2023-05-16
论文提交日期
2023-07-02
学位授予单位
南方科技大学
学位授予地点
深圳
摘要

在近地表勘探和大区域构造成像中,背景噪声互相关成像技术得到了
广泛的应用。然而,随着密集台阵的大量部署,可用数据的增多,致使人
工拾取频散曲线成为一项重复繁琐,耗时的过程。 常规的背景噪声成像需
要人工逐步进行从背景噪声中提取频散谱,拾取频散曲线,横波速度反演,
这需要大量的人工干预,致使获得地下结构需要较长的时间。 而全自动化
速度成像是全程无人为干预的,从数据到数据的自动化成像方法,目的是
将背景噪声数据自动转换为对应的横波速度,从而进行速度结构实时扫描
成像,减少人为的干预,而频散曲线自动拾取就是全自动化成像的关键。
随着大数据时代的到来,深度学习受到了广大科研人员的关注。 本文
提出了一种基于深度学习的自动拾取频散曲线的方法。该方法使用卷积神
经网络学习频散谱中频散曲线的特征,从而进行频散曲线的自动拾取。经
过卷积神经网络的处理,从频散谱中去除非频散曲线的能量,得到高信噪
比的频散谱。 该方法可以在频散曲线拾取中节省大量的时间和精力。
由于不同类型频散谱存在特征差异, 卷积神经网络处理不同数据时会
存在一些性能的差异,主要表现为频散曲线识别过少或者噪声去除过少。
文中引入了基于域自适应技术的方法,该方法可以动态地调整卷积神经网
络的识别结果,较好地改善卷积神经网络的结果,使得它可以识别到更多
的频散点。同样的,由于数据间的特征差异,使用不同类型数据训练同一
卷积神经网络时, 它并不能较好地学习不同类型的特征,致使实际的训练
结果不理想。 文中引入了域模糊技术, 该技术可以拉近训练集各样本之间
的距离,有利于卷积神经网络的训练,从而提升卷积神经网络的性能。域
自适应和域模糊都是对数据进行特征处理,从而降低卷积神经网络的区域
性,提升频散曲线的识别效果。
本文对频散曲线自动拾取进行了系统性研究,提出了利用卷积神经网
络自动拾取多阶频散曲线的方法, 利用域自适应和域模糊解决数据特征多
样性导致的区域性问题。该文的研究使得卷积神经网络自动拾取频散曲线
从方法上到实际应用上均得到了较大的进步。频散曲线自动拾取是全自动
化速度成像的核心,可以有效推动全自动化成像的发展,具有重要意义。
 

关键词
语种
中文
培养类别
独立培养
入学年份
2019
学位授予年份
2023-06
参考文献列表

[1] AKI, K. Space and time spectra of stationary stochastic waves, with special referenceto microtremors[J]. Bulletin of the Earthquake Research Institute, 1957, 35, 415–456.
[2] ARFKEN, G., WEBER, H., & HARRIS, F. Mathematical methods for physicists: Acomprehensive guide 7th ed[M]. London: Academic Press, 2012.
[3] BADRINARAYANAN, V., KENDALL, A., & CIPOLLA, R. Segnet: A deepconvolutional encoder-decoder architecture for image segmentation[J]. IEEETransactions on Pattern Analysis and Machine Intelligence, 2017, 39(12), 2481–2495.doi: 10.1109/TPAMI.2016.2644615
[4] BENSEN, G. D., RITZWOLLER, M. H., BARMIN, M. P., et al. Processing seismicambient noise data to obtain reliable broad-band surface wave dispersionmeasurements[J]. Geophysical Journal International, 2007, 169(3), 1239–1260. doi:https://doi.org/10.1111/j.1365-246X.2007.03374.x
[5] BENSEN, G. D., RITZWOLLER, M. H., & YANG, Y. A 3-D shear velocity model ofthe crust and uppermost mantle beneath the United Statesfrom ambient seismic noise[J].Geophysical Journal International, 2009, 177(3), 1177–1196.https://doi.org/10.1111/j.1365-246X.2009.04125.x
[6] BI, Z., WU, X., GENG, Z., et al. Deep relative geologic time: A deep learning methodfor simultaneously interpreting 3-D seismic horizons and faults[J]. Journal ofGeophysical Research: Solid Earth, 2021, 126, e2021JB021882.https://doi.org/10.1029/2021JB021882
[7] BORGWARDT, K. M., GRETTON, A., RASCH, M. J., et al. Integrating structuredbiological data by kernel maximum mean discrepancy[J]. Bioinformatics, 2006, 22(14),e49-e57.
[8] CAI, A., QIU, H., & NIU, F. Semi‐Supervised Surface Wave Tomography WithWasserstein Cycle‐Consistent GAN: Method and Application to Southern CaliforniaPlate Boundary Region[J]. Journal of Geophysical Research: Solid Earth, 2022, 127(3),e2021JB023598.
[9] CAMPILLO, M., & PAUL, A. Long-range correlations in the diffuse seismic coda[J].Science, 2003, 299(5606), 547–549. https://doi.org/10.1126/science.1078551.
[10] CHEN, L. C., PAPANDREOU, G., KOKKINOS, I., et al. DeepLab: Semantic imagesegmentation with deep convolutional nets, atrous convolution, and fully connectedCRFs[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2017, 40(4),834–848. doi: 10.1109/TPAMI.2017.2699184
[11] CHEN, X. A systematic and efficient method of computing normal modes formultilayered half-space[J]. Geophysical Journal International, 1993, 115(2), 391–409.doi: 10.1111/j.1365-246X.1993.tb01194.x
[12] CHEN, X. Seismogram synthesis in multi-layered half-space Part I. Theoreticalformulations[J]. Earthquake Research in China, 1999, 13(2), 149-174.
[13] CHEN, X., XIA, J., PANG, J., et al. Deep learning inversion of Rayleigh-wavedispersion curves with geological constraints for near-surfaceinvestigations[J]. Geophysical Journal International, 2022, 231(1), 1-14.
[14] CHENG, F., XIA, J., ZHANG, K., et al. Phase-weighted slant stacking for surface wavedispersion measurement[J]. Geophysical Journal International, 2021, 226(1), 256–269.
[15] DAI, T., XIA, J., NING, L., et al. Deep learning for extracting dispersioncurves[J]. Surveys in Geophysics, 2021, 42, 69-95.
[16] DERODE, A., LAROSE, E., CAMPILLO, M., et al. How to estimate the Green'sfunction of a heterogeneous medium between two passive sensors? Application toacoustic waves[J]. Applied Physics Letters, 2003, 83(15), 3054–3056.https://doi.org/10.1063/1.1617373
[17] DING, H., JIANG, X., SHUAI, B., et al. Semantic segmentation with context encodingand multi-path decoding[J]. IEEE Transactions on Image Processing, 2020, 29, 3520-3533.
[18] DONG, S., LI, Z., CHEN, X., et al. DisperNet: An effective method of extracting andclassifying the dispersion curves in the frequency–bessel dispersionspectrum[J]. Bulletin of the Seismological Society of America, 2021, 111(6), 3420-3431.
[19] FU, L., PAN, L., MA, Q., et al. Retrieving S-wave velocity from surface wavemultimode dispersion curves with DispINet[J]. Journal of Applied Geophysics, 2021,193, 104430.
[20] GOODFELLOW, I., POUGET-ABADIE, J., MIRZA, M., et al. Generative adversarialnetworks[J]. Communications of the ACM, 2020, 63(11), 139-144.
[21] GANIN, Y., USTINOVA, E., AJAKAN, H., et al. Domain-adversarial training of neuralnetworks[J]. The journal of machine learning research, 2016, 17(1), 2096-2030.
[22] GAO, H., WU, X., & LIU, G. ChannelSeg3D: Channel simulation and deep learningfor channel interpretation in 3D seismic images[J]. Geophysics, 2021, 86(4), IM73-IM83.
[23] GAO, L., ZHANG, W., ZHANG, Z., et al. Extraction of multimodal dispersion curvesfrom ambient noise with compressed sensing[J]. Journal of Geophysical Research:Solid Earth, 2021, e2020JB021472.
[24] GENG, Z., WU, X., SHI, Y., et al. Deep learning for relative geologic time and seismichorizonsDL for RGT and horizons[J]. Geophysics, 2020, 85(4), WA87-WA100.
[25] GENG, Z., Z. HU, X. WU, et al. Semi-supervised salt segmentation using meanteacher[J]. Interpretation, 2022, Vol. 10(3), SE21-SE29.
[26] GHIFARY, M., KLEIJN, W. B., ZHANG, M., et al. Deep reconstruction-classificationnetworks for unsupervised domain adaptation[C]. In Proceedings of the 14th EuropeanConference on Computer Vision. Amsterdam, Netherlands, 2016.
[27] HE, K., ZHANG, X., REN, S., et al. Deep residual learning for image recognition[C].In Proceedings of the 29th Conference on Computer Vision and Pattern Recognition.Las Vegas, America, 2016.
[28] HERRMANN, R. B. Computer programs in seismology: An evolving tool forinstruction and research[J]. Seismological Research Letters, 2013, 84(6), 1081–1088.doi: https://doi.org/10.1785/0220110096
[29] HU, J., QIU, H., ZHANG, H., et al. Using deep learning to derive shear‐wave velocitymodels from surface‐wave dispersion data[J]. Seismological Research Letters, 2020,91(3), 1738-1751.
[30] JEDDI, Z., GUDMUNDSSON, O., & TRYGGVASON, A. Ambient-noise tomographyof Katla volcano, south Iceland[J]. Journal of Volcanology and Geothermal Research,2017, 347, 264–277. https://doi.org/10.1016/j.jvolgeores.2017.09.019
[31] KIM, T., CHA, M., KIM, H., et al. Learning to discover cross-domain relations withgenerative adversarial networks[C]. In Proceedings of 34th International Conferenceon Machine Learning. Sydney, Australia, 2017.
[32] KUANG, W., YUAN, C., & ZHANG, J. Real-time determination of earthquake focalmechanism via deep learning[J]. Nature communications, 2021, 12(1), 1432.
[33] LI, Y., & PENG, X. Network architecture search for domain adaptation[J]. arXivpreprint arXiv:2008.05706, 2020.
[34] LI, Z., MEIER, M. A., HAUKSSON, E., et al. Machine learning seismic wavediscrimination: Application to earthquake early warning[J]. Geophysical ResearchLetters, 2018, 45(10), 4773-4779.
[35] LIN, F. C., MOSCHETTI, M. P., & RITZWOLLER, M. H. Surface wave tomographyof the western United States from ambient seismic noise: Rayleigh and Love wavephase velocity maps[J]. Geophysical Journal International, 2008, 173(1), 281–298.https://doi.org/10.1111/j.1365-246X.2008.03720.x
[36] LIN, F. C., RITZWOLLER, M. H., & SHEN, W. On the reliability of attenuationmeasurements from ambient noise cross-correlations[J]. Geophysical Research Letters,2011, 38(11). https://doi.org/10.1029/2011GL047366
[37] LIN, G., MILAN, A., SHEN, C., et al. Refinenet: Multi-path refinement networks forhigh-resolution semantic segmentation[C]. In Proceedings of the 29th Conference onComputer Vision and Pattern Recognition. Las Vegas, America, 2016.
[38] LIN, J. T., MELGAR, D., THOMAS, A. M., et al. Early warning for great earthquakesfrom characterization of crustal deformation patterns with deep learning[J]. Journal ofGeophysical Research: Solid Earth, 2021, 126(10), e2021JB022703.
[39] LIU, A. H., LIU, Y. C., YEH, Y. Y., et al. A unified feature disentangler for multidomain image translation and manipulation[C]. In Proceedings of 32nd Conference onNeural Information Processing System. Montréal, Canada, 2018.
[40] LOBKIS, O. I., & WEAVER, R. L. On the emergence of the Green's function in thecorrelations of a diffuse field[J]. The Journal of the Acoustical Society of America,2001, 110(6), 3011–3017. https://doi.org/10.1121/1.1417528
[41] LONG, J., SHELHAMER, E., & DARRELL, T. Fully convolutional networks forsemantic segmentation[C]. In Proceedings of the 28th Conference on Computer Visionand Pattern Recognition. Boston, America, 2015.
[42] LUC, P., COUPRIE, C., CHINTALA, S., et al. Semantic segmentation usingadversarial networks[C]. In Proceedings of 30th Conference on Neural InformationProcessing System. Barcelona, Spain, 2016.
[43] LUO, Y., HUANG, Y., YANG, Y., et al. Constructing shear velocity models fromsurface wave dispersion curves using deep learning[J]. Journal of AppliedGeophysics, 2022, 196, 104524.
[44] LUO, Y., XU, Y., LIU, Q., et al. Rayleigh-wave dispersive energy imaging and modeseparating by high-resolution linear Radon transform[J]. The Leading Edge, 2008,27(11), 1536–1542. https://doi.org/10.1190/1.3011026
[45] MEIER, M.‐A., ROSS, Z. E., RAMACHANDRAN, A., et al. Reliable real‐time seismicsignal/noise discrimination with machine learning[J]. Journal of Geophysical Research:Solid Earth, 2019, 124, 788–800. https://doi.org/ 10.1029/2018JB016661
[46] MOUSAVI, S. M., ELLSWORTH, W. L., ZHU, W., et al. Earthquake transformer—anattentive deep-learning model for simultaneous earthquake detection and phasepicking[J]. Nature communications, 2020, 11(1), 3952.
[47] MOSCHETTI, M. P., RITZWOLLER, M. H., & SHAPIRO, N. M. Surface wavetomography of the western United States from ambient seismic noise: Rayleigh wavegroup velocity maps[J]. Geochemistry, Geophysics, Geosystems, 2007, 8(8).https://doi.org/10.1029/2007GC001655
[48] MÜNCHMEYER, J., WOOLLAM, J., RIETBROCK, A., et al. Which picker fits mydata? A quantitative evaluation of deep learning based seismic pickers[J]. Journal ofGeophysical Research: Solid Earth, 2022, 127, e2021JB023499.
[49] OKADA, H., & SUTO, K. The microtremor survey method[C]. Society of ExplorationGeophysicists with the cooperation of Society of Exploration Geophysicists of Japan[and] Australian Society of Exploration Geophysicists, 2003.
[50] PARK, C. B., MILLER, R. D., & XIA, J. Imaging dispersion curves of surface waveson multichannel record[C]. In SEG Technical Program Expanded Abstracts 1998 (pp.1377–1380). Society of Exploration Geophysicists, 1998.
[51] PAN, S. J., & YANG, Q. A survey on transfer learning[J]. IEEE Transactions onKnowledge and Data Engineering, 2009, 22(10), 1345–1359. doi:10.1109/TKDE.2009.191
[52] PAN, Y., XIA, J., XU, Y., et al. Delineating shallow S wave velocity structure usingmultiple ambient-noise surface wave methods: An example from Western Junggar,China[J]. Bulletin of the Seismological Society of America, 2016, 106(2), 327–336.https://doi.org/10.1785/0120150014
[53] RAISSI, M., PERDIKARIS, P., & KARNIADAKIS, G. E. Physics-informed neuralnetworks: A deep learning framework for solving forward and inverse problemsinvolving nonlinear partial differential equations[J]. Journal of Computationalphysics, 2019, 378, 686-707.
[54] RONNEBERGER, O., FISCHER, P., & BROX, T. U-Net: Convolutional networks forbiomedical image segmentation[C]. In Proceedings of International Conference onMedical Image Computing and Computer-Assisted Intervention, 2015.
[55] ROSS, Z. E., MEIER, M. A., HAUKSSON, E., et al. Generalized seismic phasedetection with deep learning[J]. Bulletin of the Seismological Society ofAmerica, 2018, 108(5A), 2894-2901.
[56] ROSS, Z. E., MEIER, M.-A., & HAUKSSON, E. P wave arrival picking and firstmotion polarity determination with deep learning[J]. Journal of Geophysical Research:Solid Earth, 2018, 123, 5120–5129. https://doi.org/10.1029/2017JB015251
[57] SAAD, O. M., HUANG, G., CHEN, Y., et al. Scalodeep: A highly generalized deeplearning framework for real‐time earthquake detection[J]. Journal of GeophysicalResearch: Solid Earth, 2021, 126(4), e2020JB021473.
[58] SÁNCHEZ-SESMA, F. J., & CAMPILLO, M. Retrieval of the greens function fromcross correlation: The canonical elastic problem[J]. Bulletin of the SeismologicalSociety of America, 2006, 96(3), 1182–1191.
[59] SATO, H., FEHLER, M. C., & MAEDA, T. Green's function retrieval from the crosscorrelation function of random waves, Seismic wave propagation and scattering in theheterogeneous Earth: Second edition [M]. Berlin, Heidelberg: Springer, 2012.
[60] SHEN, W., & RITZWOLLER, M. H. Crustal and uppermost mantle structure beneaththe United States[J]. Journal of Geophysical Research: Solid Earth, 2016, 121(6),4306–4342. doi: https://doi.org/10.1002/2016JB012887
[61] SHEN, W., RITZWOLLER, M. H., KANG, D., et al. A seismic reference model for thecrust and uppermost mantle beneath China from surface wavedispersion[J]. Geophysical Journal International, 2016, 206(2), 954–979.
[62] SHI, Y., WU, X., & FOMEL, S. SaltSeg: Automatic 3D salt segmentation using a deepconvolutional neural network[J]. Interpretation, 2019, 7(3), SE113-SE122.
[63] SHI, Y., WU, X., & FOMEL, S. Waveform embedding: Automatic horizon picking withunsupervised deep learning[J]. Geophysics, 2020, 85(4), WA67-WA76.
[64] SHAPIRO, N. M., & CAMPILLO, M. Emergence of broadband Rayleigh waves fromcorrelations of the ambient seismic noise[J]. Geophysical Research Letters, 2004, 31(7).https://doi.org/10.1029/2004GL019491
[65] SHAPIRO, N. M., CAMPILLO, M., STEHLY, L., et al. High-resolution surface wavetomography from ambient seismic noise[J]. Science, 2005, 307(5715), 1615–1618.https://doi.org/10.1126/science.1108339
[66] SONG, W., FENG, X., WU, G., et al. Convolutional neural network, Res‐Unet++,‐based dispersion curve picking from noise cross‐correlations [J]. Journal ofGeophysical Research: Solid Earth, 2021, 126(11), e2021JB022027.
[67] SONG, W., FENG, X., ZHANG, G., et al. Domain adaptation in automatic picking ofphase velocity dispersions based on deep learning[J]. Journal of Geophysical Research:Solid Earth, 2022, 127(6), e2021JB023389.
[68] SUN, B., & SAENKO, K. Deep coral: Correlation alignment for deep domainadaptation[C]. In Proceedings of the 14th European conference on computer vision.Amsterdam, Netherlands, 2016.
[69] TAIGMAN, Y., POLYAK, A., & WOLF, L. Unsupervised cross-domain imagegeneration[J]. arXiv preprint arXiv:1611.02200, 2016.
[70] TORREY, L., & SHAVLIK, J. Transfer learning[M]. In Handbook of research onmachine learning applications and trends: algorithms, methods, and techniques (pp.242–264). IGI global, 2010.
[71] TZENG, E., HOFFMAN, J., ZHANG, N., et al. Deep domain confusion: Maximizingfor domain invariance[J]. arXiv preprint arXiv:1412.3474, 2014.
[72] TZENG, E., HOFFMAN, J., SAENKO, K., et al. Adversarial discriminative domainadaptation[C]. In Proceedings of the 30th conference on computer vision and patternrecognition. Hawaii, America, 2017.
[73] VILLASENOR, A., YANG, Y., RITZWOLLER, M. H., et al. Ambient noise surfacewave tomography of the Iberian Peninsula: Implications for shallow seismicstructure[J]. Geophysical Research Letters, 2007, 34(11).https://doi.org/10.1029/2007GL030164
[74] WANG, F., WU, X., & WANG, H. Seismic horizon identification using semisupervised learning with virtual adversarial training[J]. IEEE Transactions onGeoscience and Remote Sensing, 2022, 60, 1-11.
[75] WANG, J., WU, G., & CHEN, X. Frequency-Bessel transform method for effectiveimaging of higher-mode Rayleigh dispersion curves from ambient seismic noise data[J].Journal of Geophysical Research: Solid Earth, 2019, 124(4), 3708–3723.https://doi.org/10.1029/2018JB016595
[76] WANG, J., XIAO, Z., LIU, C., et al. Deep learning for picking seismic arrivaltimes[J]. Journal of Geophysical Research: Solid Earth, 2019, 124(7), 6612-6624.
[77] WANG, K., LU, L., MAUPIN, V., et al. Surface wave tomography of NortheasternTibetan Plateau using beamforming of seismic noise at a dense array [J]. Journal ofGeophysical Research: Solid Earth, 2020, 125(4), e2019JB018416
[78] WANG, X., CHEN, Q. F., LI, J., et al. Seismic sensor misorientation measurementusing P-wave particle motion: An application to the NECsaids array[J]. SeismologicalResearch Letters, 2016, 87(4), 901–911.
[79] WANG, W., MCMECHAN, G. A., MA, J., et al. Automatic velocity picking fromsemblances with a new deep-learning regression strategy: Comparison with aclassification approach[J]. Geophysics, 2021, 86(2), U1–U13.https://doi.org/10.1190/geo2020-0423.1
[80] WEAVER, R. L., & LOBKIS, O. I. Ultrasonics without a source: Thermal fluctuationcorrelations at MHz frequencies[J]. Physical Review Letters, 2001, 87(13), 134301.
[81] WEISS, K., KHOSHGOFTAAR, T. M., & WANG, D. D. A survey of transferlearning[J]. Journal of Big Data, 2016, 3(1), 9. doi: https://doi.org/10.1186/s40537-016-0043-6
[82] WU, G. X., PAN, L., WANG, J. N., et al. Shear velocity inversion using multimodaldispersion curves from ambient seismic noise data of USArray transportable array [J].Journal of Geophysical Research: Solid Earth, 2020, 125(1), e2019JB018213.https://doi.org/10.1029/2019JB018213
[83] WU, X., LIANG, L., SHI, Y., et al. FaultSeg3D: Using synthetic data sets to train anend-to-end convolutional neural network for 3D seismic faultsegmentation[J]. Geophysics, 2019, 84(3), IM35-IM45.
[84] WU, X., LIANG, L., SHI, Y., et al. Multitask learning for local seismic imageprocessing: fault detection, structure-oriented smoothing with edge-preserving, andseismic normal estimation by using a single convolutional neuralnetwork[J]. Geophysical Journal International, 2019, 219(3), 2097-2109.
[85] WU, X., SHI, Y., FOMEL, S., et al. FaultNet3D: Predicting fault probabilities, strikes,and dips with a single convolutional neural network[J]. IEEE Transactions onGeoscience and Remote Sensing, 2019, 57(11), 9138-9155.
[86] WU, X., YAN, S., QI, J., et al. Deep learning for characterizing paleokarst collapsefeatures in 3‐D seismic images[J]. Journal of Geophysical Research: Solid Earth, 2020,125(9), e2020JB019685.
[87] XIAO, Z., WANG, J., LIU, C., et al. Siamese Earthquake Transformer: A pairinputdeep-learning model for earthquake detection and phase picking on a seismic array[J].Journal of Geophysical Research: Solid Earth, 2021, 126, e2020JB02144
[88] XU, M., ZHANG, J., NI, B., et al. Adversarial domain adaptation with domainmixup[C]. In Proceedings of the AAAI Conference on Artificial Intelligence. New York,America, 2020.
[89] YANG, S., ZHANG, H., GU, N., et al. Automatically Extracting Surface‐Wave Groupand Phase Velocity Dispersion Curves from Dispersion Spectrograms Using aConvolutional Neural Network[J]. Seismological Society of America, 2022, 93(3),1549-1563.
[90] YANG, Y., RITZWOLLER, M. H., LEVSHIN, A. L., et al. Ambient noise Rayleighwave tomography across Europe[J]. Geophysical Journal International, 2007, 168(1),259–274. https://doi.org/10.1111/j.1365-246X.2006.03203.x
[91] YANG, Y., & RITZWOLLER, M. H. Characteristics of ambient seismic noise as asource for surface wave tomography[J]. Geochemistry, Geophysics, Geosystems, 2008,9(2). https://doi.org/10.1029/2007GC001814
[92] YANG, Y., SHEN, W., & RITZWOLLER, M. H. Surface wave tomography on a largescale seismic array combining ambient noise and teleseismic earthquake data[J].Earthquake Science, 2011, 24(1), 55–64. https://doi.org/10.1007/s11589-011-0769-3
[93] YANG, Y., & SOATTO, S. FDA: Fourier domain adaptation for semanticsegmentation[C]. In Proceedings of the 33rd Conference on Computer Vision andPattern Recognition. Seattle, America, 2020.
[94] YILMAZ, O. Seismic data processing[M]. Investigation in Geophysics, 1987, 2, 526.
[95] ZHAN, W., PAN, L., & CHEN, X. A widespread mid-crustal low-velocity layer beneathNortheast China revealed by the multimodal inversion of Rayleigh waves from ambientseismic noise[J]. Journal of Asian Earth Sciences, 2020, 196, 104372.https://doi.org/10.1016/j.jseaes.2020.104372
[96] ZHANG, G., LIU, Q., & CHEN, X. Enhancing the Frequency–Bessel Spectrogram ofAmbient Noise Cross‐Correlation Functions[J]. Bulletin of the Seismological Societyof America, 2023, 113(1), 361-377.
[97] ZHANG, Q., ZHANG, W., WU, X., et al. Deep Learning for Efficient MicroseismicLocation Using Source Migration‐Based Imaging[J]. Journal of Geophysical Research:Solid Earth, 2022, 127(3), e2021JB022649.
[98] ZHANG, X., JIA, Z., ROSS, Z. E., et al. Extracting dispersion curves from ambientnoise correlations using deep learning[J]. IEEE Transactions on Geoscience andRemote Sensing, 2022, 58(12), 8932-8939.
[99] ZHENG, X. F., YAO, Z. X., LIANG, J. H., et al. The role played and opportunitiesprovided by IGP DMC of China National Seismic Network in Wenchuan earthquakedisaster relief and research[J]. Bulletin of the Seismological Society of America, 2010,100(5B), 2866–2872.
[100] ZHOU, Z., SIDDIQUEE, M. M. R., TAJBAKHSH, N., et al. Unet++: A nested unet architecture for medical image segmentation[C]. In Proceedings of 4th DeepLearning in Medical Image Analysis. Granada, Spain, 2018.
[101] ZHU, W., & BEROZA, G. C. Phasenet: a deep-neural-network-based seismicarrival-time picking method[J]. Geophysical Journal International, 2018, 216(1), 261-273
[102] ZHU, W., TAI, K. S., MOUSAVI, S. M., et al. An end‐to‐end earthquake detectionmethod for joint phase picking and association using deep learning[J]. Journal ofGeophysical Research: Solid Earth, 2022, 127(3), e2021JB023283.
[103] 张功恒. 利用背景噪声高阶频散曲线研究四川盆地结构[D]: 哈尔滨工业大学,2019.

所在学位评定分委会
力学
国内图书分类号
O343.7
来源库
人工提交
成果类型学位论文
条目标识符http://sustech.caswiz.com/handle/2SGJ60CL/544770
专题理学院_地球与空间科学系
推荐引用方式
GB/T 7714
宋卫宾. 基于深度学习的频散曲线自动拾取[D]. 深圳. 南方科技大学,2023.
条目包含的文件
文件名称/大小 文献类型 版本类型 开放类型 使用许可 操作
11930823-宋卫宾-地球与空间科学(17361KB)----限制开放--请求全文
个性服务
原文链接
推荐该条目
保存到收藏夹
查看访问统计
导出为Endnote文件
导出为Excel格式
导出为Csv格式
Altmetrics Score
谷歌学术
谷歌学术中相似的文章
[宋卫宾]的文章
百度学术
百度学术中相似的文章
[宋卫宾]的文章
必应学术
必应学术中相似的文章
[宋卫宾]的文章
相关权益政策
暂无数据
收藏/分享
所有评论 (0)
[发表评论/异议/意见]
暂无评论

除非特别说明,本系统中所有内容都受版权保护,并保留所有权利。