Abstract
Algorithms for automated processing of seismic records are being constantly upgraded, and the tasks of data analysis are becoming more complex. Most algorithms require preliminary preparation of the data. This preprocessing is either very simple, such as frequency filtering, or highly sophisticated to extract specific properties of the signal. Adequate preprocessing can increase the efficiency of the further analysis by order and more. However, specialized preprocessing cannot be used for solving other tasks or with other postprocessing algorithms. We consider the solutions that do not result in the significant loss of information and that can be used for solving any tasks. The main goals of the preprocessing are to reduce the noise level, to remove the anthropogenic noise, and to reduce the dimensionality of the data. We assume that deep neural networks of certain architecture are used for further data processing; however, this does not preclude from the application of other algorithms. As the preprocessing of seismic data, in this paper we consider wavelet transform, autoencoder, and some other algorithms.
Similar content being viewed by others
REFERENCES
Allen, R., Automatic phase pickers: their present use and future prospects, Bull. Seismol. Soc. Am., 1982, vol. 72, no. 6 (B), pp. 225–242.
Altunkaynak, A., Predicting water level fluctuations in Lake Michigan-Huron using wavelet-expert system methods, Water Resour. Manage., 2014, vol. 28, no. 8, pp. 2293–2314. https://doi.org/10.1007/s11269-014-0616-0
Bao, W., Yue, J, and Rao, Y., A deep learning framework for financial time series using stacked autoencoders and long-short term memory, PLOS ONE, 2017, vol. 12, no. 7, e0180944. https://doi.org/10.1371/journal.pone.0180944
Ben-Haim, Z., Eldar, Y.C., and Elad, M., Coherence-based performance guarantees for estimating a sparse vector under random noise, IEEE Trans. Signal Process, 2010, vol. 58, no. 10, pp. 5030–5043. https://doi.org/10.1109/TSP.2010.2052460
Blumensath, T. and Davies, M., Iterative hard thresholding for compressive sensing, Appl. Comput. Harmon. Anal., 2009, vol. 27, no. 3, pp. 265–274. https://arxiv.org/ pdf/0805.0510.pdf
Bourgain, J., Dilworth, S., Ford, K., Konyagin, S., and Kutzarova, D., Explicit constructions of rip matrices and related problems, Duke Math. J., 2011, vol. 159, pp. 145–185. arXiv:1008.4535v3.
Candès, E.J. and Wakin, M.B., An introduction to compressive sampling [A sensing/sampling paradigm that goes against the common knowledge in data acquisition], IEEE Signal Process. Mag., 2008, vol. 25, no. 2, pp. 21–30. https://doi.org/10.1109/MSP.2007.914731
Candes, E., Romberg, J., and Tao, T., Robust uncertainty principles: Exact signal reconstruction from highly incomplete frequency information, IEEE Trans. Inform. Theory, 2006, vol. 52, no. 2, pp. 489–509. https://doi.org/10.1109/TIT.2005.862083
Chen, X., Kopsaftopoulos, F., Wu, Q., Ren, H., and Chang, F.-K., A self-adaptive 1D convolutional neural network for flight-state identification, Sensors, 2019, vol. 19, article ID pii: E275. https://doi.org/10.3390/s19020275
Chicheva, M.A., Bystrye algoritmy diskretnogo kosinusnogo preobrazovaniya (Fast Discrete Cosine Transform Algorithms), Samara: Samar. gos. aerokosm. univ., 2006.
Claerbout, J.F. and Muir, F., Robust modeling with erratic data, Geophysics, 1973, vol. 38, no. 5, pp. 826–844.
Creswell, A. and Bharath, A.A., Denoising adversarial autoencoders, IEEE Trans. Neural Netw. Learn. Syst., 2019, vol. 30, no. 4, pp. 968–984. https://doi.org/10.1109/TNNLS.2018.2852738
Dai, H. and MacBeth, C., The application of back propagation neural network to automatic picking seismic arrivals from single component recordings, J. Geophys. Res.: Solid Earth, 1997, vol. 102, no. B7, pp. 15105–15113.
Davenport, M.A., Boufounos, P.T., Wakin, M.B., and Baraniuk, R.G., Signal processing with compressive measurements, IEEE J. Sel. Top. Signal Process., 2010, vol. 4, no. 2, pp. 445–460. https://doi.org/10.1109/JSTSP.2009.2039178
Davenport, M.A., Laska, J.N., Treichler, J.R., and Baraniuk, R.G., The pros and cons of compressive sensing for wideband signal acquisition: noise folding versus dynamic range, IEEE Trans. Signal Process, 2012, vol. 60, no. 9, pp. 4628–4642. https://doi.org/10.1109/TSP.2012.2201149
Donoho, D., Compressed sensing, IEEE Trans. Inform. Theory, 2006, vol. 52, no. 4, pp. 1289–1306. https://doi.org/10.1109/TIT.2006.871582
Erhan, D., Bengio, Y., Courville, A., Manzagol, P.-A., Vincent, P., and Bengio, S., Why does unsupervised pre-training help deep learning? J. Mach. Learn. Res., 2010, vol. 11, pp. 625–660.
Foucart, S. and Rauhut, H., A Mathematical Introduction to Compressive Sensing, New York: Springer, 2013.
Gan, S., Wang, S., Chen, Y., Chen, X., Huang, W., and Chen, H., Compressive sensing for seismic data reconstruction via fast projection onto convex sets based on seislet transform, J. Appl. Geophys., 2016, vol. 130, pp 194–208. https://doi.org/10.1016/j.jappgeo.2016.03.033
Gehring, J., Miao, Y., Metze, F., and Waibel, A., Extracting deep bottleneck features using stacked auto-encoders, Proc. ICASSP, IEEE Int. Conf. on Acoustics, Speech and Signal Processing, 2013, Vancouver. https://doi.org/10.1109/ICASSP.2013.6638284
Gentili, S. and Michelini, A., Automatic picking of P and S phases using a neural tree, J. Seismol, 2006, vol. 10, no. 1, pp. 39–63. https://doi.org/10.1007/s10950-006-2296-6
Granichin, O.N. and Pavlenko, D.V., Randomization of data acquisition and l1-optimization, Komp’yut. Instr. Obrazovanii, 2010, no. 1. pp. 4-14.
Gravirov, V.V. and Kislov, K.V., The seismic data preparation program for training of an artificial neural network for ultrashort earthquake warning system, Book of Abstracts, 10th Int. Conf. “Problems of Geocosmos,” St.-Petersburg, 2014, pp. 86–87. http://geo.phys.spbu.ru/geocosmos/book_of_abstracts.pdf
Gravirov, V.V., Kislov, K.V., and Vinberg, F.E., Separation of informative signal from nonstationary highly noisy seismic data using neural network classifiers, Prom. ASU Kontrol., 2012, no. 12, pp. 55–59.
Gravirov, V.V., Kislov, K.V., Gravirova, L., and Vinberg, F., The use of wavelet transformation techniques in structure of an artificial neural network for recognition of early arrival of earthquakes on strongly noisy seismic records, Book of Abstracts CTBT: Science and Technology. Vienna, Austria, 2013, abstract T3-P132, p. 139. http://www.ctbto.org/fileadmin/ user_upload/SnT2013/bookofabstracts.pdf
Gravirov, V.V., Kislov, K.V., and Vinberg, F.E., Wavelet transform as a tool for processing and analysis of seismograms, Proc. 10th Int. Conf. “Problems of Geocosmos–2014,” St.-Petersburg State University, St.-Petersburg, Petrodvorets, 2014, pp. 168–172. http://geo.phys.spbu.ru/materials_of_a_ conference_2014/S2014/30_Gravirov<br><br>.pdf
Gurbuz, A.C., McClellan, J.H., and Scott, W.R., A compressive sensing data acquisition and imaging method for stepped frequency GPRs, IEEE Trans. Signal Process., 2009, vol. 57, no. 7, pp. 2640–2650. https://doi.org/10.1109/TSP.2009.2016270
Guyon, I. and Elisseeff, A., An Introduction to variable and feature selection, JMLR Spec. Iss. on Variable and Feature Selection, 2003, no. 3, pp. 1157–1182. http://www.jmlr.org/ papers/volume3/guyon03a/guyon03a.pdf
Hannibal, A.E., On the possibility of using artificial neural networks in seismic monitoring tasks, Seismic Instrum., 2018, vol. 54, no. 3, pp. 5–21. https://doi.org/10.3103/S074792391903006X
Haupt, J. and Nowak, R., Signal reconstruction from noisy random projections, IEEE Trans. Inform. Theory, 2006, vol. 52, no. 9, pp. 4036–4048. https://doi.org/10.1109/TIT.2006.880031
Herrmann, F.J., Wang, D., Hennenfent, G., and Moghaddam, P., Curvelet-based seismic data processing: a multiscale and nonlinear approach, Geophysics, 2008, vol. 73, no. 1, p. 5. https://doi.org/10.1190/1.2799517
Herrmann, F.J., Compressive Sensing. Seismic Laboratory for Imaging and Modeling, https://www.slim.eos.ubc.ca/ research/compressive-sensing. Cited April 1, 2019.
Hinton, G. and Salakhutdinov, R., Reducing the dimensionality of data with neural networks, Science, 2006, vol. 313, pp. 504–507. https://doi.org/10.1126/science.1127647
Hu, R. and Wang, Y., A first arrival detection method for low SNR microseismic signal, Acta Geophys., 2018, vol. 66, no. 5, pp. 945–957. https://doi.org/10.1007/s11600-018-0193-3
Ji, S., Xue, Y., and Carin, L., Bayesian compressive sensing, IEEE Trans. Signal Process, 2008, vol. 56, no. 6, pp. 2346–2356. https://doi.org/10.1109/TSP.2007.914345
Kislov, K.V. and Gravirov, V.V., Earthquake arrival identification in a record with technogenic noise, Seism. Instrum., 2010, vol. 47, no. 1, pp. 66–79. https://doi.org/10.3103/S0747923911010129
Kislov, K.V. and Gravirov, V.V., Neural network techniques for earthquake detection in high noise, Issledovano Rossii, 2010, article ID 070e, pp. 837–848.
Kislov, K.V. and Gravirov, V.V., Issledovaniye vliyaniya okruzhayushchey sredy na shum shirokopolosnoy seysmicheskoy apparatury (Influence of the Environment on the Noise of Broadband Seismic Instruments), Vychisl. Seismologiya, vol. 42, Moscow: Krasand, 2013.
Kislov, K.V. and Gravirov, V.V., The use of artificial neural networks for classification of noisy seismic signal, Seism. Instrum., 2017, vol. 53, no. 1, pp. 87–101. https://doi.org/10.3103/S0747923917010054
Kislov, K.V. and Gravirov, V.V., Deep artificial neural networks as a tool for the analysis of seismic data, Seism. Instrum., 2018, vol. 54, no. 1, pp. 8–16. https://doi.org/10.3103/S0747923918010073
Komarov, I.E., Selection of discrete wavelet transform parameters for various classes of signals, Cand. Sci. (Techn.) Dissertation, Omsk: Omsk State Techn. Univ., 2010.
Kong, Q., Trugman, D.T., Ross, Z.E., Bianco, M.J., Meade, B.J., and Gerstoft, P., Machine learning in seismology: turning data into Insights, Seismol. Res. Lett., 2018, vol. 90, no. 1, pp. 3–14. https://doi.org/10.1785/0220180259
Kotsiantis, S.B., Kanellopoulos, D., and Pintelas, P.E., Data preprocessing for supervised learning, Int. J. Comp. Sci., 2006, vol. 1, no. 1, pp. 111–117. http://citeseerx.ist.psu.edu/viewdoc/download?doi=10.1.1.104.8413&rep=rep1&type=pdf
Li, Y., Song, B., Kang, X., Du, X., and Guizani, M., Vehicle-type detection based on compressed sensing and deep learning in vehicular networks, Sensors, 2018, vol. 18, no. 12. article ID pii: E4500. https://doi.org/10.3390/s18124500
Lin, H., Li, Y., Yang, B., and Ma, H., Random denoising and signal nonlinearity approach by time-frequency peak filtering using weighted frequency reassignment, Geophysics, 2013, vol. 78, no. 6, pp. V229–V237. https://doi.org/10.1190/geo2012-0432.1
Lv, L., Zhao, D., and Deng, Q., A semi-supervised predictive sparse decomposition based on task-driven dictionary learning, Cognit. Comput., 2017, vol. 9, no. 1, pp. 115–124. https://doi.org/10.1007/s12559-016-9438-0
Madureira, G. and Ruano, A.E., A neural network seismic detector, Acta Techn. Jaurinensis, 2009, vol. 2, no. 2, pp. 159–170. https://doi.org/10.3182/20090921-3-TR-3005.00054
Majumdar, A. and Tripathi, A., Asymmetric stacked autoencoder, Int. Joint Conf. on Neural Networks (IJCNN), 2017. https://doi.org/10.1109/IJCNN.2017.7965949
Meyer, M., Weber, S., Beutel, J., and Thiele, L., Systematic identification of external influences in multi-year microseismic recordings using convolutional neural networks, Earth Surf. Dynam., 2019, vol. 7, pp. 171–190. https://doi.org/10.5194/esurf-7-171-2019
Oldenburg, D.W., Scheuer, T., and Levy, S., Recovery of the acoustic impedance from reflection seismograms, Geophysics, 1983, vol. 48, no. 10, pp. 1318–1337. https://doi.org/10.1190/1.1441413
Perol, T., Gharbi, M., and Denolle, M., Convolutional neural network for earthquake detection and location, Sci. Adv., 2018, vol. 4, no. 2, article ID E1700578. https://doi.org/10.1126/sciadv.1700578
Robucci, R., Gray, J.D., Chiu, L.K., Romberg, J., and Hasler, P., Compressive sensing on a CMOS separable-transform image sensor, Proc. IEEE, 2010, vol. 98, no. 6, pp. 1089–1101. https://doi.org/10.1109/JPROC.2010.2041422
Ross, Z.E., Meier, M.-A., and Hauksson, E.P., Wave arrival picking and first-motion polarity determination with deep learning, J. Geophys. Res.-Solid Earth, 2018, vol. 123, pp. 5120–5129. https://doi.org/10.1029/2017JB015251
Saad, O.M., Shalaby, A., and Sayed, M.S., Automatic discrimination of earthquakes and quarry blasts using wavelet filter bank and support vector machine, J. Seismol., 2019, vol. 23, no. 2, pp. 357–371. https://doi.org/10.1007/s10950-018-9810-5
Santosa, F. and Symes, W.W., Linear inversion of band-limited reflection seismograms, SIAM J. Sci. Statist. Comput., 1986, vol. 7, no. 4, pp. 1307–1330. https://doi.org/10.1137/0907087
Shen, Y., Han, T., Yang, Q., Yang, X., Wang, Y., Li, F., and Wen, H., CS-CNN: Enabling robust and efficient convolutional neural networks inference for Internet-of-things applications, IEEE Access, Special section on multimedia analysis for internet-of-things, 2018, no. 6, pp. 13439–13448. https://doi.org/10.1109/ACCESS.2018.2810264
Sheng, G., Li, Z., Wang, W., and Lan, G., A new automatic detection method of microseismic events based on wavelet decomposition and high-order statistics, Geophys. Prospect. Petrol., 2015, vol. 54, no. 4, pp. 388–395.
Shi, Y., Lei, M., Ma, R., and Niu, L., Learning robust auto-encoders with regularizer for linearity and Sparsity, IEEE Access, 2019, no. 7. pp. 17195–17206. https://doi.org/10.1109/ACCESS.2019.2895884
Stadnik, A.V., Use of artificial neural networks and wavelet analysis for increasing the efficiency in the problems of recognition and classification, Cand. Sci. (Phys.- Math) Dissertation, Ivanovo: Ivanovo State Univ., 2004.
Taylor, H.L., Banks, S.C., McCoy, J.F., Deconvolution with the l1 norm, Geophysics, 1979, vol. 44, no. 1, pp. 39–52. https://doi.org/10.1190/1.1440921
Valentine, A.P. and Trampert, J., Data space reduction, quality assessment and searching of seismograms: autoencoder networks for waveform data, Geophys. J. Int., 2012, vol. 189, no. 2, pp. 1183–1202. https://doi.org/10.1111/j.1365-246X.2012.05429.x
Vera Rodriguez, I., Sacchi, M., and Gu, Y., Simultaneous recovery of origin time, hypocentre location and seismic moment tensor using sparse representation theory, Geophys. J. Int., 2012, vol. 188, pp. 1188–1202. https://doi.org/10.1111/j.1365-246X.2011.05323.x
Wang, J. and Teng, T.-L., Artificial neural network-based seismic detector, Bull. Seismol. Soc. Am., 1995, vol. 85, pp. 308–319.
Yao, H., Gerstoft, P., Shearer, P.M., and Mecklenbräuker, C., Compressive sensing of the Tohoku-Oki Mw 9.0 earthquake: Frequency-dependent rupture modes, Geophys. Res. Lett., vol. 38, article ID L20310. https://doi.org/10.1029/2011GL049223
Yoon, C.E., O’Reilly, O., Bergen, K.J., and Beroza, G.C., Earthquake detection through computationally efficient similarity search, Sci. Adv., 2015, vol. 1, no. 11, article ID E1501057. https://doi.org/10.1126/sciadv.1501057
Yuan, S., Liu, J., Wang, S., Wang T., and Shi, P., Seismic waveform classification and first-break picking using convolution neural networks, IEEE Geosci. Remote Sens. Let., 2018, vol. 15, no. 2, pp. 272–276. https://doi.org/10.1109/LGRS.2017.2785834
Zhang, L., Zhang, L., and Du, B., Deep learning for remote sensing data: A technical tutorial on the state of the art, IEEE Geosci. Remote Sens. Mag., 2016, vol. 4, no. 2, pp. 22–40.https://doi.org/10.1109/MGRS.2016.2540798
Zhao, Y. and Takano, K., An artificial neural network approach for broadband seismic phase picking, Bull. Seismol. Soc. Am., 1999, vol. 89, no. 3, pp. 670–680.
Zheng, X., Wang, M., and Ordieres-Meré, J., Comparison of data preprocessing approaches for applying deep learning to human activity recognition in the Context of Industry 4.0, Sensors, 2018, vol. 18, no. 7, article ID 2146. https://doi.org/10.3390/s18072146
Author information
Authors and Affiliations
Corresponding author
Additional information
Translated by M. Nazarenko
Rights and permissions
About this article
Cite this article
Kislov, K.V., Gravirov, V.V. & Vinberg, F.E. Possibilities of Seismic Data Preprocessing for Deep Neural Network Analysis. Izv., Phys. Solid Earth 56, 133–144 (2020). https://doi.org/10.1134/S106935132001005X
Received:
Revised:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1134/S106935132001005X