Denoising of desert seismic signal based on synchrosqueezing transform and Adaboost algorithm

• Autorzy: Sun Xiaofu , Li Yue

Identyfikatory

DOI

10.1007/s11600-020-00408-1

• Języki publikacji: EN

Abstrakty

EN

Seismic data in desert area generally have low signal-to-noise ratio (SNR) due to special surface conditions. Desert noise is characterized as low-frequency, non-Gaussian and non-stationary noise, which makes the noise suppression in desert area more challenging by conventional methods. Conventional methods are efective for the signal with high SNR, but in desert seismic signal, the SNR is low and the signal can easily be obliterated in desert noise. In this paper, we propose an approach that operates in synchrosqueezing transform (SST) domain and use classifcation techniques obtained from supervised machine learning to identify the coefcients associated with signal and noise. First of all, we transform the real desert seismic data into time–frequency domain by SST. Secondly, we select features by calculating the SST coefcients of signal and noise. And then, we train them in the Adaboost classifer. Finally, when the training is completed, we can obtain the fnal classifer that can efectively separate the signal from noise. We perform tests on synthetic and feld records, and the results show great advantages in suppressing random noise as well as retaining efective signal amplitude.

Słowa kluczowe

EN

desert; low frequency; noise suppression; seismic signal; detection; synchrosqueezing transform; adaboost classifer

PL

pustynia; niska częstotliwość; tłumienie dźwięków; sygnał sejsmiczny; wykrywanie

• Wydawca: Instytut Geofizyki PAN ; Springer
• Czasopismo: Acta Geophysica
• Rocznik: 2020
• Tom: Vol. 68, no. 2
• Strony: 403--412
• Opis fizyczny: Bibliogr. 24 poz.

Twórcy

autor

Sun Xiaofu

• Department of Information, College of Communication Engineering, Jilin University, Changchun 130012, China

autor

Li Yue

• Department of Information, College of Communication Engineering, Jilin University, Changchun 130012, China

Bibliografia

• 1. Anvari R, Siahsar MAN, Gholtashi S, Roshandel Kahoo A, Mohammadi M (2017) Seismic random noise attenuation using synchrosqueezed wavelet transform and low-rank signal matrix approximation. IEEE Trans Geosci Remote Sens 55(11):6574–6581. https://doi.org/10.1109/TGRS.2017.2730228
• 2. Bekara M, van der Baan M (2009) Random and coherent noise attenuation by empirical mode decomposition. Geophysics 74(5):V89–V98. https://doi.org/10.1190/1.3157244
• 3. Chen Y (2017) Fast dictionary learning for noise attenuation of multidimensional seismic data. Geophys J Int 209(1):21–31. https://doi.org/10.1093/gji/ggw492
• 4. Chen Y (2018) Fast waveform detection for microseismic imaging using unsupervised machine learning. Geophys J Int 215(2):1185–1199. https://doi.org/10.1093/GJI/GGY348
• 5. Chen Y, Ma J (2014) Random noise attenuation by f-x empirical-mode decomposition predictive filtering. Geophysics 79(3):81–91. https://doi.org/10.1190/GEO2013-0080.1
• 6. Daubechies I, Maes S (1996) A nonlinear squeezing of the continuous wavelet transform based on auditory nerve models. Wavelets Med Biol. https://doi.org/10.1201/9780203734032-20
• 7. Daubechies I, Lu J, Wu H (2011) Synchrosqueezed wavelet transforms: an empirical mode decomposition-like tool. Appl Comput Harmon Anal 30(2):243–261. https://doi.org/10.1016/j.acha.2010.08.002
• 8. Deng X, Li Y, Yang B (2007) Ricker wavelet LS-SVM and its parameters setting for seismic prospecting signals denoising. In: Paper presented at the second international conference on space information technology 2007, vol 6795. https://doi.org/10.1117/12.773771
• 9. Freund Y, Schapire RE (1997) A decision-theoretic generalization of on-line learning and an application to boosting. J Comput Syst Sci 55(1):119–139. https://doi.org/10.1006/jcss.1997.1504
• 10. Kumar R, Sumathi P, Kumar A (2017) Synchrosqueezing transform-based frequency shifting detection for earthquake-damaged structures. IEEE Geosci Remote Sens Lett 14(8):1393–1397. https://doi.org/10.1109/LGRS.2017.2714428
• 11. Li G, Li Y, Yang B (2017) Seismic exploration random noise on land: modeling and application to noise suppression. IEEE Trans Geosci Remote Sens PP(99):1–14
• 12. Liu Y (2013) Noise reduction by vector median filtering. Geophysics 78(3):V79–V86. https://doi.org/10.1190/GEO2012-0232.1
• 13. Liu Y, Liu C, Wang D (2009) A 1D time-varying median filter for seismic random, spike-like noise elimination. Geophysics 74(1):V17–V24. https://doi.org/10.1190/1.3043446
• 14. Lv T, Yan J, Xu H (2017) An EEG emotion recognition method based on AdaBoost classifier. In: Paper presented at the 2017 Chinese automation congress (CAC), pp 6050–6054. https://doi.org/10.1109/CAC.2017.8243867
• 15. Singer SF (1981) Oil exploration. 213(4515):1448
• 16. Qin X, Song W (2016) Weak signal extraction method of microseismic data based on synchrosqueezing transform. Geophys Prospect Pet 55(1):60–66
• 17. Wang Y, Peng Z, He Y (2017) Time-frequency representation for seismic data using sparse S transform. In: 2nd IEEE international conference on computer and communications (ICCC). IEEE, Chengdu, China. https://doi.org/10.1109/CompComm.2016.7925036
• 18. Wang W, Jin Y, Wang B, Li W, Wang X (2018) Chaotic signal de-noising based on adaptive threshold synchrosqueezed wavelet transform. Tien Tzu Hsueh Pao/Acta Electron Sin 46(7):1652–1657. https://doi.org/10.3969/j.issn.0372-2112.2018.07.016
• 19. Yuan S, Liu J, Wang S, Wang T, Shi P (2018) Seismic waveform classification and first-break picking using convolution neural networks. IEEE Geosci Remote Sens Lett 15(2):272–276. https://doi.org/10.1109/LGRS.2017.2785834
• 20. Zhang C, Van Der Baan M (2018a) A denoising framework for microseismic and reflection seismic data based on block matching. Geophysics 83(5):V283–V292. https://doi.org/10.1190/geo2017-0782.1
• 21. Zhang C, van der Baan M (2018b) Multicomponent microseismic data denoising by 3D shearlet transform. Geophysics 83(3):A45–A51. https://doi.org/10.1190/GEO2017-0788.1
• 22. 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. https://doi.org/10.1109/LGRS.2018.2882058
• 23. Zhong T, Li Y, Wu N, Nie P, Yang B (2015) A study on the stationarity and Gaussianity of the background noise in land-seismic prospecting. Geophysics 80(4):V67–V82. https://doi.org/10.1190/geo2014-0153.1
• 24. Zhou Q, Gao J, Wang Z, Li K (2016) Adaptive variable time fractional anisotropic diffusion filtering for seismic data noise attenuation. IEEE Trans Geosci Remote Sens 54(4):1905–1917. https://doi.org/10.1109/TGRS.2015.2490158

Uwagi

Opracowanie rekordu ze środków MNiSW, umowa Nr 461252 w ramach programu "Społeczna odpowiedzialność nauki" - moduł: Popularyzacja nauki i promocja sportu (2021)