Iranian Journal of Geophysics

Iranian Journal of Geophysics

Seismic 2D blind deconvolution via convolutional neural network

Document Type : Research Article

Authors
Fatemeh Khalouei 1
Hojjat Haghshenas Lari 2
Parvin Razzaghi 3
1 M.Sc. Student of Seismology, Institute for Advanced Studies in Basic Sciences (IASBS), Zanjan, Iran
2 Assistant Professor, Institute for Advanced Studies in Basic Sciences (IASBS), Zanjan, Iran
3 Assistant Professor, Department of Computer Science and Information Technology, Institute for Advanced Studies in Basic Sciences (IASBS), Zanjan, Iran
10.30499/ijg.2024.473193.1619
Abstract
The convolutional model of the earth proposes that seismic data results from the combination of reflectivity and a source wavelet along with some random noise. As a result, enhancing seismic data resolution involves mitigating the impact of the seismic wavelet, an essential task in seismic data processing. Deconvolution of seismic data is a method utilized for this purpose, ultimately improving the interpretation of seismic sections by enhancing data resolution and bandwidth. This process can be applied to both single and multichannel seismic data. In single-channel deconvolution, it is assumed that multidimensional seismic data is a weighted combination of one-dimensional traces, and deconvolution is applied to each trace independently. On the other hand, multichannel deconvolution takes into account the time and spatial correlation between seismic channels, making it more advantageous compared to single-channel deconvolution methods. Deconvolution can be performed in nonblind or blind manners. In the case of nonblind deconvolution, information about the source wavelet is available. This type of deconvolution relies on recorded source wavelets or estimated wavelets obtained from sources such as well logs. Conversely, due to the often unavailability of precise information about seismic wavelets, blind deconvolution techniques are utilized to estimate the wavelets before or during the deconvolution process. Traditional seismic deconvolution methods commonly utilize optimization techniques to solve this issue, often heavily dependent on the accuracy of the optimization parameters and requiring human intervention for decision-making. To address these challenges, deep learning methods have been proposed. These methods automatically determine the parameters and reduce the need for human-computer interaction. In this paper, a deep learning-based deconvolution method is proposed for applying multichannel semi-blind deconvolution to two-dimensional (2D) post-stack seismic data sets. This approach employs 2D convolutional neural networks (CNNs) to generate high-resolution reflectivity images from seismic sections. CNN is a network where some of the hidden layers are convolutional, and the convolution layer combines the inputs as feature maps with convolution filters to form transformed feature maps. The trainable parameters are adjusted through backpropagation of errors using advanced optimization algorithms. We used the advantages of this network and proposed a CNN-based multichannel semi-blind deconvolution method. The method is referred to as semi-blind since it requires a wavelet estimation as the initial step to produce training data, but does not demand precise wavelet information, as a rough estimation suffices to achieve good results. The effectiveness of this proposed method has been confirmed using both synthetic and real seismic data examples incorporating complex structures and varying
signal-to-noise ratios. The experiments have demonstrated that the method can effectively handle diverse scenarios, highlighting a significant improvement in data deconvolution results through training with simple synthetic data.
Keywords
Blind deconvolution, CNN, 2D operator

Subjects

Araya-Polo, M., Dahlke, T., Frogner, C., Zhang, C., Poggio, T., & Hohl, D. (2017). Automated fault detection without seismic processing. The Leading Edge, 36(3), 208–214.
Biswas, R., Vassiliou, A., Stromberg, R., & Sen, M.K. (2018). Stacking velocity estimation using recurrent neural network. SEG Technical Program Expanded Abstracts 2018, 2241–2245.
Chai, X., Tang, G., Lin, K., Yan, Z., Gu, H., Peng, R., Sun, X., & Cao, W. (2021). Deep learning for multitrace sparse-spike deconvolution. Geophysics, 86(3), V207-V218.
Chen, H., Sacchi, M. D., Haghshenas Lari, H., Gao, J., & Jiang, X. (2023). Nonstationary seismic reflectivity inversion based on prior-engaged semisupervised deep learning method. Geophysics, 88(1), WA115-WA128.
Cui, T., & Margrave, G. F. (2014). Seismic wavelet estimation. CREWES Research Report.
Fish, B.C., & Kusuma, T. (2005). A neural network approach to automate velocity picking. SEG Technical Program Expanded Abstracts 1994, 185–188.
Gholami, A., & Sacchi, M.D. (2012). A fast and automatic sparse deconvolution in the presence of outliers. IEEE Transactions on Geoscience and Remote Sensing, 50(10), 4105–4116.
Gholami, A., & Sacchi, M.D. (2013). Fast 3D blind seismic deconvolution via constrained total variation and GCV. SIAM Journal on Imaging Sciences, 6(4), 2350–2369.
Goldstein, T., & Osher, S. (2009). The Split Bregman Method for L1-Regularized Problems. SIAM Journal on Imaging Sciences, 2, 323–343.
Gurbuz, A.C., McClellan, J.H., Scott, W.R., & Larson, G.D. (2006). Seismic tunnel imaging and Detection. 2006 International Conference on Image Processing, 3229–3232.
Haghshenas Lari, H., & Gholami A. (2019). Nonstationary blind deconvolution of seismic records. Geophysics, 84, V1-V9.
Hargreaves, N. D., & Calvert, A. J. (1991). Inverse q filtering by Fourier transform. Geophysics, 56, 519–527.
Heimer, A., & Cohen, I. (2008). Multichannel blind seismic deconvolution using dynamic programming. Signal Processing, 88(4), 1839–1851.
Heimer, A., & Cohen, I. (2009). Multichannel seismic deconvolution using Markov-Bernoulli Random Field modeling. IEEE Transactions on Geoscience and Remote Sensing, 47(7), 2047–2058.
Heimer, A., Cohen, I., & Vassiliou, A. (2007). Dynamic programming for multichannel blind seismic deconvolution. SEG Technical Program Expanded Abstracts, 1845–1849.
Hubel, D.H., & Wiesel, T.N. (1968). Receptive fields and functional architecture of monkey striate cortex. The Journal of Physiology, 195, 215–243.
Idier, J., & Goussard, Y. (1993). Multichannel seismic deconvolution. IEEE Transactions on Geoscience and Remote Sensing, 31(5), 961–979.
Kaaresen, K., & Taxt, T. (1998). Multichannel blind deconvolution of seismic signals. Geophysics, 63(6), 2093–2107.
Kingma, D. P., & Ba, J. (2014). Adam: A method for stochastic optimization. arXiv preprint arXiv:1412.6980.
Mendel, J., Kormylo, J., Aminzadeh, F., Lee, J., & Habibi-Ashrafi, F. (1981). A novel approach to seismic signal processing and modeling. Geophysics, 46, 1398–1414.
Li, C., & Liu, G. (2022). Warped mapping–based blind deconvolution for resolution improvement. Geophysical Prospecting, 70(4), 677–701.
 
Li, S., Liu, B., Ren, Y., Chen, Y., Yang, S., Wang, Y., & Jiang, P. (2011). Deep Learning Inversion of Seismic Data. CoRR abs/1901.07733. http://arxiv.org/abs/1901.07733
Nguyen, T., & Castagna, J. (2010). High resolution seismic reflectivity inversion. Journal of Seismic Exploration, 19(4), 303–320.
Margrave, G., Lamoureux, M.P., & Henleyl, D. (2011). Gabor deconvolution: estimating reflectivity by nonstationary deconvolution of seismic data. Geophysics, 76(3), W15–W30.
Margrave, G. F. (2013). Methods of seismic data processing – Geophysics 517/557 Course Notes. The Department of Geoscience, University of Calgary.
Pereg, D., Cohen, I., & Vassiliou, A. A. (2020). Sparse seismic deconvolution via recurrent neural network. Journal of Applied Geophysics, 175, 103979. https://doi.org/10.1016/j.jappgeo.2020.103979
Priezzhev, I., & Stanislav, E. (2018). Application of machine learning algorithms using seismic data and well logs to predict reservoir properties. 80th EAGE Conference and Exhibition 2018.
Ram, I., Cohen, I., & Raz, S. (2010). Multichannel deconvolution of seismic signals using statistical MCMC methods. IEEE Transactions on Signal Processing, 58(5), 2757–2769.
Rumelhart, D. E., Hinton, G. E., & Williams, R. J. (1986). Learning representations by back-propagating errors. Nature, 323, 533–536.
Riel, P.V., & Berkhout, A.J. (1985). Resolution in seismic trace inversion by parameter estimation. Geophysics, 50, 1440–1455.
Robinson, E. A. (1985). Seismic time-invariant convolutional model. Geophysics, 50, 2742–2751.
Russell, B. (2019). Machine learning and geophysical inversion—A numerical study. The Leading Edge, 38(7), 512–519.
Sacchi, M. D., Velis D. R., & Comínguez A. H. (1994). Minimum entropy deconvolution with frequency-domain constraints. Geophysics, 59, 938–945.
Sherif, R., & Geldart, L. (1983). Exploration Seismology (2nd ed.). UK: Cambridge University Press.
Sun, Y., Cao, S., Chen, S., & Su, Y. (2024). Blind spectral inversion of seismic data. Geophysical Prospecting.
Taylor, H.L., Banks, S.C., & McCoy, J.F. (1979). Deconvolution with the ‘1 norm. Geophysics, 44, 39–52.
van der Baan, M. (2008). Time-varying wavelet estimation and deconvolution by kurtosis maximization. Geophysics, 73, V11–V18.
Wiggins, R. (1978). Minimum entropy deconvolution. Geoexploration, 16, 21–35.
Yamashita, R., Nishio, M., Do, R.K.G., & Togashi, K. (2018). Convolutional neural networks: an overview and application in radiology. Insights into Imaging, 9, 611–629. https://doi.org/10.1007/s13244-018-0639-9
Yilmaz, Ö. (2001). Seismic Data Analysis. Tulsa: Society of Exploration Geophysicists.
Yin, X., Xu, W., Yang, Z., & Wu, B. (2024). Seismic Blind Deconvolution Based on Self-Supervised Machine Learning. Applied Sciences.
Zhang, R., & Castagna, J. (2011). Seismic sparse-layer reflectivity inversion using basis pursuit decomposition. Geophysics, 76(6), 147–158.
 
Iranian Journal of Geophysics
Volume 19, Issue 4
September and October 2025
Pages 23-38