Desert low frequency noise suppression based on multi-level wavelet convolution neural network
Ju, H.Q., Li, Y., Wang, H.Z. and Yang, B.J., 2020. Desert low frequency noise suppression based on multi-level wavelet convolution neural network. Journal of Seismic Exploration, 29: 575-586. Due to the effect of various environment factors, the random noise in desert seismic exploration has complex characteristics, including low frequency, non-Gaussian and frequency band aliasing of signal and noise. Therefore, it is difficult for the denoising processing. Aiming at this problem, a Multi-level Wavelet Convolution Neural Network (MWCNN) is proposed to suppress the desert noise. MWCNN is a combination of two-dimensional discrete wavelet transformation and convolution neural network. Specifically, Discrete Wavelet Transformation (DWT) and inverse wavelet transformation (IWT) are used to replace the pooling layer and up-convolution of U-net respectively. So that the trade-off between receptive field and computational efficiency can be achieved. Consequently, the expansion of the receptive field can obtain more overall information of the events. In this paper, by adjusting the training set and structure of MWCNN, it is applied to suppress the random noise in desert seismic exploration. Furthermore, compared with other neural networks, MWCNN achieves better better denoising effect and better events’ continuity by enlarging the receptive field in desert seismic records. And experiments on simulated synthetic records and actual seismic records respectively show our trained MWCNN model achieve a satisfactory denoising performance for the random noise in desert seismic exploration.
- Cao, S. and Chen, X., 2005. The second-generation wavelet transform and its application
- in denoising of seismic data. Appl. Geophys., 2(2): 70-74.
- Harris, P.E. and White, R.E.. 2010. Improving the performance of f-x prediction filtering
- at low signal-to-noise ratios. Geophys. Prosp., 45: 269-302.
- Huang, L.. Dong, X. and Clee, T.E.. 2017. A scalable deep learning platform for
- identifying geologic features from seismic attributes. The Leading Edge, 36:
- 249-256.
- Huang, M.H. and Li, Y., 2016. Random noise suppression in seismic exploration based
- on directional controllable filtering. J. Geophys., 59: 1815-1823.
- He, K., Zhang, X., Ren, S. and Sun, J., 2015. Deep residual learning for image
- recognition. arXiv:1512.03385,
- Liu, P. , Zhang, H. , Zhang, K. , Lin, L. and Zuo, W., 2018. Multi-level wavelet-CNN for
- image restoration. CoRR, abs/1805.07071.
- Jain, V. and Seung, S.H., 2008. Natural image denoising with convolutional networks. In:
- Koller, D., Schuurmans, D., Bengio, Y. and Bottou, L. (eds.), Advances in Neural
- Informat. Process. Syst., 21 (NIPS’08).
- Krizhevsky, A. , Sutskever, I. and Hinton, G.E., 2012. ImageNet Classification with
- Deep Convolutional Neural Networks. In: Advances in Neural Informat. Process.
- Syst., 25: 1097-1105.
- Kingma, D.P. and Ba, J., 2014. Adam: a method for stochastic optimization. Comput.
- Sci., CoRR, abs/1412.6980, 2014.
- Ronneberger. O.. Fischer. P. and Brox, T., 2015. U-net: convolutional networks for
- biomedical image segmentation. CoRR, abs/1412.6980, 2014.
- Tang, P. , Wang, H. and Kwong, S., 2016. G-ms2f: googlenet based multi-stage feature
- fusion of deep cnn for scene recognition. Neurocomputing, S092523 1216314047.
- Wang, J.J., Yuan, L., Liu, W.R. and Xu, X.H., 2016. Dual-tree complex wavelet domain
- bivariate method for seismic signal random noise attenuation. Chin. J. Geophys.,
- 59: 3046-3055.
- Yan, Z.. Weiiian. R. and Guowei, T.. 2017. Random noise suppression based on sparse
- representation of multi-trace similarity group. Oil Geophys. Prosp., 52: 442-450.
- Zhang, W., Li, R., Deng, H., Wang, L., Lin, W. and Ji, S., 2015. Deep convolutional
- neural networks for multi-modality isointense infant brain image
- segmentation. Proc. IEEE Internat. Symp. Biomed. Imag., 108: 1342-1345.
- Zhang, K., Zuo, W., Chen, Y., Meng, D. and Zhang, L., 2017. Beyond a Gaussian
- denoiser: residual learning of deep CNN for image denoising. IEEE Transact.
- Image Process., 26: 3142-3155.
- Zhao, M., Chen, S. and Yuen, D., 2019. Automatic classification and recognition of
- seismic waveforms based on deep learning convolution neural network. J.
- Geophys., 62: 380-388.
