Multiscale dilated denoising convolution with channel attention mechanism for micro-seismic signal denoising

被引:0
作者
Jianxian Cai
Zhijun Duan
Li Wang
Juan Meng
Zhenjing Yao
机构
[1] Hebei Ke Laboratory of Seismic Disaster Instrument and Monitoring Technology,
来源
Journal of Petroleum Exploration and Production Technology | 2024年 / 14卷
关键词
Micro-seismic signals; Signal denoising; Convolutional neural networks; Multiscale dilated convolution; Attention mechanisms;
D O I
暂无
中图分类号
学科分类号
摘要
Denoising micro-seismic signals is paramount for ensuring reliable data for localizing mining-related seismic events and analyzing the state of rock masses during mining operations. However, micro-seismic signals are commonly contaminated by various types of complex noise, which can hinder micro-seismic accurate P-wave pickup and analysis. In this study, we propose the Multiscale Dilated Convolutional Attention denoising method, referred to as MSDCAN, to eliminate complex noise interference. The MSDCAN denoising model consists of an encoder, an improved attention mechanism, and a decoder. To effectively capture the neighborhood features and multiscale features of the micro-seismic signal, we construct an initial dilated convolution block and a multiscale dilated convolution block in the encoder, and the encoder focuses on extracting the relevant feature information, thus eliminating the noise interference and improving the signal-to-noise ratio (SNR). In addition, the attention mechanism is improved and introduced between the encoder and decoder to emphasize the key features of the micro-seismic signal, thus removing the complex noise and further improving the denoising performance. The MSDCAN denoising model is trained and evaluated using micro-seismic data from Stanford University. Experimental results demonstrate an impressive increase in SNR by 11.237 dB and a reduction in root mean square error (RMSE) by 0.802. Compared to the denoising results of the DeepDenoiser, CNN-denoiser and Neighbor2Neighbor methods, the MSDCAN denoising model outperforms them by enhancing the SNR by 2.589 dB, 1.584 dB and 2dB, respectively, and reducing the RMSE by 0.219, 0.050 and 0.188, respectively. The MSDCAN denoising model presented in this study effectively improves the SNR of micro-seismic signals, offering fresh insights into micro-seismic signal denoising methodologies.
引用
收藏
页码:883 / 908
页数:25
相关论文
共 79 条
[1]  
Ahmad BA(2021)Machine learning for automatic slump identification from 3D seismic data at convergent plate margins Marine Pet Geol 13 1324-848
[2]  
Takeshi T(2023)Denoising method for seismic co-band noise based on a u-net network combined with a residual dense block Appl Sci 40 834-929
[3]  
Cai J(2017)Deeplab: semantic image segmentation with deep convolutional nets, atrous convolution, and fully connected crfs IEEE Transact Pattern Anal Mach Intell 18 925-1394
[4]  
Wang L(2020)A deep-learning-based denoising method for multiarea surface seismic data IEEE Geosci Remote Sens Lett 43 1363-440
[5]  
Zheng J(2022)Seismic shot gather denoising by using a supervised-deep-learning method with weak dependence on real noise data: A solution to the lack of real noise data Surv Geophys 23 1023-3754
[6]  
Chen LC(2023)Dual residual denoising autoencoder with channel attention mechanism for modulation of signals Sensors 3 422-16
[7]  
Papandreou G(2021)Physics-informed machine learning Nat Rev Phys 56 3725-1113
[8]  
Kokkinos I(2023)Extracting and predicting rock mechanical behavior based on microseismic spatio-temporal response in an ultra-thick coal seam mine Rock Mech Rock Eng 60 1-355
[9]  
Dong X(2022)Spatial-domain synchrosqueezing wavelet transform and its application to seismic ground roll suppression IEEE Transact Geosci Remote Sens 70 1103-5
[10]  
Zhong T(2022)Improving the resolution of seismic data based on s-transform and modified variational mode decomposition, an application to songliao basin, northeast china Acta Geophysica 44 323-179476