Seismic Data Compression Using Deep Learning

被引:14
作者
Helal, Emad B. [1 ]
Saad, Omar M. [1 ,2 ]
Hafez, Ali G. [1 ,3 ,4 ]
Chen, Yangkang [2 ]
Dousoky, Gamal M. [3 ,5 ,6 ]
机构
[1] Natl Res Inst Astron & Geophys NRIAG, Dept Seismol, Helwan 11421, Egypt
[2] Zhejiang Univ, Sch Earth Sci, Hangzhou 310027, Peoples R China
[3] Nahda Univ, Dept Commun & Comp Engn, Fac Engn, Bani Suwayf 65211, Egypt
[4] LTLab Inc, Res & Dev Div, Fukuoka 8140155, Japan
[5] Kyushu Univ, Dept Elect Engn, Fukuoka 8190395, Japan
[6] Minia Univ, Elect Engn Dept, Al Minya 61517, Egypt
关键词
Data compression; Feature extraction; Decoding; Convolution; Deep learning; Image reconstruction; Data models; Convolutional autoencoders (CAE); deep learning; seismic data compression; EFFICIENT COMPRESSION; AUTOENCODER; TRANSFORM; NETWORKS;
D O I
10.1109/ACCESS.2021.3073090
中图分类号
TP [自动化技术、计算机技术];
学科分类号
0812 ;
摘要
The exponential growth of the size of seismic data recorded in seismic surveys and real time data monitoring makes seismic data compression strongly demanded. Furthermore, compression will lead to an efficient use of the bandwidth assigned for the communication link between the seismic stations and the main center. In this paper, two convolutional autoencoders (CAEs) are proposed for seismic data compression. The two algorithms are mainly based on the convolutional neural network (CNN), which has the capability to compress the seismic data into feature representations, thereby allowing the decoder to perfectly reconstruct the input seismic data. The results show that the first model is efficient at low compression ratios (CRs), while the second model improves the signal-to-noise ratio (SNR) from about 3 dB to 12 dB compared to the other benchmark algorithms at moderate and high CRs.
引用
收藏
页码:58161 / 58169
页数:9
相关论文
共 46 条
[1]  
Abeer ZA, 2018, INT WIREL COMMUN, P370, DOI 10.1109/IWCMC.2018.8450511
[2]   Signal speech reconstruction and noise removal using convolutional denoising audioencoders with neural deep learning [J].
Abouzid, Houda ;
Chakkor, Otman ;
Gabriel Reyes, Oscar ;
Ventura, Sebastian .
ANALOG INTEGRATED CIRCUITS AND SIGNAL PROCESSING, 2019, 100 (03) :501-512
[3]  
[Anonymous], 2015, ACS SYM SER
[4]  
[Anonymous], 2014, STRIVING SIMPLICITY
[5]   LCT-WAVELET BASED ALGORITHMS FOR DATA COMPRESSION [J].
Averbuch, Amir Z. ;
Zheludev, Valery A. ;
Guttmann, Moshe ;
Kosloff, Dan D. .
INTERNATIONAL JOURNAL OF WAVELETS MULTIRESOLUTION AND INFORMATION PROCESSING, 2013, 11 (05)
[6]   Low bit-rate efficient compression for seismic data [J].
Averbuch, AZ ;
Meyer, F ;
Strömberg, JO ;
Coifman, R ;
Vassiliou, A .
IEEE TRANSACTIONS ON IMAGE PROCESSING, 2001, 10 (12) :1801-1814
[7]   High-Efficiency Observations: Compressive Sensing and Recovery of Seismic Waveform Data [J].
Bai, Lanshu ;
Lu, Huiyi ;
Liu, Yike .
PURE AND APPLIED GEOPHYSICS, 2020, 177 (01) :469-485
[8]   Compressive Data Gathering With Generative Adversarial Networks for Wireless Geophone Networks [J].
Bin, Kangcheng ;
Luo, Shihao ;
Zhang, Xiaopu ;
Lin, Jun ;
Tong, Xunqian .
IEEE GEOSCIENCE AND REMOTE SENSING LETTERS, 2021, 18 (03) :558-562
[9]  
Brownlee J., 2016, Deep Learning With Python
[10]   THE WAVELET TRANSFORM, TIME-FREQUENCY LOCALIZATION AND SIGNAL ANALYSIS [J].
DAUBECHIES, I .
IEEE TRANSACTIONS ON INFORMATION THEORY, 1990, 36 (05) :961-1005