Abstract
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.
Highlights
Seismic data are collected for many purposes, e.g., crustal earth structure studies, earthquake parameter calculations, and oil and gas explorations
We propose two deep learning models based on the convolutional neural network (CNN)
NRMSE is used to measure the distortion level resulted from the lossy compression [44]
Summary
Seismic data are collected for many purposes, e.g., crustal earth structure studies, earthquake parameter calculations, and oil and gas explorations. Multiscale sparse dictionary learning has been proposed for data compression [13] In this method the dictionary learning process is integrated with wavelet transform. Nuha et al [16] integrates the extreme learning machine technique [17] with deep neural networks autoencoder This method is considered a fast method due to the analytically calculated encoder/decoder weights without any iterations. A 3D deep learning technique is proposed in Schiavon et al [18] to compress seismic data with low bit rate This technique is less sensitive to noise and can reconstruct the seismic data with high quality. Applications to real earthquake data show that the proposed CAE models can compress the input samples at different CRs. the original data is reconstructed successfully with a high signal-to-noise ratio (SNR). The proposed models are robust and have a strong generalization ability
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
