The dictionary learning and sparse approximation method using the K‐singular value decomposition algorithm rely on the knowledge of the sparsity or noise variance as a constraint when it is used for data denoising. However, the determination of the sparsity or noise variance of seismic data can be tricky and sometimes unknown, especially in seismic field data. Thus, where the cardinality or the noise variance is not known, the intrinsic character of the relative coherence between the removed noise from noisy data and its learned dictionary is instead used as a constraint for the sparse approximation of simultaneous‐source seismic data. The dictionary learning is obtained using a modified orthogonal matching pursuit algorithm which uses coherence as a constraint and is referred to as coherence dictionary learning. The coherence dictionary learning is then adapted to handle the simultaneous‐source seismic data deblending. A blending structure with random time dithering of sequential source shooting is used to guarantee adequate randomness of the noise. Two‐dimensional overlap patches of the noisy data were extracted from the common receiver gather domain to train the dictionary and to determine the sparse representation of the signal. The method is tested on both synthetic and field data, and it shows adequate data recovery. Comparing the result of this method to the matching pursuit algorithm constrained by the signal sparsity and the noise variance reveals that our approach performs better at noise attenuation and yields a reasonable data recovery especially for strong seismic signal.
Within the field of seismic data acquisition with active sources, the technique of acquiring simultaneous data, also known as blended data, offers operational advantages. The preferred processing of blended data starts with a step of deblending, that is separation of the data acquired by the different sources, to produce data that mimic data from a conventional seismic acquisition and can be effectively processed by standard methods. Recently, deep learning methods based on the deep neural network have been applied to the deblending task with promising results, in particular using an iterative approach. We propose an enhancement to deblending with an iterative deep neural network, whereby we modify the training stage of the deep neural network in order to achieve better performance through the iterations. We refer to the method that only uses the blended data as the input data as the general training method. Our new multi-data training method allows the deep neural network to be trained by the data set with the input patches composed of blended data, noisy data with low amplitude crosstalk noise, and unblended data, which can improve the ability of the deep neural network to remove crosstalk noise and protect weak signal. Based on such an extended training data set, the multi-data training method embedded in the iterative separation framework can result in different outputs at different iterations and converge to the best result in a shorter iteration number. Transfer learning can further improve the generalization and separation efficacy of our proposed method to deblend the simultaneous-source data. Our proposed method is tested on two synthetic data and two field data to prove the effectiveness and superiority in the deblending of the simultaneous-source data compared with the general training method, generic noise attenuation network and low-rank matrix factorization methods.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
customersupport@researchsolutions.com
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.