Deblending by modified dictionary learning using Sparse Parameter Training

Considerable attempts have been made on removing the crosstalk noise in a simultaneous source data using the popular K-means Singular Value Decomposition algorithm ( KSVD ). Several hybrids of this method have been designed and successfully deployed, but the complex nature of blending noise makes it difficult to manipulate easily. One of the challenges of the K-means Singular Value Decomposition approach is the chal-lenge to obtain an exact KSVD for each data patch which is believed to result in a better output. In this work, we propose a learnable architecture capable of data training while retaining the K-means Singular Value Decom-position essence to deblend simultaneous source data.     

A multi-data training method for a deep neural network to improve the separation effect of simultaneous-source data

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.     

基于结构匹配反褶积的同时震源数据直接成像

针对同时震源数据最小二乘偏移(LSM)计算效率低的问题,笔者研究并提出了同时震源混合数据直接成像的结构匹配反褶积(SMD)方法。通过分窗的方式求取局部Hessian逆,加入局部结构约束,可以压制混合数据成像串扰噪音的同时对成像做照明补偿,提高成像质量。并在复杂sigesbee2A模型的数值测试中验证了SMD方法的有效性。结果表明,SMD能够有效地压制成像中的串扰噪音,且对成像振幅有一定的补偿作用,计算效率相比LSM有巨大提升。