Attenuation of linear noise based on denoising convolutional neural network with asymmetric convolution blocks
Attenuation of linear noise based on denoising convolutional neural network with asymmetric convolution blocks
复制标题
DOI：
10.1080/08123985.2021.1999772
复制
发表时间：
2021-11
影响因子：
0.9
通讯作者：
Yijun Yuan;Y. Zheng;Xu Si
中科院分区：
文献类型：
--
作者：
Yijun Yuan;Y. Zheng;Xu Si
震源产生的线性噪声是地震数据中最常见的噪声类型之一。地震记录中经常出现一组或多组具有强能量的倾斜线性事件，并严重降低地下反射的质量。因此，如何有效去除这种噪声是提高反射质量的关键。在这里，我们使用一种将前馈降噪卷积神经网络（DnCNN）与非对称卷积块（ACB）相结合的方法来衰减地震数据中的线性噪声。与传统的滤波方法相比，该方法对信号和噪声的假设较少；我们只是训练神经网络来识别地震数据中的反射特征。 DnCNN 是一种有监督的深度学习方法。它需要足够的训练数据来优化网络参数。因此，我们生成大量数据对（包括合成和真实地震数据）以馈送到网络。这种数据输入使网络能够直接识别地震数据中的反射，从而获得去噪数据。基于地震数据中线性噪声的特点，我们将DnCNN与ACB相结合构建了非对称网络架构。这使得网络能够自动识别地震数据中的反射信号。为了验证所提出方法的性能，我们将其应用于合成和真实地震数据。结果表明，该方法能够有效地从噪声数据中识别出信号，并且与其他四种方法相比，在线性噪声的衰减和信号的保存方面取得了更好的效果。
Source-generated linear noise is one of the most common types of noise in seismic data. One or more groups of slanted linear events with strong energy often appear in seismic records and severely degrade the quality of subsurface reflections. Therefore, how to effectively remove this noise is the key to improve the quality of reflections. Here, we use a method that combines a feed-forward denoising convolutional neural network (DnCNN) with asymmetric convolution blocks (ACB) to attenuate linear noise in seismic data. Compared with traditional filter methods, this method involves less assumptions concerning the signals and noise; we merely train the neural network to recognise the features of reflections in seismic data. The DnCNN is a supervised deep learning method. It needs sufficient training data to optimise network parameters. Therefore, we generate numerous pairs thereof – including synthetic and real seismic data – to feed to the network. This input of data enables the network to identify reflections in seismic data directly and thus obtain the denoised data. Based on the characteristics of linear noise in seismic data, we build an asymmetric network architecture by combining the DnCNN with ACB. This enables the network to develop an ability to automatically identify reflected signals in seismic data. To validate the performance of the proposed method, we apply it to synthetic and real seismic data. The results demonstrate the method can effectively identify signals from noisy data and obtain better results in attenuation of linear noise and preservation of signals compared with the four other methods.