当前位置: X-MOL 学术Geophysics › 论文详情
Our official English website, www.x-mol.net, welcomes your feedback! (Note: you will need to create a separate account there.)
Deep-seismic-prior-based reconstruction of seismic data using convolutional neural networks
Geophysics ( IF 3.0 ) Pub Date : 2021-02-18 , DOI: 10.1190/geo2019-0570.1
Liuqun Liu 1 , Lihua Fu 1 , Meng Zhang 2
Affiliation  

The reconstruction of seismic data with missing traces has been a long-standing issue in seismic data processing. Deep learning (DL) has emerged as a popular tool for seismic interpolation; it learns priors from training data sets of incomplete/complete data pairs. However, these DL methods are restricted to training data because they are supervised. When the features of the testing and training data are different, the recovery performance decreases, which prevents practical application. We have introduced a “deep-seismic-prior-based” approach via a convolution neural network (CNN), which captures priors based on the particular structure of the CNN, but it does not need any training data set. The ill-posed inverse problem in seismic interpolation is thus solved using the CNN structure as a prior, and the learned network weights are the parameters that represent the seismic data. Because the convolutional filter weights are shared to achieve spatial invariance, the CNN structure can function as a regularizer to guide network learning. In our method, corrupted seismic data are reconstructed during the iterative process by minimizing the mean square error between the network output and the original data. We applied our method for interpolating irregularly and regularly missing traces in prestack and poststack seismic data. The experimental results indicate that our approach outperforms the traditional singular spectrum analysis and the dealiased Cadzow methods commonly used in the reconstruction of such data.

中文翻译:

基于卷积神经网络的基于深度地震先验的地震数据重建

丢失迹线的地震数据的重建一直是地震数据处理中的长期问题。深度学习(DL)已经成为地震插值的流行工具。它从不完整/完整数据对的训练数据集中学习先验。但是,由于这些DL方法受到监督,因此仅限于训练数据。当测试数据和训练数据的特征不同时,恢复性能会降低,从而无法进行实际应用。我们通过卷积神经网络(CNN)引入了一种“基于深度地震先验”的方法,该方法基于CNN的特定结构捕获先验,但不需要任何训练数据集。因此,使用CNN结构作为先验方法可以解决地震插值中的不适定逆问题,所学习的网络权重是代表地震数据的参数。因为共享卷积滤波器权重以实现空间不变性,所以CNN结构可以充当正则化器来指导网络学习。在我们的方法中,通过最小化网络输出与原始数据之间的均方误差,可以在迭代过程中重建损坏的地震数据。我们将我们的方法用于对叠前和叠后地震数据中不规则和规则缺失的迹线进行插值。实验结果表明,我们的方法优于传统的奇异谱分析和重建此类数据时常用的脱碳的Cadzow方法。CNN结构可以充当引导网络学习的规则化器。在我们的方法中,通过最小化网络输出与原始数据之间的均方误差,可以在迭代过程中重建损坏的地震数据。我们将我们的方法用于对叠前和叠后地震数据中不规则和规则缺失的迹线进行插值。实验结果表明,我们的方法优于传统的奇异谱分析和重建此类数据时常用的脱碳的Cadzow方法。CNN结构可以充当引导网络学习的规则化器。在我们的方法中,通过最小化网络输出与原始数据之间的均方误差,可以在迭代过程中重建损坏的地震数据。我们将我们的方法用于对叠前和叠后地震数据中不规则和规则缺失的迹线进行插值。实验结果表明,我们的方法优于传统的奇异谱分析和重建此类数据时常用的脱碳的Cadzow方法。我们将我们的方法用于对叠前和叠后地震数据中不规则和规则缺失的迹线进行插值。实验结果表明,我们的方法优于传统的奇异谱分析和重建此类数据时常用的脱碳的Cadzow方法。我们将我们的方法用于对叠前和叠后地震数据中不规则和规则缺失的迹线进行插值。实验结果表明,我们的方法优于传统的奇异谱分析和重建此类数据时常用的脱碳的Cadzow方法。
更新日期:2021-02-19
down
wechat
bug