arXiv 2004.073882020-04-15physics.geo-phcs.LGeess.IV

大规模海底地震波场重建中的迁移学习

Transfer learning in large-scale ocean bottom seismic wavefield reconstruction

Georgia Institute of Technology（佐治亚理工学院）；China University of Petroleum - Beijing（中国石油大学（北京））

Mi Zhang, Ali Siahkoohi, Felix J. Herrmann

摘要：

由于成本的考虑，在海底采集中实现期望的接收器采样通常是不可能的。假设足够的源采样是可用的，这是可以实现的凭借互惠和现代随机化（随机源）海洋采集技术的使用，我们是在一个位置，训练卷积神经网络（CNN），使接收器采样到相同的空间网格作为密集的源采样。为了完成这一任务，我们形成训练对组成的密集采样数据和人工二次采样数据使用互易参数和假设的源站点采样是密集的。虽然这种方法已成功地用于恢复单色频率切片，但其在实践中的应用需要时域数据的波场重建。尽管可以选择并行化，但如果我们决定为每个频率独立进行训练和恢复，这种方法的总体成本可能会变得过高。由于不同的频率切片共享信息，我们提出使用转移训练的方法，通过使用从相邻频率切片获得的CNN权重来热启动训练，使我们的方法在计算上更有效。如果两个相邻的频率切片共享信息，我们将期望训练得到改进并更快地收敛。我们的目的是证明这一原则进行了一系列精心挑选的实验上一个相对较大规模的五维数据合成数据体与宽方位角三维海底节点采集。从这些实验中，我们观察到，通过迁移训练，我们能够在训练中显着加速，特别是在相对较高的频率下，连续的频率切片更加相关。

英文摘要：

Achieving desirable receiver sampling in ocean bottom acquisition is often not possible because of cost considerations. Assuming adequate source sampling is available, which is achievable by virtue of reciprocity and the use of modern randomized (simultaneous-source) marine acquisition technology, we are in a position to train convolutional neural networks (CNNs) to bring the receiver sampling to the same spatial grid as the dense source sampling. To accomplish this task, we form training pairs consisting of densely sampled data and artificially subsampled data using a reciprocity argument and the assumption that the source-site sampling is dense. While this approach has successfully been used on the recovery monochromatic frequency slices, its application in practice calls for wavefield reconstruction of time-domain data. Despite having the option to parallelize, the overall costs of this approach can become prohibitive if we decide to carry out the training and recovery independently for each frequency. Because different frequency slices share information, we propose the use the method of transfer training to make our approach computationally more efficient by warm starting the training with CNN weights obtained from a neighboring frequency slices. If the two neighboring frequency slices share information, we would expect the training to improve and converge faster. Our aim is to prove this principle by carrying a series of carefully selected experiments on a relatively large-scale five-dimensional data synthetic data volume associated with wide-azimuth 3D ocean bottom node acquisition. From these experiments, we observe that by transfer training we are able t significantly speedup in the training, specially at relatively higher frequencies where consecutive frequency slices are more correlated.

机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。

摘要：

英文摘要：

相关论文