The data-driven surface-related multiple elimination (SRME)-type approach requires fully sampled sources and receivers during the multidimensional convolution process. Otherwise, the estimated multiples will be aliased. Compared to expensive reconstruction processes before prediction, dealiasing on the estimated multiples from limited sources might provide a potential easier solution in a 2D scenario, where deep learning (DL)-based methods suit well for this highly non-linear problem. Unfortunately, DL-based multiple dealising will not function well for 3D data due to extremely coarse sampling in either source or receiver side. Thus, data interpolation/reconstruction is the only option, though the performance might not be desired. Generalized surface multiple prediction (GSMP) is the most used on-the-fly interpolation approach in 3D. Still, GSMP accuracy heavily relies on the existing traces. When fed with coarsely sampled recorded data only, GSMP tends to generate multiples with low amplitude and distorted phase, especially for small offsets. We propose a U-Net framework to repair GSMP estimated multiples such that the amplitude loss and distorted phase can be restored. In this way, the strong non-linear mapping power from DL can help repair the GSMP estimated multiples.@en

Ground penetrating radar (GPR) is a commonly used technology for identifying and examining ice. The low electrical conductivity and the uniformity of ice covers provide GPR with exceptional signal penetration and, thus, the ability to reveal the internal layers of glaciers. To extract the necessary information, wavefield separation and imaging processing is required. This abstract presents a simultaneous diffraction and reflection imaging (SDRI) framework for ice detection using GPR data. The framework can extract hidden information in the recorded data by using wavefield separation and enhancement, for instance, the internal small-scale diffracted objects and the internal reflection layer. The traditional methods of processing and imaging data from GPR cannot provide a comprehensive understanding of the subsurface, particularly in Antarctica, due to the mutual interference between diffraction and reflection energy. This leads to the valuable geological information being concealed. The SDRI framework allows for information from both diffraction and reflection to be obtained without any interference. The diffraction method will focus on small-scale geological features while reflection will highlight large-scale structural information. The proposed SDRI framework has been applied to a field ice GPR data set from Antarctica, demonstrating its effectiveness in uncovering the hidden geology buried under the ice.@en

A field experiment was conducted in Zuidbroek, the Netherlands to compare the performance of a DAS and horizontal-geophone system for shear-wave (SV) reflection surveying. The data were subjected to processing for reflection imaging, including conversion of the geophone data to strain-rate data, to enable such a comparison on migrated-section level. Our findings indicate that DAS straight-fibre data shows a lower-frequency information content, but achieves better reflector continuity than the geophone data due to the more continuous and denser sampling with the DAS system.@en

Seismic data interpolation is a topic well suited for deep learning (DL) applications. Scaling operation-based DL neural networks, e.g., U-Net, have been popular since its booming development in the field of seismic data processing. Although many successful studies using U-Net on seismic data, scientists start to realize the downside of its implementation, i.e., large trainable parameters (normally larger than 1 million), the potential risks of over-fitting, and tedious hyper-parameter selection. Therefore, in this abstract, we introduce a mixed-scale dense convolutional neural network (MS-DCNN) for seismic data interpolation with relatively few trainable parameters to reduce the risk of over-fitting. This MS-DCNN was originally developed for biomedical image processing. In addition, this neural network can be trained with relatively small training set. Via a field data case study, the different behavior of U-Net and MS-DCNN is analyzed and compared for a specific interpolation problem, where 9 consecutive shot records were missing from a 2D line of marine seismic data.@en