To streamline fast-track processing of large data volumes, we have developed a deep learning approach to deblend seismic data in the shot domain based on a practical strategy for generating high-quality training data along with a list of data conditioning techniques to improve performance of the data-driven model. We make use of unblended shot gathers acquired at the end of each sail line, to which the access requires no additional time or labor costs beyond the blended acquisition. By manually blending these data we obtain training data with good control of the ground truth and fully adapted to the given survey. Furthermore, we train a deep neural network using multi-channel inputs that include adjacent blended shot gathers as additional channels. The prediction of the blending noise is added in as a related and auxiliary task with the main task of the network being the prediction of the primary-source events. Blending noise in the ground truth is scaled down during the training and validation process due to its excessively strong amplitudes. As part of the process, the to-be-deblended shot gathers are aligned by the blending noise. Implementation on field blended-by-acquisition data demonstrates that introducing the suggested data conditioning steps can considerably reduce the leakage of primary-source events in the deep part of the blended section. The complete proposed approach performs almost as well as a conventional algorithm in the shallow section and shows great advantage in efficiency. It performs slightly worse for larger traveltimes, but still removes the blending noise efficiently.
Geological Everything Model 3D: A Promptable Foundation Model for Unified and Zero-Shot Subsurface Understanding
University of Science and Technology of China, School of Earth and Space Sciences（中国科学技术大学地球和空间科学学院）；University of Texas at Austin, UT Institute for Geophysics（德克萨斯大学奥斯汀分校UT地球物理研究所）；NVIDIA（NVIDIA公司）
Iterative separation of coherent blended signals in common shot gathers using synchrosqueezed curvelet-Radon constraints
State Key Laboratory of Oil and Gas Reservoir Geology and Exploitation, Chengdu University of Technology（油气藏地质及开发工程国家重点实验室，成都理工大学）；College of Geophysics, Chengdu University of Technology（地球物理学院，成都理工大学）；Key Laboratory of Earth Exploration and Information Technology of Ministry of Education, Chengdu University of Technology（教育部地球探测与信息技术重点实验室，成都理工大学）
StorSeismic: A new paradigm in deep learning for seismic processing
King Abdullah University of Science and Technology（阿卜杜拉国王科技大学）
地震数据上的机器学习任务通常是顺序和单独训练的，即使它们利用数据的相同特征（即几何特征）。我们提出StorSeismic，作为地震数据处理的框架，它包括神经网络预训练和微调程序。具体而言，我们利用神经网络作为预处理模型来存储特定数据集的地震数据特征以用于任何下游任务。在预训练之后，所得到的模型可以稍后通过微调过程来使用，以使用有限的额外训练来执行任务。BERT（Bidirectional Encoder Representations from Transformer）是一种Transformer模型的形式，经常用于自然语言处理（NLP），最近用于视觉任务，为该框架提供了最佳平台。BERT的注意力机制，在这里应用于炮集内的一系列道，能够捕获和存储地震数据的关键几何特征。在自我监督步骤中，我们根据现场数据以及综合生成的数据对StorSeismic进行预训练。然后，我们使用标记的合成数据以监督的方式微调预训练的网络，以执行各种地震处理任务，如去噪、速度估计、初至拾取和动校正。最后，使用微调后的模型对现场数据进行推理，得到了满意的结果。
GeoFWI3D: Large-scale 3D Velocity Model Dataset for Deep Learning-assisted Seismic Imaging
The University of Texas at Austin（德克萨斯大学奥斯汀分校）；Los Alamos National Laboratory（洛斯阿拉莫斯国家实验室）；Uppsala University（乌普萨拉大学）；The University of Texas at Permian Basin（德克萨斯大学佩米安盆地分校）；King Fahd University of Petroleum and Minerals（法赫德国王石油与矿产大学）
Reliability-calibrated deep residual full-waveform inversion using geometry-invariant physics encoding: synthetic validation and zero-shot Marmousi-2 testing
Institute of Geophysics, Polish Academy of Sciences（波兰科学院地球物理研究所）；University of Allahabad（阿拉哈巴德大学）；CSIR–National Geophysical Research Institute（印度科学工业研究理事会国家地球物理研究所）
