Search

Seismic records from reflection seismic exploration in complex surface areas often contain scattered direct waves, a type of scattered waves generated by direct waves propagating on a rugged surface. For imaging reflections, scattered direct waves are regarded as noise, which lowers the signal‐to‐noise ratio of the reflected waves and deteriorates the quality of the seismic profile. Importantly, it is very challenging to separate scattered direct waves with strong energy and complex wave field characteristics owing to the rugged surface. In recent years, the rapid development of machine‐learning technology has broadened and advanced the application of deep learning in denoising seismic data. In this context, we propose an approach to using the convolutional autoencoder, a deep learning network, to intelligently separate scattered direct waves from seismic records on a rugged surface. The spectral element method is applied to simulate the elastic wave seismic records and scattered direct waves on a rugged surface. The synthetic shot gathers on the rugged ground are employed as the input for training the convolutional autoencoder network, while the simulated scattered direct waves on the uniform half‐space with the same rugged ground are employed as the label data for training. After the network training is completed, the trained convolutional autoencoder network can be applied to predict scattered direct waves from seismic records. The numerical experiments demonstrate that the proposed approach has good potential for suppressing complex scattered direct waves generated by direct waves propagating on a rugged surface. [ABSTRACT FROM AUTHOR]

In seismic data acquisition, because of several factors, such as surface barriers, receiver failure, noise contamination and budget control, seismic records often exhibit irregular sampling in the space domain. As corrupted seismic records have a negative effect on seismic migration, inversion and interpretation, seismic trace interpolation is a key step in seismic data pre‐processing. In this paper, we propose a high‐efficiency and high‐precision seismic trace interpolation method for irregularly spatially sampled data by combining an extreme gradient boosting decision tree and principal component analysis in a semi‐supervised learning method. The adjacent trace number, sampling number and amplitudes of the effective seismic data were taken as features to build the training data set for the extreme gradient boosting decision tree. Principal component analysis is applied to remove redundant information and accelerate the training speed. This is different from the traditional trace interpolation method in that the proposed method is data‐driven; therefore, it does not require any assumptions. Compared with other deep learning‐based trace interpolation methods, the proposed method has fewer control parameters and learning labels and a smaller training cost. Experiments using synthetic and field data demonstrated the validity and flexibility of this trace interpolation method. [ABSTRACT FROM AUTHOR]

Deep learning has been used in seismic exploration to solve seismic inversion problems, however it requires sufficient and diverse training samples and labels to obtain satisfactory results. Insufficient training labels are a common problem since labels usually come from well‐logging data, which are limited and sparsely distributed. This can result in a trained network with poor generalizability. A novel complete synthetic dataset‐driven method utilizing convolutional neural network is presented for seismic amplitude‐versus‐offset attributes P and G inversion. Gaussian simulation sampling with physical constraints is used to generate a complete elastic parameter dataset by traversing the entire elastic parameter model space. By randomly combining elastic parameters from the full elastic parameters model space, sufficient synthetic pre‐stack amplitude‐versus‐offset gathers and attribute datasets are generated for training the convolutional neural network. Compared with the limited real data‐driven convolutional neural network, the complete synthetic dataset‐driven convolutional neural network has better generalizability. Broadband training labels improve the accuracy and resolution of the complete synthetic dataset‐driven convolutional neural network's inversion results beyond that of the conventional least‐square data‐fitting method. The complete synthetic dataset‐driven convolutional neural network is robust for processing noise‐contaminated seismic data, but if the frequency band of the labels for training the network is too wide and the signal‐to‐noise ratio of pre‐stack amplitude‐versus‐offset gathers is too low, the quality of the inversion results will reduce. The Marmousi II model and field data examples show that the novel complete synthetic dataset‐driven convolutional neural network can extract higher‐resolution amplitude‐versus‐offset attributes P and G. [ABSTRACT FROM AUTHOR]

The blended acquisition allows multiple sources to be simulated simultaneously in a narrow time interval, which can improve the acquisition efficiency and reduce the acquisition cost tremendously. However, the overlapped information from multiple sources poses challenges for traditional seismic data migration or inversion algorithms. Thus, accurate and efficient deblending should be implemented as a pre-requisite. Traditional inversion-based deblending algorithms can provide deblended data with a high computational burden, especially for a large volume of seismic data. As a deep learning strategy can match seismic data accurately in a nonlinear way through supervised learning, we propose a U-net-based accurate deblending algorithm, which incorporates transfer learning and an iterative strategy. A set of labeled synthetic data with a blending fold of 2 are classified into the training and validation data for U-net training and validation. Field data are regarded as the test data to assess the performance of the trained U-net. To guarantee the deblending performance of the field data to some extent, parts of field data with labels are used to fine-tune the trained U-net based on transfer learning. The fine-tuning procedure is relatively fast within several minutes. To further improve the deblending performance, we incorporate an iterative strategy with the fine-tuned U-net. The deblending performance is promising in the quality and computational efficiency compared with the curvelet-thresholding-based deblending method, which demonstrates the validity of the proposed intelligent deblending method. [ABSTRACT FROM AUTHOR]