In prestack Kirchhoff depth migration, the quality of the migration profile is determined by how well common image gathers (CIGs) are flattened and corrected. The migration velocity analysis (MVA) method is proposed to flatten the offset domain CIGs (ODCIGs) by updating the migration velocities. However, conventional MVA such as the residual curvature analysis (RCA) method is typically challenging to complex structures such as lateral velocity variations or high-dip reflectors. In addition, there are structural artifacts in ODCIGs due to the multipath ray problem even if the migration velocity is accurate. To address the above problems, we developed a kernel prediction network (KPN) for ODCIG flattening and correction. Compared with conventional neural networks, the primary advantage of the KPN is that its outputs consist of a series of predicted kernels instead of pixel vectors or matrices. These predicted kernels are capable of processing the input ODCIGs pixel by pixel and slice by slice. The KPN is built by an encoder-decoder architecture, and we modified the loss function of the KPN and introduced an extra parameter associated with the migration offset to ensure that the network is more effective for the ODCIG problem.The training samples of the KPN are acquired by a random extraction algorithm, and the corresponding labels are calculated by a convolution method.Image enhancements are also applied in training samples to improve the generalization capability of the KPN. We demonstrate the effectiveness of the KPN method by comparing it with the RCA method in both synthetic and field data examples. The results show that the KPN method can flatten the events in ODCIGs, correct the depth of the improperly migrated reflectors, remove unfocused artifacts simultaneously, and further yield high-quality migration profiles in different geological examples.

In the exploration of oil and gas reservoirs, channels are important locations for storing oil and gas, and their distribution in the subsurface is usually heterogeneous. Therefore, interpreting channels from seismic data is very meaningful for oil and gas exploration. Currently, methods for extracting channels from seismic data mainly rely on seismic attributes, edge detection algorithms, and deep learning. However, these methods cannot fully and accurately delineate the boundary details and structural characteristics of channels when faced with poor-quality seismic data. To address this issue, we proposed an interactive interpretation method for 2-D channels based on multiattributes and a convolutional neural network (CNN) that could more accurately identify and segment channel bodies with fuzzy boundaries and poor continuity. First, we selected seed points from seismic data to indicate the presence of channels in the area. To highlight the channel structures and reduce the difficulties in identification, we used the geodesic distance map calculated from the seed points and two seismic attributes commonly used for channel identification as the inputs to the CNN model. Next, the probability map of the channels was output from the CNN model to obtain the preliminary results of the channel recognition. Finally, we judged whether additional seed points needed to be added according to the preliminary results, and we combined the conditional random field (CRF) to fuse the geodesic distance map of the additional points with the probability map of the CNN model, ultimately obtaining accurate channel results. Compared to the automatic CNN method, this method extracted more complete channels and improved the continuity of the channel boundaries. In the case of complex seismic data, this method can effectively interpret channels and has important practical significance.

Tunnel seismic prediction (TSP) faces challenges in accurately imaging geological anomalies due to the confined spaces of subterranean tunnels in observation, differing markedly from the open spaces encountered in surface seismic exploration. Conventional prestack depth migration approaches, such as Kirchhoff and reverse time migration, are prone to producing annular artifacts centered on the survey line, as these standard imaging techniques cannot discriminate the propagation direction of reflected waves, imaging them indistinctly onto all possible imaging points. Although previous studies utilizing the polarization attributes of seismic waves can mitigate such symmetrical artifacts to some extent, they fall short of fully suppressing them, particularly for reflectors at small azimuth angles relative to the survey line. This paper proposes an innovative solution, Whole-Space Kirchhoff Polarization Depth Migration (WSKPDM), designed to thoroughly eliminate these migration artifacts. WSKPDM utilizes polarization information extracted from multiple seismic traces to ascertain the true propagation directions of reflected waves, thereby imaging only veritable reflection points. This effectively removes symmetrical artifacts, enhancing the visualization of subsurface geological structure. Testing on synthetic seismic data from diverse fault models and real-world tunnel data shows that WSKPDM surpasses conventional techniques in imaging accuracy. Moreover, WSKPDM demonstrates robust noise immunity even with random noise and reversed polarity in seismic data. With minimal adjustments to account for the distinct polarization directions of S-wave and P-wave, WSKPDM also allows efficient S-wave imaging. This promising WSKPDM method significantly improves the clarity and reliability of TSP imaging, providing a crucial tool for safer and more efficient tunnel construction.

Seismic data processing often encounters the challenge of near-surface complexity. Characterization of near-surface velocity structures is important for the selection of strategies and parameters in structure imaging. Repeated processing of a dataset without characterizations could waste large computational costs. Furthermore, manual characterization is typically time-consuming especially for super-large shot gathers. In this study, we propose a dilated convolution neural network (D-CNN) method to characterize near-surface velocity structures. The seismic shot gathers are labeled as layered, gradient, and complex velocity structures, respectively. The D-CNN uses fewer convolution layers to get the same size of receptive field as conventional CNNs and mitigates the overfitting problem. The proper architecture of the D-CNN is determined by evaluating different numbers of dilated convolution layers. For mitigating the generalization problem of D-CNN, we develop a sample acquisition method to automatically generate synthetic training samples with various near-surface features, and the other part of the training samples is acquired from field data in Sichuan, China. We propose an automatic linear move out (LMO) method to process the seismic shot gathers for better performance of D-CNN. The effectiveness of the D-CNN method is demonstrated in both synthetic and real data tests by comparing it with the k-means clustering method. The comparison results show that the D-CNN method can achieve higher accuracy compared with the k-means method. By applying the D-CNN method to the field data example, we develop an efficient early waveform inversion (EEWI) method. The results show that EEWI can save more than 65% computational costs to achieve nearly the same reconstruction accuracy compared with the conventional early waveform inversion (EWI) method.

Deep learning-based seismic horizon tracking methods have been extensively researched in the past few years. However, the predicted results of previous methods are currently unstable and require additional processing to obtain reasonable interpretations, limiting their applications to field seismic data. There are two potential reasons for this: 1) the training labels may not consider the uncertainty in horizon interpretation and 2) the characteristics of the seismic data used for training may differ from those for prediction (domain shift). In addition, the previous deep learning methods are mostly based on point-by-point cost functions, which are not well-suitable for horizon tracking problems. To address these issues, we proposed a method that mimics the process of manual horizon interpretation to avoid the domain shift problem and regard horizon identification and tracking as a problem of conditional probability density estimation using deep learning. In the North Sea F3 seismic data experiments, our proposed method can predict horizons accurately and stably when we select only 1.6% of the seismic sections to create labels. Taking mean absolute error (MAE) and accuracy as evaluation indices, the MAE for single-horizon prediction is as low as 2.0 ms, and the accuracy reaches 98.1%. A surprising finding revealed by the experiments is that the predicted results could provide a perspective of underground structures, such as faults and salt domes, demonstrating the feasibility of our method in interpreting complex field seismic data.

Fluvial facies exhibit higher porosity and permeability during sedimentation, making it crucial to study reservoir characteristics and assess the potential for oil and gas exploration. Traditional methods for identifying fluvial facies often rely on specific seismic attributes, which often require manual extraction of channel feature, especially when interpreting 3-D seismic data, which is inefficient. To improve the efficiency of channel interpretation in 3-D seismic data, we proposed a two-stage convolutional neural network to implement an interactive 3-D channel interpretation method. We generated 3-D seismic data with real channel structures and used their seismic attributes as inputs to the first stage network to automatically obtain initial and rough channel results. Then, based on this result, we added manual interaction to mark errors and combined the geodesic distance to transform the manual interaction information. Finally, we input the interaction information into the second-stage network to obtain high-quality identification results. Synthetic and field data examples demonstrated that this method retains good applicability even under complex geological conditions, providing valuable insights for the fields of oil and gas exploration and geological research.

Improving the computational efficiency of 3D FWI is a challenging task in seismic imaging. Using a multi-GPU cluster with acceleration strategy to simulate the wave propagation is an important means to improve its efficiency. We propose a multi-GPU acceleration 3D acoustic FWI algorithm based on the FDTD method in this paper. We improved the parallelism of 3D wavefield simulation algorithm based on a single GPU using a sliding 2D thread block algorithm with three different 2D shared memory stencils. For the multi-node implementation, we achieved bidirectional parallel data transfer between GPUs and used multiple kernels to further overlap the calculation and transfer. Numerical tests verify the validity of our 3D FWI algorithm accelerated with multi-GPU. The strategies used in our algorithm can significantly bring improvement in most cases. And the improvement is strongly related to the model size and the number of GPUs used. In our test, we achieve an acceleration of up to 19% in forward simulation and 25% in gradient calculation, compared with a typical multi-GPU implementation.

This research aims at the robust and high-resolution reconstruction of asteroid’s interior structure using lander-to-orbiter radar system. In recent years, the full waveform inversion (FWI) has been suggested as a potential method to asteroid tomography. Due to the limitation of computing capacity, FWI is usually performed by local rather than global optimization method, which makes it suffer from local minima problem especially when the signal lacks low-frequency components. To ensure the global convergence, FWI requires the initial model be accurate enough to avoid the local minima. But in practice, the low-frequency components are naturally absent in the remote radar signal as the limitation of bandwidth, and the prior information of asteroid is usually not sufficient to build an accurate initial model, which leads that using conventional FWI directly may not be capable to obtain a robust reconstruction. Considering the above problems, envelope inversion (EI) which works on the baseband signal and therefore, can recover the long-wavelength structure of asteroid is proposed as a supplementary to FWI. Initial model dependence and noise sensitivity of FWI and EI in asteroid tomography are analyzed based on 2-D numerical experiments. The EI + FWI combination constrained by total variation regularization shows the characteristics of good independence on the initial model and high imaging resolution. Based on EI + FWI strategy, a series of 3-D numerical experiments are conducted to test the influence of orbital measurement density and landing site on the tomography.

A new hybrid inversion methodology for petrophysical properties (porosity, water saturation, and volume of clay) based on partially stacked seismic angle gathers was presented. The innovation of this method is that it combines the advantages of high efficiency of analytical and semianalytical multistep petrophysical estimation with the advantages of spatial continuity and high resolution of geostatistical direct inversion of reservoir parameters. A trace-by-trace linearized amplitude versus offset (AVO) inversion and semianalytical petrophysical estimation approach could efficiently achieve a preliminary estimation of reservoir parameters under some assumptions and approximations. These laterally unconstrained preliminary estimation results are able to provide effective information for finer-resolution geostatistical simulation and improve the computational efficiency of stochastic optimization. The 3-D fast Fourier transform moving average (FFT-MA) geostatistical cosimulation and the stochastic optimization by gradual deformation method (GDM) improve the resolution and spatial continuity of the preliminary estimation results. At the same time, stochastic inversion overcomes the assumptions in the analytical inversion algorithm that the parameters need to conform to the logarithmic Gaussian distribution and the linear approximation of the Zoeppritz equation. The method was tested on a synthetic case and a real case. The results show that compared with the analytical and semianalytical methods, this hybrid inversion can obtain results with finer resolution and better spatial continuity, and the computational efficiency is significantly improved compared with the geostatistical direct inversion of reservoir parameters. Uncertainty evaluation can be obtained by performing statistical analysis on the multiple realizations of stochastic inversions.

Salt body extraction plays an important role in the analysis of salt structures and the exploration of oil and gas. Seismic attributes and edge detection algorithms, which require manual effort, are the conventional methods of extracting salt boundaries from seismic images. Convolutional neural networks (CNNs) have become the state-of-the-art automatic segmentation method for seismic interpretation. However, the fully automatic results of the extraction of salt boundaries may still need to be modified to become accurate and robust enough for practical production. We present a novel deep-learning-based interactive segmentation method for extracting salt boundaries. To incorporate the interaction points into our method, we transform positive and negative points into two Euclidean distance maps (EDMs), which are combined with seismic images to train our CNN model. The model is composed of a U-net and a pyramid pooling module (PPM), and it is trained on the Tomlinson Geophysical Services (TGS) Salt Identification Challenge dataset. Then, we use a graph cut algorithm to refine the likelihood maps predicted by our CNN model and, subsequently, update the salt boundaries. Some field examples show that the proposed method outperforms fully automatic CNN methods with a higher matching degree of the ground truth.