Mapping of seismic and lithologic facies from 3D reflection seismic data plays a key role in depositional environment analysis and reservoir characterization during hydrocarbon exploration and development. Although a variety of machine-learning methods have been developed to speed up interpretation and improve prediction accuracy, there still exist significant challenges in 3D multiclass seismic facies classification in practice. Some of these limitations include complex data representation, limited training data with labels, imbalanced facies class distribution, and lack of rigorous performance evaluation metrics. To overcome these challenges, we have developed a supervised convolutional neural network (CNN) and a semisupervised generative adversarial network (GAN) for 3D seismic facies classification in situations with sufficient and limited well data, respectively. The proposed models can predict 3D facies distribution based on actual well log data and core analysis, or other prior geologic knowledge. Therefore, they provide a more consistent and meaningful implication to seismic interpretation than commonly used unsupervised approaches. The two deep neural networks have been tested successfully on a realistic synthetic case based on an existing reservoir and a real case study of the F3 seismic data from the Dutch sector of the North Sea. The prediction results show that, with relatively abundant well data, the supervised CNN-based learning method has a good ability in feature learning from seismic data and accurately recovering the 3D facies model, whereas the semisupervised GAN is effective in avoiding overfitting in the case of extremely limited well data. The latter seems, therefore, particularly adapted to exploration or early field development stages in which labeled data from wells are still very scarce.
We describe here methods of estimating interval velocities based on two nonlinear optimization methods; very fast simulated annealing (VFSA) and a genetic algorithm (GA). The objective function is defined using prestack seismic data after depth migration. This inverse problem involves optimizing the lateral consistency of reflectors between adjacent migrated shot records. In effect, the normal moveout correction in velocity analysis is replaced by prestack depth migration. When the least‐squared difference between each pair of migrated shots is at a minimum, the true velocity model has been found. Our model is parameterized using cubic‐B splines distributed on a rectangular grid. The main advantages of using migrated data are that they do not require traveltime picking, knowledge of the source wavelet, and expensive computation of synthetic waveform data to assess the degree of data‐model fit. Nonlinear methods allow automated determination of the global minimum without relying on estimates of the gradient of the objective function, the starting model, or making assumptions about the nature of the objective function itself. For the velocity estimation problem, the VFSA converges 4 to 5 times faster than the GA for both a 2-D synthetic example and a structurally complex real data example from the Gulf of Mexico. Though computationally intensive, this problem requires few model parameters, and use of a fast traveltime code for Kirchhoff migration makes the algorithm tractable for real earth problems.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.