In this paper, we propose a novel approach of deep-learning-based seismic horizon auto-picking that introduces a modified vector quantized variational autoencoder (VQ-VAE) framework to improve the accuracy of seismic horizon interpretation and, for the first time, quantitatively evaluate the uncertainty of the auto-picked horizon by exploiting the concept of entropy. Compared with the conventional VQ-VAE approach, the proposed method not only modifies the VQ-VAE model with more deep-learning channels at each layer of the network to enhance the performance of horizon auto-picking within the VQ-VAE framework, but also extends the 1D seismic labels with more continuous samplings within a single trace to boost the stability of auto-picked horizon in geologically complex settings and also significantly suppress the resulting uncertainty. To further improve the resulting accuracy in geologically complex settings, we introduce the directional structure tensor to extract a more reliable initial horizon and, moreover, a dilated horizon searching strategy to extend the capacity of the proposed method in dealing with the large fault displacement and reducing the computational cost simultaneously. Additionally, the resulting uncertainty quantitatively measured by entropy can also serve as an effective indicator to enable a further refinement of the auto-picked result accordingly. Both 2D example and 3D field applications are carried out to validate the effectiveness of the proposed method.
In seismic mapping of reservoirs, it is usually difficult to identify a single layer in a thin interbed formation. The main reason for this is interference of adjacent layers in the thin beds. We have developed a slice method basis spectral decomposition workflow to decrease this interference rely on the good vertical resolution of the thin layers, which is not always achievable. To overcome this, we have developed two frequencies at which the thin-bed response is weakest at a fixed time. These are the low minimum interference (LMI) and high minimum interference frequencies. The LMI frequency is useful for thin-bed detection when the thin bed cannot be resolved vertically in the seismic profile. The LMI frequency is usually less than the dominant frequency. However, the thin bed can still be identified on the seismic slice at this frequency. In practice, the LMI frequency can be estimated from the time-frequency spectrum and used in spectral decomposition using wavelet transformation to generate the amplitude slices for various frequencies. The amplitude slicing method was verified by case studies using synthetic and real data from a seismic exploration site in the Junggar Basin, China. The results indicate that this methodology is feasible and effective in identifying oil reservoirs in the thin interbeds strata.
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.