![]() In this study, we make detailed comparisons between the DL models using DA and EL. Qualitatively and quantificationally analyzing the performances of these two techniques is a rarely studied domain. data augmentation (DA) and ensemble learning (EL). For the DL based models, there are two widely used techniques, which can enhance the model performance, i.e. Recently, deep learning (DL) models are used to automatic seismic fault interpretation. ![]() Model test and case study prove that the proposed fused algorithm can effectively identify the amplitude and waveform differences in seismic data.ĭelineating seismic faults is one of the main steps in seismic structure interpretation. This paper proposes an amplitude coherence attribute to measure semblance of root-mean-square (RMS) amplitudes of multiple traces and fuses it with the third-generation coherence (C3) to describe the boundary of underground river. Typically, the coherence algorithm based on eigen-structure analysis is the most robust, but is sensitive to waveform differences and insensitive to amplitude differences. There are many algorithms to determine the coherence. Thus, it is a widely used key technique in seismic interpretation. Seismic coherence attribute can highlight seismic discontinuity caused by tectonic movements, reservoir boundaries, sedimentary body boundaries or other factors. In the Tarim Basin, the main hydrocarbon reservoirs of Ordovician carbonate rocks are fractured-vuggy reservoirs, of which the underground river type reservoirs are an important type. In the end, representative coherence applications in fault, channel, volcano, and carbonate karst are demonstrated in Sect. 7 In order to effectively extract target signal features and suppress the noise interference at the same time, coherence enhancement methods are mentioned in Sect. 6. Nevertheless, there are also possible artifacts associated with the coherence implementation algorithms that influence the quality of seismic coherence attributes (Sect. 5). So we can observe some anisotropic features from the methods discussed in Sect. 4. In contrast to the poststack seismic data, prestack seismic gathers contain more information about the dynamics (amplitudes and phase distortions) of seismic waves as they propagate along the ray. While Section 2 treats the seismic data as an integrated whole, Sect. 3 discusses the coherence calculation on extracted spectral band-limited components, where certain previously overlooked features show up in the scale-based coherence. Section 2 introduces the seismic coherence calculation methods. To better compare different techniques, field applications are provided, where different disciplinary coherence attributes with enhancement techniques are calculated for the channel, fault, carbonate karst, and volcano interpretation.Ī flow diagram of the sections in this survey. In addition, we also discuss the possible coherence artifacts and pitfalls. We cover the development of the seismic coherence attributes via introducing existing approaches for coherence calculation, enhancement, spectral band-limited coherence methods, and offset-/azimuth-limited coherence methods. In this survey, we provide a general overview of seismic coherence, which is commonly used to delineate structural and stratigraphic discontinuities. We have also seen different coherence enhancement techniques and modified ways for coherence calculation to address different problems in diverse field applications. In the last 25 years, there have been different kinds of approaches to calculate seismic coherence attributes, such as cross-correlation, semblance, and eigen-structure. Since its appearance in 1995, seismic coherence has become one of the most popular and highly recognized interpretation tools. Seismic coherence is of the essence for seismic interpretation as it highlights seismic discontinuity features caused by the deposition process, reservoir boundaries, tectonic movements, etc.
0 Comments
Leave a Reply. |
AuthorWrite something about yourself. No need to be fancy, just an overview. ArchivesCategories |