Mingjun Su

Seismic attributes are critical in understanding geologic factors, such as sand body configuration, lithology, and porosity. However, existing attributes typically reflect the combined response of multiple geologic factors. The interplay between these factors can obscure the features of the target factor, posing a challenge to its direct seismic characterization, particularly when the factor is subtle. To address this, we develop an innovative neural network designed to disentangle and characterize the individual geologic factors within seismic data. Our approach divides the geologic information in the seismic data into two categories: a single geologic factor of interest and an aggregate of all other information. A novel feature-swapping mechanism within our network facilitates the disentanglement of these two categories, providing an interpretable representation. We use a triplet loss function to differentiate data samples with similar waveforms but varying subtle geologic details, thus enhancing the extraction of distinct features. In addition, our network uses a cotraining strategy to integrate the synthetic and actual field data during the training process. This strategy helps mitigate the potential performance degradation arising from the discrepancies between simulated and actual field data. We apply our method to synthetic data experiments and field data from two geologically distinct areas. Current results indicate that our method surpasses traditional approaches, such as a deep autoencoder and a convolutional neural network classifier, in extracting seismic attributes with more explicit geophysical implications.

The core challenges to automatic full-horizon tracking are how to establish a potential local connection relationship between the horizon points, conduct accurate global diffusion in a three-dimensional space, and finally, how to form a complex horizon surface. The existing attribute-based horizon-tracking methods based on waveform similarity, dip guidance, and RGT (relative geological time) can not solve the problems of local connection and global diffusion at the same time. In view of this challenge, this paper proposes an automatic 3D seismic horizon-tracking method based on global corrugated diffusion, which can completely integrate local connection and global diffusion so that all horizons in the whole data volume can be interpreted simultaneously. For the problem of local horizon-point connection, this paper uses the correlation between seismic trace pairs based on DTW (dynamic time warping) correlation to mine the connection mode between horizon points. For the global diffusion problem, this paper proposes the realization of global modeling based on the relationship between seismic samples, constructing a complex 3D horizon through a central ripple-diffusion process. The example shows that the horizon tracked by this method well reflects the original stratum occurrence and stratum-contact relationship, retains the structural details, accurately reflects the structural shape, and realizes automatic tracking across faults.

Underground flow paths (UFP) often play an important role in the illustration of geological data by geologists, especially in illustrating geological data and revealing stratigraphic structures, which can help domain experts in their exploration of petroleum information. In this paper, we present a new immersive visualization tool to help domain experts better illustrate stratigraphic data. We use a visualization method based on bit-array-based 3-D texture to represent stratigraphic data. Our visualization tool has three major advantages: it allows for flexible interaction at the immersive device, it enables domain experts to obtain their desired UFP structure through the execution of quadratic surface queries, and supports different stratigraphic display modes, as well as switching and integration geological information flexibly. Feedback from domain experts has shown that our tool can contribute more for domain experts in the scientific exploration of stratigraphic data, compared to the existing UFP visualization tools in the field. Thus, experts in geology can have a more comprehensive understanding and more effective illustration of the structure and distribution of UFPs.

The traditional constant time window-based waveform classification method is a robust tool for seismic facies analysis. However, when the interval thickness is seismically variable, the fixed time window is not able to contain the complete geologic information of interest. Therefore, the constant time window-based waveform classification method is inapplicable to conduct seismic facies analysis. To expand the application scope of seismic waveform classification in the strata with varying thickness, we have proposed a novel scheme for unsupervised seismic facies analysis of variable window length. The input of the top and bottom horizons can guarantee the comprehensive geologic information of the target interval. Throughout the whole workflow, we use the dynamic time warping (DTW) distance to measure the similarities between seismic waveforms of different lengths. First, we improve the traditional spectral clustering algorithm by replacing the Euclidean distance with the DTW distance. Therefore, it can be applicable in the interval of variable thickness. Second, to solve the problem of large computation when applying the improved spectral clustering approach, we adopt the method of seismic data thinning based on the technology of the superpixel. We combine these two algorithms and perform the integrated workflow of improved spectral clustering. The experiments on synthetic data show that the proposed workflow outperforms the traditional fixed time window-based clustering algorithm in recognizing the boundaries of different lithologies and lithologic associations with varying thickness. The practical application shows great promise for reservoir characterization of interval with varying thickness. The plane map of waveform classification provides convincing reference to delineate reservoir distribution of the data set.

A method of identifying lithostratigraphic traps based on seismic sedimentology is proposed. We first establish a 3D high-resolution (fifth-order) sequence stratigraphic framework by using the stratal slices. Then, the reservoir distribution and reservoir-seal assemblage are investigated within the high-resolution sequence framework. This method turns the interpretation of lithostratigraphic traps from traditional seismic facies-based approach to the dynamic analysis of high-resolution seismic geomorphic information. We divide the lower Sha-1 member in the Banqiao Sag, Bohai Bay Basin, East China, into fourth- and fifth-order sequences by applying our method. The fifth-order sequence corresponding to Sha1-2 shows that the fan delta-distal subaqueous fan depositional system can be observed at the bottom of Sha1-2. The bounding fault and paleogeomorphology control the deposition of sand, whereas the sand bodies in the fan delta and distal subaqueous fan are developed near the bounding fault and the open lake basin, respectively. We then predict the sand thickness based on the well logs and seismic amplitudes. Moreover, according to the structural features, at least four lithostratigraphic traps are identified. These traps form a good reservoir-seal assemblage with overlying mudstones deposited during the period of lacustrine level rising. The drilling results in Trap-3 suggest that, our method can be a method of choice for effectively identifying the lithostratigraphic traps, a significant measure for hydrocarbon exploration.

Accurate and efficient seismic horizon interpretation is important for seismic geomorphology study. By integrating the improved density-based clustering method to generate horizon patches and a heuristic combining strategy to merge horizon patches, we have developed a novel data mining approach to automatically extract globally optimal horizons for detailed geomorphologic interpretation. First, the application of improved density-based clustering method has distinct merits in calculation speed and avoiding the phenomenon of mis-ties. We design a heuristic combining strategy to effectively combine the horizon patches. It is also able to ameliorate the problem of mis-ties that frequently occurs in horizon picking. Second, the proposed algorithm can identify abnormal unit in terms of independent horizon fragments. Furthermore, the introduced method is capable of detecting small-scale seismic geomorphologic features. The applications indicate good real-time performance of our new global interpretation algorithm in automated-tracking speed and quality. Our method can resolve the problem of mis-ties in cases of complex seismic reflection to a certain extent. Besides, not only are a series of channels separately recognized, but also small-scale meandering rivers are clearly mapped. Our algorithm is capable of adding more geologic information and realizing a better showcase of geomorphologic features.

In this paper, we propose a new method of seismic spectral sparse reflectivity inversion that, for the first time, introduces Expectation-Maximization-based sparse Bayesian learning (SBL-EM) to enhance the accuracy of stratal reflectivity estimation based on the frequency spectrum of seismic reflection data. Compared with the widely applied sequential algorithm-based sparse Bayesian learning (SBL-SA), SBL-EM is more robust to data noise and, generally, can not only find a sparse solution with higher precision, but also yield a better lateral continuity along the final profile. To investigate the potential of SBL-EM in a seismic spectral sparse reflectivity inversion, we evaluate the inversion results by comparing them with those of a SBL-SA-based approach in multiple aspects, including the sensitivity to different frequency bands, the robustness to data noise, the lateral continuity of the final profiles and so on. Furthermore, we apply the mean square error (MSE), residual variance (RV) of seismograms and residual energy (RE) between the frequency spectra of the true and inverted reflectivity model to highlight the advantages of the proposed method over the SBL-SA-based approach in terms of spectral sparse reflectivity inversion within a sparse Bayesian learning framework. Multiple examples, including both numerical and field experiments, are carried out to validate the proposed method.