One of the most important goals of seismic stratigraphy studies is to interpret the elements of the seismic facies with respect to the geologic environment. Prestack seismic data carry rich information that can help us get higher resolution and more accurate facies maps. Therefore, it is promising to use prestack seismic data for the seismic facies recognition task. However, because each identified object changes from the poststack trace vectors to a prestack trace matrix, effective feature extraction becomes more challenging. We have developed a novel data-driven offset-temporal feature extraction approach using the deep convolutional autoencoder (DCAE). As an unsupervised deep learning method, DCAE learns nonlinear, discriminant, and invariant features from unlabeled data. Then, seismic facies analysis can be accomplished through the use of conventional classification or clustering techniques (e.g., K-means or self-organizing maps). Using a physical model and field prestack seismic surveys, we comprehensively determine the effectiveness of our scheme. Our results indicate that DCAE provides a much higher resolution than the conventional methods and offers the potential to significantly highlight stratigraphic and depositional information.

The 3-D seismic data reconstruction can be understood as an underdetermined inverse problem, and thus, some additional constraints need to be provided to achieve reasonable results. A prevalent scheme in 3-D seismic data reconstruction is to compute the best low-rank approximation of a formulated Hankel matrix by rank-reduction methods with a rank constraint. However, the predefined Hankel structure is easily damaged by the low-rank approximation, which leads to harming its recovery performance. In this article, we present a structured tensor completion (STC) framework to simultaneously exploit both the Hankel structure and the low-tubal-rank constraint to further enhance the performance. Unfortunately, under the assumption of elementwise sampling used by existing methods, STC is intractable to be solved since Hankel constraints cannot be expressed as linear tensor equations. Instead, tubal sampling is proposed to describe the missing trace behavior more accurately and further build a bridge between tensor and matrix completion (MC) to overcome the solving issue in two aspects: through the bridge from tensor to MC, STC can be solved efficiently using MC from random samplings of each frontal slice in the Fourier domain. Through the bridge from matrix to tensor completion, various tensor models within the framework can be developed from noise-specific MC to meet the need for data reconstruction in changeable noise environments. Moreover, alternating-minimization and alternating-direction methods of multipliers are developed to solve the proposed STC. The superior performance of STC is demonstrated in both synthetic and field seismic data.

A structural geological model describes the structure of subsurface and plays an important role in the exploration of mineral and petroleum resources. Despite the widespread use of three-dimensional geological models, the theoretical research of informatics in the field of structural geology is still very limited. We have noticed a lack of methods for integrating explicit semantics of field observation data and geophysical data into geological models. The existing model representation methods focus on accurately representing the geometric morphological information of underground structures, ignoring the high-level semantics implied in the model. The formal representation of the semantic information is necessary to promote the development of intelligent methods in geomodeling and geophysical inversion. In this paper, we propose a new framework to formally represent the semantics of structural geological models with a clear distinction of geometric and geological semantics. For the geometric semantics, based on the extension of the 9-intersection model, we mathematically define the spatial topological relations between geometric objects that make up the geological model. For the geological semantics, we define the geological contact and compositional relations between geological bodies and geological surfaces and reveal the temporal implications of these geological relationships. We design a multilayer heterogeneous network as a computer characterization of the semantics of the geological model. A better representation of semantic information aids in the creation and validation of geological models, as well as management, queries, and analyses of geological knowledge.

Elastic full-waveform inversion (FWI) has received significant attention in the industry for many years. Numerous studies have shown that parameter optimization methods based on physics-informed neural networks are more promising in FWI compared to traditional methods. Compared with surface seismic techniques, vertical seismic profiling (VSP) offers advantages such as lower acquisition costs, higher signal-to-noise ratios, and higher resolution. To address the problem of FWI for VSP, this study proposed a physics-informed recurrent neural network method with prior knowledge constraint for elastic FWI. Our main idea is threefold. First, we mined and characterized the prior knowledge for VSP FWI, which primarily includes geological knowledge, the 1D velocity profile around the wellbore, and the empirical relationships between compressional and shear wave velocities. Second, we implemented a PIRNN with prior knowledge constraint, using the RNN framework to optimize trainable parameters. Finally, using the PIRNN framework with prior knowledge constraint, we achieved elastic full-waveform inversion for VSP. Numerical examples demonstrate that the inversion results for the salt and Marmousi models indicate that incorporating prior knowledge increases the accuracy of full-waveform inversion. Compared to data-driven machine learning methods, this architecture eliminates the impact of sample quality on parameter optimization.

Vertical seismic profiling (VSP) is widely applied in the field of seismic exploration to deliver high-quality subsurface images and enable quantitative characterization around the wellbore region. The separation of VSP upgoing and downgoing wavefields is a practical step in the wavefield processing, which sets the foundation for the final imaging quality. With recent advances in deep learning (DL), a number of new attempts in seismic signal processing have proven effective. Inspired by that, we propose an unsupervised VSP wavefield separation framework via dual convolutional autoencoders (dualCAEs). Our method is based on two characteristics of up- and downgoing wavefields: one is directional continuity, and the other is the zero-mean feature. Two regularizers are proposed to constrain these two features. Thanks to this, our method does not require any training data other than the input data itself. Ablation and comparison studies on synthetic data validate the effectiveness of our method. Generalization tests on SEAM open data and field VSP records in the Dong area show the superiority of robustness and fidelity over traditional $F$ – $K$ and median filtering methods.

The geological model plays an important role in geophysics and engineering geology. The data source of geological modeling comes from interpretation data, borehole data, and outcrop data. Due to economic and technical limitations, it is impossible to obtain highly accurate and high-density data sources. The sparsity and inaccuracy of data sources lead to the uncertainty in geological models. Unlike the problem of probability, there is not enough samples for a geological model. Spatial diffusion model and merging model are introduced, which are more satisfied with the cognition of uncertainty than the existing methods. And then, using conditional information entropy, a quantification method of geological uncertainty, is proposed. Compared with the approaches of information entropy, this method took full account of the constraints of geological laws. Based on the uncertainty models and conditional information entropy, a framework of uncertainty assessment in geological models is established. It is not necessary in our framework to create multiple geological models, which is a time-consuming and laborious task. The application of Hashan survey located at north of China shows that the method and framework of this study are reasonable and effective.