Time-frequency analysis can provide useful information in seismic data processing and interpretation. An accurate time-frequency representation is important in highlighting subtle geologic structures and in detecting anomalies associated with hydrocarbon reservoirs. The popular methods, like short-time Fourier transform and wavelet analysis, have limitations in dealing with fast varying instantaneous frequencies, which is often the characteristic of seismic data. The synchrosqueezing transform (SST) is a promising tool to provide a detailed time-frequency representation. We apply the SST to seismic data and show its potential to seismic signal processing applications.

Seismic records are often contaminated with various kinds of noise, which makes it very difficult to distinguish the expected geological features. In this paper, we introduce a novel adaptive variable time fractional-order anisotropic diffusion equation for seismic data noise removal and strongly oriented structure enhancement. Since the time fractional-order differential equation interpolates a parabolic equation and a hyperbolic equation, the solution benefits both of these approaches. The presented differential equation can be written as a Volterra integral equation, and its well-posedness can be guaranteed for all time. We employ a structure tensor to analyze the flow-like texture characteristic which is typical in seismic data. Then, the diffusion process is guided reasonably by a diffusion tensor based on the structure tensor analysis which allows real anisotropic behavior comparing to the classical scalar diffusion approach. In reference to the numerical implementation, we utilize the predictor-corrector algorithm to solve the Volterra integral equation which provides high-order numerical precision jointly with good stability property. Finally, numerical experiments involved with synthetic and prestacked real seismic data are presented. The obtained results demonstrate that the noise is effectively removed, and the coherent seismic events that express some important geological structures are not only preserved but significantly enhanced.

Deep-learning methods, such as convolutional neural networks (CNNs), have been successfully applied to seismic impedance inversion in recent years. Compared with traditional geophysical inversion, deep-learning inversion can give inversion results with higher resolution. In this letter, we further improve the performance of deep-learning inversion and propose a seismic impedance inversion method based on conditional generative adversarial network (cGAN). In the proposed method, a generator learns to predict seismic impedance from seismic data, and a discriminator learns to distinguish between fake and real impedance. We mix the cGAN objective with mean square error (MSE) loss to bring in more information for model training. Besides, a CNN-based seismic forward model is trained to introduce the constraint of unlabeled data in the training of cGAN. Tests on Marmousi2 model and overthrust model show that the proposed method can obtain more accurate impedance and have better robustness against random noise than CNN method.

Seismic facies classification plays an important role in oil and gas reservoir interpretation. In the past few years, convolution neural network (CNN)-based models have been widely used in supervised seismic facies classification. However, to improve some inherent limitations of CNNs, it is significant to explore alternative architectures, such as the Transformer with the self-attention mechanism. In this study, based on the Segformer, a cutting-edge semantic segmentation Transformer, we propose a U-shaped model of joint the Segformer and the Hypercolumn representation for seismic facies classification, named U-Segformer-Hyper. As the emerging lightweight variant of the Transformer for seismic facies segmentation, the proposed U-Segformer-Hyper consists of a specific encoder-decoder-hypercolumns scheme, which can extract various features in different layers and fuse the output features of different layers with different scales. In the application of the public F3 seismic data, compared with the CNN Benchmark model, the U-Segformer-Hyper model has fewer parameters, fewer floating-point operations per second, and higher accuracy of classification in both the section-based and patch-based training modes. Moreover, the proposed U-Segformer-Hyper is open-source, which benefits to further explore alternative deep models in seismic interpretation.

Synchrosqueezing transform (SST) is an effective time-frequency analysis (TFA) approach for the processing of nonstationary signals. The SST shows a satisfactory ability of the TF localization of the nonlinear signal with a slowly time-varying instantaneous frequency (IF). However, for the signal of which ridge curves in the TF domain are fast varying, or even almost parallel to the frequency axis, the SST will provide a blurred TF representation (TFR). To solve this issue, the transient-extracting transform (TET) was recently put forward. The TET can effectively characterize and extract transient features in the much concentrated TFR for the strongly frequency-modulated (FM) signal, especially the impulse-like signal. However, contrary to the SST, it is not suitable for weak FM modes. In this study, we propose a TFA method called the time-synchroextracting general chirplet transform (TEGCT). The TEGCT can achieve a highly concentrated TFR for strong FM signals as well as weak FM ones. Quantized indicators, the concentration measurement and the peak signal-to-noise ratio, are used to analyze the performances of the proposed method compared with those of other methods. The comparisons show that the TEGCT can provide a result with better TF localization. Then, the proposed method was applied to the spectrum analysis of the seismic data for oil reservoir characteristics. The horizontal slices of the offshore 3-D seismic data show that the TEGCT delineates more distinct and continuous subsurface channels in a fluvial-delta deposition system. All the results illustrate that our proposed method is a good potential tool for seismic processing and interpretation in the geoscience.

One important application of time-frequency analysis (TFA) is seismic spectral decomposition for reservoir characterization. However, traditional seismic TFA techniques are usually limited by diffused TF distribution, which can result in unreliable seismic interpretations. Synchrosqueezing transform (SST) is an effective TFA method that improves the concentration of the TF representation (TFR) of nonstationary signals. However, for the signal with a rapidly varying instantaneous frequency, the SST method suffers from a blurred TFR. In this letter, we propose a novel TFA method called time-synchroextracting transform (TSET) that provides highly concentrated TFR for transient signals where the TF curve is nearly parallel to the frequency axis. We applied the proposed TSET to synthetic signals and field seismic data to verify its validity of time localization and effective delineation of subsurface geological information.