Saturated rocks typically contain pores of various geometric shapes. The complex pore structure not only significantly affects the elastic and seismic response characteristics of rocks but also influences the accuracy of petrophysical parameter predictions. Existing rock physics inversion methods struggle to quantitatively describe pore type distributions and their geological implications, and there remains a lack of comprehensive inversion methods for simultaneously determining pore types and petrophysical parameters in porous reservoirs. Porosity, pore structure, and fluid properties collectively reflect the reservoir's physical attributes, pore space complexity, and pore fluid types. Establishing an accurate relationship between seismic parameters and reservoir pore characteristics can enhance the reliability of reservoir predictions. In this paper, taking the oil and gas-bearing sandstone reservoir as an example, the influence of reservoir pore space geometry on rock elastic parameters and seismic AVO reflection coefficients is theoretically considered from the perspective of seismic petrophysics, and the relationship between seismic reflection coefficient and effective pore structure is established. By combining the Biot-Gassmann pore theory and Russell's linear approximation equation, a target functional containing the fluid term and pore structure was derived. Based on the stochastic inversion algorithm, the inversion of the fluid term and pore structure is stably achieved.

Predicting the petrophysical properties of rocks from seismic data is challenging because the relationship between petrophysical properties and their seismic response is nonlinear and multisolution. A targeted framework is presented to enhance the effectiveness of petrophysical properties prediction based on deep learning (DL) in this study. We utilize statistical rock physics and geological methods to tackle the challenge of the limited availability of labeled data. Moreover, in response to the issue of multiple solutions, we propose a multitask inversion neural network architecture for predicting petrophysical properties from multiinformation guided by a physical model. To evaluate the validity of the framework, we built a numerical model and carried out a quantitative analysis using threefold cross-validation and comparison of single trace predictive results. The framework is finally applied to a real work area of a deep tight dolomite reservoir in Southwest China, demonstrating promising prospects for practical application.

The existence of coal seams suppresses other useful information, especially the below-thin layers, and is unfavorable for delineating the target reservoirs beneath them. The matching pursuit (MP) based methods are commonly used for removing strong reflections caused by coal seams. They first decompose a seismic trace into several wavelets based on a user-defined wavelet dictionary and then separate the most similar wavelet with the coal seam. However, how to define a complete wavelet dictionary and how to maintain horizontal continuity are two unsolved issues. We propose a multi-scale attention deep learning (MSADL) model for separating and removing seismic strong reflections. First, we suggest a workflow to generate a synthetic data set for model training based on the characteristics of field data and well logs. Next, we build an MSADL model by integrating the discrete wavelet transform (DWT) and convolutional block attention module (CBAM) into the widely used Unet. After model training, we apply the well-trained MSADL model to 3D field data in the Sichuan Basin, China for the separation and removal of strong reflections and characterization of the beneath target thin layers.

Pre-stack seismic inversion is an effective means of using seismic data to achieve prediction of physical parameters of underground media. However, pure PP wave inversion suffers from high inversion multiplicity solutions and limited prediction accuracy. Therefore, we propose a multi-wave stochastic inversion physical parameters prediction method driven by linearized rock physics. Firstly, this method establishes a robust relationship between elastic and physical parameters based on a statistical rock physics model. Secondly, the linearized AVO approximations for PP wave and SH-SH wave expressed by porosity, clay volume and water saturation are derived. Numerical simulations of the reflection characteristics of the two model interfaces show that both new formulations have high accuracy. On this basis, we construct a joint inversion equation of PP wave and SH-SH wave for porosity, clay volume and water saturation. A stochastic inversion method based on the ensemble smoother with multiple data assimilation (ES-MDA) for the multi-wave joint physical parameters is proposed. Stanford VI-E model tests indicate that the physical parameters obtained from the joint PP wave and SH-SH wave inversion have higher identification accuracy and smaller relative errors compared to the pure PP wave inversion. Moreover, field data tests demonstrate the good practicality of the method for seismic prediction of underground media physical parameters.

Deep learning is a data-driven technique that demands network models trained using big datasets. In seismic structure interpretation, it is very difficult, time-consuming, and relatively economic costs to prepare training datasets by directly annotating real seismic data. Seismic convolution method is an efficient way to synthesize seismic data, which can easily and quickly generate large amount of training datasets. However, there are large differences in feature space between synthetic seismic data and real seismic data. That results in the poor performance of network models trained using synthetic training datasets on real seismic data. In this paper, we propose to use Fourier domain adaptation (FDA) to achieve domain transfer. First, amplitude spectrum of synthetic seismic data is replaced with those of real seismic data to make feature space mapping. Then synthetic seismic data is used for transfer training of network models to improve its performance on real seismic data. The experimental results demonstrate that the FDA performs the domain transfer of synthetic seismic data to real seismic data, which improves the generalization of network models trained based on synthetic seismic data. Meanwhile, the FDA is a promising method for deep learning model transfer training in seismic structure interpretation.

Predicting gas-bearing zone of deep tight dolomite reservoirs from prestack seismic data is challenging and subject to great uncertainty. Machine learning especially for deep learning (DL) provides a new potential. One main limitation of the DL-based supervised methods is that they require large amounts of training data. However, well-log labels from the real deep reservoirs are very insufficient. To address this issue, we investigate a method based on convolutional neural networks (CNNs) considering transfer learning to predict gas distribution of deep tight dolomite reservoirs. The CNNs model we used contains three convolutional layers for automatic feature extraction from prestack data and one fully connected (FC) layer for gas-bearing probability prediction. A numerical model is designed based on petrophysical parameters extracted from the real target work area associated with deep tight dolomite reservoirs. The model is used to generate synthetic samples to pretrain the CNNs model. We then fix the network parameters in the first two convolutional layers and decay the learning rates of the third convolutional layer and the FC layer. Using the real samples to fine-tune the pretrained CNNs model with epoch increasing. The optimal predictor is finally trained well for gas-bearing prediction. The method is applied to a real work area of deep tight dolomite reservoir located in western China covering approximately 800 km2. Examples illustrate the roles of transfer learning on improving gas-bearing distribution of deep tight dolomite reservoirs and increasing the generalization of the method.

The deep exploration has become the focus of attention in the field of earth sciences. Coherence is a routine measure to identify structural and stratigraphic anomalies, such as faults, channels, and fractures in subsurface. However, deep seismic data typically suffer from a low signal-to-noise ratio and a weak reflection amplitude, thus it may not provide a better insight for seismic attribute analysis. The phase information has the ability to detect subtle changes in subsurface but it is sensitive to noise, thereby masking some stratigraphic features in the full-bandwidth data. To address these two issues, we propose a multispectral phase-based geosteering coherence method by combining coherence and spectral decomposition for deep stratigraphic feature characterization. The proposed method can effectively select and utilize the phase components of favorable spectral bands, which can detect different scale geologic discontinuities and reduce or avoid the effect of random noise in deep seismic data. Furthermore, corendering the coherence images of three different frequency components using red-green-blue blending can detect more geologic details in subsurface. The examples including 3-D physical modeling data and real seismic data set of carbonate reservoir from western deep formation are employed to demonstrate the effectiveness of the proposed method. The coherence attributes obtained from the proposed method can detect the weak or hidden geologic details clearer than the geosteering coherence calculated from the broadband seismic data, and it may serve as a future tool for detecting the distribution of geologic abnormalities in deep exploration.

Time-frequency (TF) analysis is a useful tool for seismic data processing and interpretation. We introduce sparse Bayesian learning (SBL) to TF analysis and propose a new SBL-based high-resolution TF method. The method decomposes the seismic trace into a series of Ricker wavelets using SBL-based sparse representations and subsequently implements Wigner-Ville distribution (WVD) on the decomposed wavelets to produce TF spectra. By iteratively solving a Bayesian maximum posterior and a type-II maximum likelihood, SBL-based decomposition can sequentially obtain an optimal number of Ricker wavelets with different peak frequencies or phases from a preset wavelet dictionary, and can simultaneously invert for the associated sparse TF pseudoreflectivity with the prediction uncertainty. The WVD of SBL-based decomposed wavelets can assemble TF distribution of the reconstructed signals to approximately characterize WVD of the original data. Therefore, the linear stack of WVD of all decomposed independent wavelets is immune from both the notorious cross-term interferences of the traditional WVD and random noise. Synthetic data example involving thin beds and laboratorial physical modeling data example involving several known multicave combinations are used to demonstrate the effectiveness of the proposed SBL-based TF analysis method and illustrate its advantages over WVD and the orthogonal matching pursuit-based TF analysis method. The 3-D real seismic data example is adopted to test its application potential for interpreting deep channels and the karst slope fracture zone. The results show that the proposed SBL-based TF method is a potentially effective, stable and high-resolution seismic TF analysis tool even in the presence of thin beds.