Parameters such as gas content (GAS), porosity (PHI) and total organic carbon (TOC) are key parameters that reveal the shale gas geological “sweet spot” of reservoirs. However, the lack of a three-dimensional high-precision prediction method is not conducive to large-scale exploration of shale gas. Although the parameter prediction accuracy based on well logging data is relatively high, it is only a single point longitudinal feature. On the basis of prestack inversion of reservoir information such as P-wave velocity and density, high-precision and large-scale “sweet spot” spatial distribution predictions can be realized. Based on the fast growing and widely used deep learning methods, a one-dimensional convolutional neural network (1D-CNN) “sweet spot” parameter prediction method is proposed in this paper. First, intersection analysis is carried out for various well logging information to determine the sensitive parameters of geological “sweet spot”. We propose a new standardized preprocessing method based on the characteristics of the well logging data. Then, a 1D-CNN framework is designed, which can meet the parameter prediction of both depth-domain well logging data and time-domain seismic data. Third, well logging data is used to train a high-precision and robust geological “sweet spot” prediction model. Finally, this method was applied to the WeiRong shale gas field in Sichuan Basin to achieve a high-precision prediction of geological “sweet spots” in the Wufeng–Longmaxi shale reservoir.

No abstract

To address the problem of fault?fracture reservoir identification, a new method based on super?resolution (SR) seismic signal reconstruction is established to identify faults, sliding fracture zones and induced fracture zones. First, based on a super?resolution generation countermeasure (SRGAN) deep learning method, an SR seismic signal reconstruction network framework is designed with a discriminant network (D), a generation network (G) and a visual geometry group network (V). Through the perceptual loss, objective control functions and iterative parameter updates, the nonlinear feature learning advantages of the deep network are introduced, the noise is eliminated, weak signals are recovered, and low resolution (LR) signals are restored, allowing the seismic signal to be reconstructed into an SR signal. Second, the SR seismic signal is used to extract the geometric attributes, such as the coherence based on the gradient structure tensor (GST) and the curvature based on the fractional derivative approximation (FDA). Third, principal component analysis (PCA) is used to reduce the feature dimension of the seismic attributes such as the GST coherence and FDA curvature and extract the principal components with the strongest correlations, thus eliminating redundant and residual noise interference, highlighting the spatial distribution and internal details of the fault?fracture reservoir, and allowing a fine description of the fault?fracture reservoir to be developed. Finally, this method achieves a good application effect for reconstructing SR seismic signals and identifying fault?fracture reservoirs in the Sichuan Basin of China.