Fault-fracture reservoir identification method based on a superresolution generative adversarial network and reconstructed superresolution seismic signals

To address the problem of fault-fracture reservoir identifica-tion, a new method based on superresolution (SR) seismic signal reconstruction is established to identify faults, sliding fracture zones, and induced fracture zones. First, based on an SR gen-erative adversarial network countermeasure deep learning method, an SR seismic signal reconstruction network frame-work 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 ad-vantages of the deep network are introduced, the noise is elim-inated, weak signals are recovered, and low-resolution 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 is used to reduce the feature dimension of the seismic attributes, such as the GST coherence and FDA curvature, and ex-tract 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 res-ervoir, and allowing a fine description of the fault-fracture reser-voir to be developed. Finally, this method achieves a good application effect for reconstructing SR seismic signals and iden-tifying fault-fracture reservoirs in the Sichuan Basin of China.