3D seismic intelligent prediction of fault-controlled fractured-vuggy reservoirs in carbonate reservoirs based on a deep learning method

Accurately predicting the external morphology and internal structure of fractured-vuggy reservoirs is of significant importance for the exploration and development of carbonate oil and gas reservoirs. Conventional seismic prediction methods suffer from serious non-uniqueness and low efficiency, while recent advances in deep learning exhibit strong feature learning capabilities and high generalization. Therefore, this paper proposes an intelligent prediction technique for fault-controlled fracture-vuggy reservoirs based on deep learning methods. The approach involves constructing 3D seismic geological models that conform to the geological characteristics of the study area, simulating seismic wavefield propagation, and combining the interpretation results of fractured-vuggy reservoirs. Training sample datasets are separately established for strike-slip faults, karst caves, and fault-controlled fractured-vuggy reservoir outlines, which are then input into the U-Net model in batches for training. This leads to the creation of a deep learning network model for fault-controlled fractured-vuggy reservoirs. The trained network model is applied to the intelligent identification of fault, karst cave, and fault-controlled fracture-vuggy reservoir outlines using actual seismic data from the Shunbei area. A comparison with traditional methods is conducted, and the experimental results demonstrate that the proposed deep learning approach shows excellent performance in the identification and prediction of fault-controlled fractured-vuggy reservoirs.