Seismic characterization of fault and fractures in deep buried carbonate reservoirs using CNN-LSTM based deep neural networks

Geologic structures such as faults and fractures play a vital role in reservoir development studies. Fault and fracture identification requires high-quality seismic amplitude data with good resolution and a high signal-to-noise ratio (SNR). An anticline fault-controlled carbonate structure in North China contains significant reserves of hydrocarbons. However, the heterogeneity of deeply buried carbonates (burial depth > 4000 m) results in poor resolution and low SNR of seismic amplitude data, making it challenging to distinguish fault edge characteristics under the buried structures. In this study, we apply an inverse Q-filtering method based on the Gabor transform and structure-oriented filtering to compensate for the weak signal of the seismic events and enhance the SNR under the deep buried carbonate rocks. We investigated fault and adjacent fracture zones in structurally complex deeply buried carbonate reservoirs by extracting seismic fracture attributes (fault likelihood, eigenvalue coherence, and curvature) and feedforward neural network spatial fracture distribution from high-resolution seismic amplitude data. Moreover, a fracture density prediction model based on seismic attributes, CNN (convolutional neural network), and LSTM (long short-term memory) is developed to predict spatial fracture density. The predicted fracture density results are verified with seismic fracture attributes, geological modeling, and FMI (formation micro-imager) logs. This integrated workflow can assist in identifying high-production zones in structurally complex and deeply buried carbonates reservoirs.