A convolutional neural network for prestack fracture detection
This work addresses fracture detection for hydrocarbon reservoir characterization, offering a data-driven deep learning approach to overcome limitations in existing methods, though it appears incremental as it applies CNNs to a specific domain problem.
The paper tackled the problem of detecting fracture density, dip, and strike azimuth from prestack seismic data, which existing methods based on vertical aligned fracture hypotheses could not achieve, and validated a convolutional neural network model on a practical survey with effective results.
Fractures are widely developed in hydrocarbon reservoirs and constitute the accumulation spaces and transport channels of oil and gas. Fracture detection is a fundamental task for reservoir characterization. From prestack seismic gathers, anisotropic analysis and inversion were commonly applied to characterize the dominant orientations and relative intensities of fractures. However, the existing methods were mostly based on the vertical aligned facture hypothesis, it is impossible for them to recognize fracture dip. Furthermore, it is difficult or impractical for existing methods to attain the real fracture densities. Based on data-driven deep learning, this paper designed a convolutional neural network to perform prestack fracture detection. Capitalizing on the connections between seismic responses and fracture parameters, a suitable azimuth dataset was firstly generated through fracture effective medium modeling and anisotropic plane wave analyzing. Then a multi-input and multi-output convolutional neural network was constructed to simultaneously detect fracture density, dip and strike azimuth. The application on a practical survey validated the effectiveness of the proposed CNN model.