Reconstruction of distorted structures in fault shadow zone based on Full Connected Network

Lateral changes in velocity about faults can give rise to fault shadow (FS) zones on time-migrated data volumes, which can result in structural interpretation artifacts in the fault trap reservoir. To address this issue we proposed a new reconstruction method of FS distortion structures based on a deep learning fully connected network (FCN). We use the three dimensional (3D) stratigraphic dip attributes to quantitatively delineate the extend of the FS zone. Then, we train an model to construct a nonlinear trend surface based on the structures of the stratigraphic reflectors that fall outside the shadow zone. Finally, we use this nonlinear trend surface to compensate the distorted structure within the FS zone. We calibrate our method using synthetic data and show that the method can accurately recover the structural data within the FS distortion zone. We then test the effectiveness of our workflow by applying it to recover real FS distortation sturctures in the Pearl River Mouth Basin of the South China Sea. The results confirm that our method significantly reduces the drilling depth error in the FS zone. Compared with the traditional polynomial fitting method, the multi-layer, multi-parameter and flexible nonlinear activation function of FCN is more capable of reconstructing nonlinear geological structures in the FS zone. We find the FCN-based geological reconstruction method to be both efficient and effective for exploring the potential structures in the FS zone and thereby in avoiding the risks of structural failure.