A Frangi filter aided deep learning approach for palaeochannel recognition

Abstract

Summary In view of the problem of identifying paleochannels with high concealment and complex geological structures, this paper proposes an intelligent recognition method for paleochannels based on Frangi filtering and deep learning. The methodology makes use of Maximum Entropy Wigner-Ville Distribution (MEWVD) method to process the original instantaneous amplitude data, which enhance the distinct features of micro paleochannels in different sensitive frequency bands. The sample two-dimensional stratigraphic images generated from these data is labeled for the pre-training process of Attention R2U-Net neural network model. Subsequently, Frangi filter is employed to identify and enhance the linear structures of river channels in target stratigraphic images, improving the identification effect of the neural network. Finally, RGB data fusion and three-dimensional visualization carving are performed on the identification data. This method not only eliminates redundant information using the Frangi filter but also proves that the Attention R2U-Net network model structure with attention mechanism and residual convolution structure can effectively improve the segmentation effect for river channels at different scales. Experimental examples show that this method achieves pixel-level feature segmentation of 3D seismic data for paleochannels, accurately depicting their shape, width, thickness, flow direction and other features, thus providing support for subsequent well deployment and horizontal well fracturing selection.