A Lightweight Cooperative Attention Network for Seismic Facies Classification

The deep learning method has been proven to be an effective way to recover high-precision classification of seismic facies. However, the existing methods often ignore the temporal and spatial correlation of seismic data, leading to insufficient extraction of relevant features in seismic facies classification. To address these problems, we propose a lightweight cooperative attention network for high-precision classification of seismic facies. The proposed lightweight architecture includes two key points. On the one hand, the proposed architecture employs only five convolutional layers to reduce feature redundancy and improve computational efficiency for the classification of seismic facies. On the other hand, a cooperative attention module (CAM), which comprises of two parts: self-channel and self-spatial operations, is proposed to improve the extraction ability of long-distance features and expand the receptive fields. The major benefit of the proposed attention module is that it can improve the classification accuracy of the lightweight network. Through numerical experiments with a synthetic and a field dataset, we demonstrate the effectiveness of the proposed lightweight architecture and highlight two key benefits. First, the proposed CAM can improve the prediction accuracy of the proposed lightweight architecture for the classification of seismic facies. Second, the proposed lightweight architecture embedded with the proposed attention module outperforms the standard UNet network while reducing the number of parameters by 99.5%. It has shown the proposed architecture to be a cost-effective and practical classification tool for seismic facies.