Seismic Facies Classification Based on Multilevel Wavelet Transform and Multiresolution Transformer

Seismic facies classification is pivotal for analyzing geological environments and predicting reservoirs. The transformer architecture has been widely applied in seismic facies classification due to its powerful feature learning capabilities. However, most existing transformer architecture has limitations in learning fine-grained features of seismic data, due to the high local correlation and low global correlation characteristics of seismic data. Meanwhile, they generally perform feature extraction at a single scale and fail to fully utilize the inherent multi-scale property of seismic data, which may lead to a decrease in classification accuracy. To overcome these two problems, we propose a seismic facies classification method that integrates multi-level wavelet transform with a multi-resolution transformer architecture. First, we employ the Haar wavelet decomposition algorithm to decompose the seismic data into three distinct levels of features, which are then input into a multi-scale network for feature extraction. Next, we propose a multi-resolution transformer module for fine-grained feature extraction of first-level decomposed features. It can capture both global and local spatial attention features through two branches: the global attention branch and the local attention branch. The enhanced features are merged with intermediate outputs from the other two branches to achieve feature integration. The final step involves a decision-level fusion of the classification outcomes from all three branches. Numerical experiments on synthetic and field datasets confirm the effectiveness of the proposed architecture. The classification results show that the proposed method outperforms the comparison methods and performs particularly well in classes with fewer samples.