Unsupervised Learning-Assisted Decomposition for Wigner–Ville Distribution and Its Application in Reservoir Characterization

Wigner-Ville Distribution (WVD) is a commonly used seismic time-frequency (TF) analysis tool. Nevertheless, it is prone to cross-term interference, distorting TF interpretation. Inverse problem (IP)-based approaches have been employed to suppress these cross-terms by decomposing seismic signals into a linear combination of predefined dictionary elements. While effective in reducing interference, these methods are computationally expensive, requiring iterative optimization processes that can be impractical for large-scale seismic data. To address this challenge, we propose an unsupervised learning-assisted decomposition for WVD network (ULDWVDNet) that leverages deep learning (DL) to enhance the efficiency of IP-based WVD. The proposed model comprises an inverse problem-based network that integrates DL for signal decomposition and reconstruction. The DL-based decomposition model decomposes the analyzed signal into a linear combination and improves its calculation effectiveness, while the reconstructed model maintains the accuracy of the decomposed results. Afterward, we apply the WVD to each decomposed signal to achieve a high-resolution TF result. The Marmousi II synthetic data is first used to train the proposed model, and the TF results demonstrate the effectiveness of our proposed model. Moreover, we apply the proposed model to three-dimensional (3D) real seismic data for hydrocarbon reservoir detection. The field data results reveal that the {ULDWVDNet} can produce more accurate and reliable interpretation results.