Prestack Seismic Waveform Classification via Physical Knowledge-Guided Disentangled Representation

The interpretability and reliability of the prestack seismic waveform classification are often hindered by the entanglement of various geological factors in prestack seismic waveforms, along with their intrinsic uncertainties. To address the problem, we propose a physical knowledge-guided disentangled representation network (PK-GDRN) for a specific interpretation task of prestack seismic waveform classification. Unlike physics-driven deep learning methods that incorporate physical laws directly into network structures or loss functions, our approach uses a physical knowledge constraint network to guide deep feature learning based on physical attributes. This enables the model to capture more interpretable and separable features. First, the concept of group supervision and disentangled representation theory is applied to separate specific physical attributes within the prestack seismic waveform. Then, the physical knowledge about the seismic data is incorporated to impose additional constraints during the disentangling of deep features. Finally, a clustering technique is used to cluster disentangled deep features and generate the clustering result, which can assist geological experts in inferring sedimentary environments and the distribution of the reservoir. Testing on the synthetic data demonstrates that our method effectively separates and reconstructs geological elements within seismic data, accurately classifies different types of reflection patterns, and shows strong robustness against noise. Furthermore, the application of actual data shows that the classification results of prestack seismic waveforms using the proposed method have better interpretability.