LAUSR

Seismic velocity analysis is the basis for seismic imaging and understanding complex subsurface geological structures. Although the performance of automatic velocity analysis methods based on CMP data or velocity spectra is encouraging, particularly deep learning methods. However, most methods ignore the complementarity between CMP data and velocity spectrum, and only one of them is selected for velocity modeling. We propose a multimodal neural network (MMN) that combines the advantages of CMP data details representation and simplification of velocity spectrum. MMN includes multi-layer convolution structures and auto-encoder structures, which are used to extract time-space amplitude information from CMP gathers and energy groups features from velocity spectra, respectively. This paper compared MMN with the CMP single-modal network (CSN) and the velocity spectra single-modal network (VSSN). Based on synthetic data, we investigated their differences in terms of continuity, accuracy, noise resistance, and generalization. The MMN prediction results makes a trade-off between the overall continuity and local details. Visualization analysis of the intermediate feature maps explains the MMN velocity prediction mechanism, that is, the multi-angle representation and complementary fusion of velocity information. Finally, the performance of the proposed method is demonstrated using the braided river deposited field data example.