Seismic data high-precision imaging method and device

A seismic data imaging device comprising:

• a first acquisition module configured to acquire a prestack seismic gather of a work zone to be imaged;
• a migration module configured to perform multi-azimuth prestack migration processing on the prestack seismic gather by a fixed migration aperture for each imaging line in an imaging space of the work zone to be imaged, so as to obtain a set of multi-azimuth migration imaging profiles of each imaging line, wherein the fixed migration aperture is not smaller than a maximum dip-angle of a subsurface target structure to be imaged;
• a processing module configured to process a set of multi-azimuth migration imaging profiles of a target imaging line by using a target neural network model, so as to enable both correct imaging of a subsurface dip-angle structure and migration noise suppression, to obtain a migration imaging profile of the target imaging line, wherein the target neural network model is a lightweight neural network constructed from a Transformer neural network and a convolutional neural network (CNN), the Transformer neural network is located between an encoder block and a decoder block of the CNN, a training target of the target neural network model is that an error between a prediction result of an output migration image profile and an actual migration image profile is smaller than a preset threshold, and the target imaging line represents any imaging line in the imaging space;
• and
• a first determination module configured to determine an imaging result of the work zone to be imaged based on migration imaging profiles of all imaging lines.