Multi-receptive Field Distillation Network for seismic velocity model building

Velocity model building is crucial for seismic exploration, yet conventional methods struggle with complex geological scenarios due to assumptions of horizontal layering. These challenges are exacerbated in areas with complex structures and low signal-to-noise ratios, where precise velocity determination is difficult. To overcome these limitations, we propose the Multi -receptive Field Distillation Network, a novel deep -learning approach that leverages Multi -receptive Field modules to extract detailed seismic features, and a Shot Record Transformer Block to capture long-range dependencies. Our network employs a distillation architecture to process seismic data with and without noise, enhancing the model's ability to learn from noisy records. A Composite Loss function is introduced for optimizing model parameters, promoting a unified feature representation. Numerical experiments on synthetic models demonstrate our method's superior performance in noise inversion and velocity modeling accuracy. The results underscore the network's potential for improving seismic exploration accuracy.