Shallow Subsurface Wavefield Data Interpolation Method Based on Transfer Learning

The deployment density of surface sensors can significantly impact the accuracy of subsurface shallow seismic field energy inversion. With finite budget constraints, it is often not feasible to deploy a large number of sensors, resulting in limited seismic signal acquisition that hinders accurate inversion of the shallow subsurface explosions. To address the challenge of insufficient sensor signals needed for inversion, we conducted a study on a subsurface shallow wavefield data interpolation method based on transfer learning. This method is designed to increase the overall signal acquisition by interpolating signals at target locations from limited measurement points. Our research employs neural networks to interpolate real seismic data, supplementing the sampled signals. Given the lack of extensive samples from actual data collection, we devised a training approach that combines numerically simulated signals with real collected signals. Initially, we performed conventional interpolation training using a deep interpolation network with complete synthetic gather images obtained from numerical simulations. Subsequently, the feature extraction part was frozen, and the interpolation network was transferred to real datasets, where it was trained using incomplete gather images. Finally, these incomplete gather images were re-input into the trained network to obtain interpolated results at the target locations. Our study demonstrates the superiority of our method by comparing it with two other interpolation networks and validating the effectiveness of transfer learning through four sets of ablation experiments in the actual test. This method can also be applied to other shallow geological structures to generate a large number of seismic signals for energy inversion.