Kirchhoff Integral Migration for VTI Media with Travel-Time Calculated Based on PINN

Kirchhoff integral migration imaging is widely used in industrial production due to its advantages of not being limited by observation systems, good target imaging effects, and high computational efficiency. Vertical transversely isotropic (VTI) media, as a typical anisotropic media, has always been a primary focus of anisotropic migration imaging research. We focus on the problems of low accuracy and efficiency in travel-time calculations associated with conventional Kirchhoff integral migration for VTI media. A travel-time calculation method based on physical-informed neural network (PINN) for VTI media is introduced into the process of Kirchhoff integral migration imaging. Model experiments and field data processing have shown that the travel-time calculation based on PINN can significantly improve both the accuracy and efficiency when compared to traditional finite difference algorithms, thereby enabling high-precision Kirchhoff integral migration imaging for VTI media.