AI Aided GPR Data Multipath Summation Using x-t Stacking Weights

Migration velocity of Ground Penetrating Radar (GPR) data is a low wavenumber attribute crucial for migration. Obtaining a migration velocity model, which is considered closer to a Root Mean Square (RMS) model, from zero-offset (ZO) data requires analysis of the available diffractions whose density and (x, t) coverage is random. Thus, accuracy and efficiency of such a velocity model either for migration or its usage for interval velocity model estimation is not guaranteed. Here, with the aid of an Artificiaal Intelligence (AI) algorithm, which detects diffractions and usage of their kinematic information, we generate a diffraction velocity model used for the assignment of 2D weights for weighted multipath summation. The scope is to efficiently focus the scattered energy within a GPR section. We describe this methodology and demonstrate its application in enhancing the lateral continuity of reflections. We compare it with the multipath summation using lD weights with simulated data and present its application on marble assessment GPR data for imaging cracks in the subsurface structure.