ANN-based sub-surface monitoring technique exploiting electromagnetic features extracted by GPR signals

Abstract. In this work we consider the problem of determining the dielectric characteristics of sub-surface layers by means of GPR systems. In particular, a suitable electromagnetic feature (the R_Γ parameter), strictly related to the geophysical parameters of the scenario, is first extracted from the GPR e.m. signal and then fed to an artificial neural network (ANN) in order to derive the dielectric permittivity of the sub-surface layer.