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

摘要

In this work we consider the problem of determining the dielectriccharacteristics of sub-surface layers by means of GPR systems. In particular,a suitable electromagnetic feature (the parameter), strictlyrelated to the geophysical parameters of the scenario, is first extractedfrom 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.