Realistic simulation of GPR for landmine and IED detection including antenna models, soil dispersion and heterogeneity

Abstract Ground‐penetrating radar (GPR) is an effective tool for detecting landmines and improvised explosive devices (IEDs), and its performance is strongly influenced by subsurface properties as well as the characteristics of the target. To complement or replace labour‐intensive experiments on test sites, cost‐efficient electromagnetic wave propagation simulations using the Finite‐Difference Time‐Domain (FDTD) method are being increasingly used. However, to obtain realistic synthetic data, accurate modelling of signal alteration caused by dispersion, scattering of soil material, target contrast, shape, and inner setup, as well as the coupling effects of the antenna to the ground is required. In this study, we present a detailed 3D model of a shielded GPR antenna applied to various scenarios containing metallic and non‐metallic targets buried in different soils. The frequency‐dependent intrinsic material properties of soil samples were measured with the coaxial transmission‐line technique, while a discrete random media was used to implement the heterogeneity of a gravel based on its grain‐size distribution. Our simulations show very good agreement with experimental validation data collected under controlled conditions. We accurately reproduce the amplitude and frequency content, phase of target signals, subsurface's background noise, antenna crosstalk and its interference with target signals, and the effect of antenna elevation. The approach allows for systematic investigation of the effects of soil, target, and sensor properties on detection performance, providing insight into novel and complex GPR scenarios and the potential for a wide range of simulation possibilities for demining with GPR. These investigations have the potential to improve the safety and effectiveness of landmine and IED detection in the future, such as building a database for training deminers or developing automatic signal pattern recognition algorithms. This article is protected by copyright. All rights reserved