The simulation, or forward modeling, of ground penetrating radar (GPR) is becoming a more frequently used approach to facilitate the interpretation of complex real GPR data, and as an essential component of full-waveform inversion (FWI). However, general full-wave 3-D electromagnetic (EM) solvers, such as the ones based on the finite-difference time-domain (FDTD) method, are still computationally demanding for simulating realistic GPR problems. We have developed a novel near-real-time, forward modeling approach for GPR that is based on a machine learning (ML) architecture. The ML framework uses an innovative training method that combines a predictive principal component analysis technique, a detailed model of the GPR transducer, and a large data set of modeled GPR responses from our FDTD simulation software. The ML-based forward solver is parameterized for a specific GPR application, but the framework can be applied to many different classes of GPR problems. To demonstrate the novelty and computational efficiency of our ML-based GPR forward solver, we used it to carry out FWI for a common infrastructure assessment application--determining the location and diameter of reinforcement bars in concrete. We tested our FWI with synthetic and real data and found a good level of accuracy in determining the rebar location, size, and surrounding material properties from both data sets. The combination of the near-real-time computation, which is orders of magnitude less than what is achievable by traditional full-wave 3-D EM solvers, and the accuracy of our ML-based forward model is a significant step toward commercially viable applications of FWI of GPR.

Ground penetrating radar (GPR) is a well-established tool for detecting and locating reinforcing bars (rebars) in concrete structures. However, using GPR to quantify the diameter of rebars is a challenging problem that current processing approaches fail to tackle. To that extent, we have developed a novel machine learning framework that can estimate the diameter of the investigated rebar within the resolution range of the employed antenna. The suggested approach combines neural networks and a random forest regression and has been trained entirely using synthetic data. Although the training process relied only on numerical training sets, nonetheless, the suggested scheme is successfully evaluated with real data indicating the generalization capabilities of the resulting regression. The only required input of the proposed technique is a single A-scan, avoiding laborious measurement configurations and multisensor approaches. In addition, the results are provided in real time and making this method practical and commercially appealing.

Hyperbola fitting is a mainstream interpretation technique used in ground-penetrating radar (GPR) due to its simplicity and relatively low computational requirements. Conventional hyperbola fitting is based on the assumption that the investigated medium is a homogeneous half-space, and that the target is an ideal reflector with zero radius. However, the zero-radius assumption can be easily removed by formulating the problem in a more generalized way that considers targets with arbitrary size. Such approaches were recently investigated in the literature, suggesting that hyperbola fitting can be used not only for estimating the velocity of the medium, but also for estimating the radius of subsurface cylinders, a very challenging problem with no conclusive solution to this day. In this letter, through a series of synthetic and laboratory experiments, we demonstrate that for practical GPR survey, hyperbola fitting is not suitable for simultaneously estimating both the velocity of the medium and the size of the target, due to its inherent nonuniqueness, making the results unreliable and sensitive to noise.

The preservation of natural assets is nowadays an essential commitment. In this regard, root systems are endangered by fungal diseases which can undermine the health and stability of trees. Within this framework, ground penetrating radar (GPR) is emerging as a reliable non-destructive method for root investigation. A coherent GPR-based root-detection framework is presented in this paper. The proposed methodology is a multi-stage data analysis system that is applied to semi-circular measurements collected around the investigated tree. In the first step, the raw data are processed by applying several standard and advanced signal processing techniques in order to reduce noise-related information. In the second stage, the presence of any discontinuity element within the survey area is investigated by analysing the signal reflectivity. Then, a tracking algorithm aimed at identifying patterns compatible with tree roots is implemented. Finally, the mass density of roots is estimated by means of continuous functions in order to achieve a more realistic representation of the root paths and to identify their length in a continuous and more realistic domain. The method was validated in a case study in London (UK), where the root system of a real tree was surveyed using GPR and a soil test pit was excavated for validation purposes. Results support the feasibility of the data processing framework implemented in this study.