Background Removal, Velocity Estimation, and Reverse-Time Migration: A Complete GPR Processing Pipeline Based on Machine Learning

• Published in: IEEE transactions on geoscience and remote sensing Vol. 61; pp. 1 - 11
• Main Authors: Patsia, Ourania, Giannopoulos, Antonios, Giannakis, Iraklis
• Format: Journal Article
• Language: English
• Published: New York IEEE 2023; The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
• Subjects: Antennas; Artificial neural networks; Background removal; Clutter; concrete; Cross coupling; Deep learning; Estimation; Finite difference methods; finite-difference time-domain (FDTD); Ground penetrating radar; ground-penetrating radar (GPR); Homogeneity; hyperbola fitting; Hyperbolas; Inhomogeneous media; Locating; Machine learning; machine learning (ML); migration; Neural networks; neural networks (NNs); Permittivity; Principal component analysis; Principal components analysis; processing; Radar; Removal; reverse-time migration (RTM); Target masking; Time domain analysis; Training; Velocity
• ISSN: 0196-2892; 1558-0644
• DOI: 10.1109/TGRS.2023.3300276

The performance of ground-penetrating radar (GPR) is greatly influenced by the cross coupling between the transmitter and the receiver, and the response from the background. Their combined effect often masks the weaker target signals, especially in cases where shallow buried targets are present. Moreover, errors in velocity estimation result to over/under-migrated images, which further compromises the reliability of GPR, especially in case of nonhomogeneous media. Therefore, background clutter suppression and velocity estimation are both pivotal for effectively locating targets. For this purpose, a novel deep learning scheme for background clutter prediction was developed, where a two joint artificial neural networks (ANNs) architecture combined with principal component analysis (PCA) is implemented. In the suggested scheme, the first network predicts the background response, which is subsequently subtracted, while the second network estimates the background permittivity and conductivity. Subsequently, the permittivity profile along the measurement line is used as input in reverse-time migration (RTM) to focus the signal without the need of hyperbola fitting and homogeneity assumptions. The training data were generated synthetically using the finite-difference time-domain (FDTD) method. A model of a real GPR antenna is used in the simulations, making the scheme applicable to real data. The efficiency of the proposed method is validated using both numerical and real data, with successful predictions in all cases, demonstrating its ability to perform well even when tested with previously unseen real complex scenarios. Via a series of examples, the proposed scheme was proven superior to commonly used background removal techniques and conventional migration.