Wavelet Scattering Network-Based Machine Learning for Ground Penetrating Radar Imaging: Application in Pipeline Identification

Abstract

Automatic and efficient ground penetrating radar (GPR) data analysis remains a bottleneck, especially restricting applications in real-time monitoring systems. Deep learning approaches have good practice in automatic object identification, but their intensive data requirement has reduced their applicability. This paper developed a machine learning framework based on wavelet scattering networks to analyze GPR data for subsurface pipeline identification. Wavelet scattering network is functionally equivalent to convolutional neural networks, and its null-parameter property is intended for non-intensive datasets. A double-channel framework is designed with wavelet scattering networks followed by support vector machines to determine the existence of pipelines on vertical and horizontal traces separately. Classification accuracy rates arrive around 98% and 95% for datasets without and with noises, respectively, as well as 97% for considering surface roughness. Pipeline locations and diameters are convenient to determine from the reconstructed profiles of both simulated and practical GPR signals. However, the results of 5 cm pipelines are sensitive to noises. Nonetheless, the developed machine learning approach presents promising applicability in subsurface pipeline identification.

Editorial for the Special Issue “Advanced Techniques for Ground Penetrating Radar Imaging”

“…The main goal is to detect the features corresponding to buried pipelines in GPR datasets. Results presented in [10] yield a classification accuracy greater than 95% in the presented examples.…”

“…Ref. [10] introduces a machine learning framework based on wavelet scattering networks, which are functionally equivalent to CNN. The main goal is to detect the features corresponding to buried pipelines in GPR datasets.…”

“…The scope of the Special Issue contributions can be classified into three main groups: High-resolution GPR systems [1][2][3][4], noise mitigation in GPR measurements [5,6], and GPR data processing enhancement [7][8][9][10].…”

2D Wavelet Decomposition and F-K Migration for Identifying Fractured Rock Areas Using Ground Penetrating Radar

“…Scenario 1: identifying sparse rock cracks Since visibly obtaining the actual fissure distribution inside the surrounding rocks is difficult, the numerically generated radargram is analyzed to compare the reconstructed profile with the preset geometric model. The open-source software, 'gprMax' [51], can simulate electromagnetic wave propagation inside the subterranean sections and have been extensively applied in evaluating GPR signal processing approaches (e.g., [52,53]). We assume that the signal reflections are all generated by rock fissures, not strata interfaces, since the underground caverns are built inside the single layer of granite.…”

Wavelet Scattering and Neural Networks for Railhead Defect Identification

“…Since all operators have been predefined, the WSN contains no parameters, and thus, the dataset requirement decreases. In [ 30 ], only 40 radargrams were required for training and validation to achieve a learning accuracy over 95%. The learning frameworks based on WSNs also outperformed CNNs in multiple applications, achieving a learning accuracy up to 99.7% (e.g., [ 31 , 32 ]).…”