In railway tunnel inspections using train-mounted ground penetrating radar (GPR), catenary support devices on the tunnel lining often introduce significant clutter into GPR profiles. This external clutter distorts GPR data and complicates the interpretation of internal defects. Due to its strong reflections, extensive coverage, and similarity to target features, catenary clutter lacks effective suppression methods that simultaneously preserve weak signals of interest. In this work, we propose a catenary clutter elimination generative adversarial network (2C-GAN), which conceptualizes clutter suppression and profile reconstruction as a transformation problem from the cluttered domain to the clutter-free domain. The 2C-GAN accepts unpaired clutter-free and clutter-laden GPR data, iteratively training a generator to remove clutter and reconstruct GPR profiles. Its main advantage lies in its unsupervised approach with unpaired data, enhancing its practical applicability in engineering contexts. To address the challenge of limited training data, 2C-GAN employs a lightweight design with residual cross-stage partial (CSP) modules, improving network performance and reducing generator parameters. Synthetic data testing shows that 2C-GAN significantly outperforms other unsupervised methods in catenary clutter suppression and related metrics. Furthermore, applying 2C-GAN to a real high-speed railway tunnel dataset with only 192 unpaired samples produced remarkable results, demonstrating the effectiveness of 2C-GAN in suppressing catenary clutter and its potential for application in similar above-surface diffraction (ASD) scenarios.

Distributed Acoustic Sensing (DAS) is an emerging vibration collection technology with advantages such as low cost, high-density sampling, and high sensitivity. It utilizes regional unlit fiber-optic telecommunication infrastructure (dark fiber) in the urban underground to record real-time environmental signals. How to identify vehicle signals, classify vehicle types, and estimate vehicle speeds from DAS signals has significant potential for the development of intelligent urban transportation. Addressing the challenges of high-noise environments and dense traffic, we develop an end-to-end two-stage deep learning process to identify and classify various vehicle signals in urban traffic rapidly. First, we propose the CarDenoiseNet network, based on Generative Adversarial Networks (GAN) and contrastive learning, to denoise and enhance the weak signal of DAS data. Then, the YOLOv8 segmentation model is employed to segment and classify the vehicle signal. Finally, the vehicle speeds are estimated using the segmented vehicle trajectory time and location information. We use the urban DAS field data recorded in the downtown area of Changchun to test the proposed workflow. The test result has good generalization and over 90% accuracy in identifying different vehicle types and speeds in high-density traffic environments. Moreover, transfer learning successfully applies the model to other datasets, proving its excellent generalization ability. Additionally, statistical analysis of traffic flow and speed trends provides technical references for alleviating urban traffic congestion, reducing traffic accidents, and enhancing the intelligence level of urban traffic management.

Deep learning (DL) has gained traction in ground-penetrating radar (GPR) tasks. However, obtaining sufficient training data presents a significant challenge. We introduce a structure-adaptive GPR-generative adversarial network (GAN) to generate GPR defect data. GPR-GAN employs double normalization for stabilizing parameters and convolution outputs, an adaptive discriminator augmentation (ADA) module for small dataset training stability, and a modified self-attention (MSA) module to generate GPR defects with complex features. We evaluated the performance of GPR-GAN using three datasets in conjunction with three state-of-the-art detection networks (faster region-based convolutional neural network (FasterRCNN), single-shot multibox detector (SSD), and YOLOv5). Our results reveal that GPR-GAN exhibits strong generalization skills, adeptly adapting to GPR data generation tasks that encompasses a variety of targets, frequencies, and equipment. GPR-GAN generated data increased the$F1$score for void recognition in simulation data by at least 5.27%, improved the average$F1$score for highway pavement defect detection by at least 7.68%, and enhanced the average$F1$score for railway subgrade defect detection by at least 9.22%. GPR-GAN offers a powerful data support tool for DL research in GPR.

Elastic full-waveform inversion (EFWI) is a high-resolution technique for inverting velocity structures, such as P-wave and S-wave velocities, enabling the indirect estimation of subsurface material properties like porosity and saturation through petrophysical relationships. However, conventional EFWI faces challenges such as low signal-to-noise ratio (SNR) in near-surface land seismic data and heterogeneous Poisson’s ratios in complex environments, which hinder convergence and introduce crosstalk noise during the inversion process. In this work, we propose an integrated approach that combines a neural network-based seismic inversion with a petrophysical inversion framework to enhance the estimation of soil saturation and porosity properties. We introduce an advanced strategy called elastic neural network full-waveform inversion (ENFWI), which employs convolutional neural networks (CNNs) and automatic differentiation (AD) to invert the$V_{p}$and$V_{s}$models. This method utilizes two independent CNN architectures to generate$V_{p}$and$V_{s}$gradients, effectively suppressing crosstalk noise and providing robustness against low SNR conditions. Subsequently, we develop a petrophysical iterative inversion framework using Hertz-Mindlin (HM) contact theory to update porosity and saturation properties based on the inverted velocity models and resistivity constraint term. The AD algorithm integrates multiple equations to account for the$V_{p}/V_{s}$ratio and resistivity as constraints. Two typical synthetic models show that the proposed framework inverts reliable saturation, porosity, and velocity models. Furthermore, field data illustrate the framework’s capability to accurately identify a water-bearing interlayer and the Wadi basement interface. This work offers a reliable method for imaging structural distributions and estimating properties in near-surface critical zone (CZ) applications.

The Moon-based ground penetrating radar (GPR) onboard the Chang’E-4 (CE-4) Yutu-2 rover has deployed on the far side of the Moon, which provides the Moon’s far side, providing an unprecedented opportunity to study the shallow surface geological process and the history of the volcanic eruption of the Moon. The high-frequency radar observed a buried lens structure ~27 m below the lunar surface, which was interpreted as paleo-regolith by previous studies. In this study, we conducted a quantitative analysis of the dielectric properties of the buried lens structure observed during the CE-4 mission. Our results reveal that the relative permittivity and loss tangent are of the structure is ~10.5 and ~0.037, respectively. Comparing our estimated dielectric properties with those of Apollo samples and radar-observed lava flows shows that the buried lens is neither regolith nor ejecta material but possibly basalt flow. Additionally, we speculate that the buried basalt flow may represent the latest volcanic eruption on the Moon, possibly from the Eratosthenian-aged volcano that occurred approximately 2.5-2.2 billion years ago. Finally, we update the interpretation of the regolith stratigraphic structure observed by the Yutu-2 high-frequency radar at the CE-4 landing site.

Monitoring underground fluid infiltration and estimating soil water content (SWC) is essential for hydrogeology and soil science research. Conventional hydrological survey methods, such as trenching, soil sampling, or time domain reflectometry (TDR), provide in-situ, static, and discrete measurements. However, these methods have limitations in capturing the spatiotemporal dynamics of fluid infiltration. Ground penetrating radar (GPR) offers a noninvasive and high spatiotemporal measurement approach for near-surface applications. Nevertheless, the complexity of GPR data and its weak response to small-scale fluid infiltration pose challenges in instantaneous attribute analysis and SWC estimation using the travel-time method. In this paper, we propose a time-lapse GPR data full waveform inversion (FWI) method to effectively monitor the spatial distribution of small-scale fluid transport and estimate SWC with improved accuracy. Firstly, we combine velocity spectral analysis and the structural similarity index method (SSIM) to construct a permittivity model that solves the dependence of FWI on the initial model. Subsequently, to simultaneously invert the permittivity and conductivity, we introduce gradient normalization to balance the convergence rate of the two parameters during the inversion process. The typical GPR time-lapse infiltration GPR field data example confirms that the proposed method can accurately characterize small-scale fluid infiltration distribution and estimate SWC parameters. The total estimated error in SWC is found to be less than 5%. The proposed time-lapse GPR data processing protocol provides a quantitative means for monitoring small-scale fluid infiltration.

As one of the most important geophysical methods for detecting the lunar underground structure of the Moon, the lunar penetrating radar (LPR) is applied to the Chang’e-4 (CE-4) mission to explore the Von Kármán crater on the far side of the Moon. With the Yutu-2 rover continues to move towards the Zhinyu crater at the west, radar will likely detect the fractures created by the impact that formed the Zhinyu Crater. Therefore, the establishment of a comprehensive lunar subsurface structure model with fracture, random media and fractal terrain is crucial for the LPR data processing and the understanding of the lunar geological impact process. In addition, the method that can image the radar data with fractures well has great significance to the interpretation of the LPR data. In this paper, we establish a comprehensive lunar subsurface structure model firstly, the considering factors including fractures, random media, fractal terrain, and the radar response are calculated through forward modeling. Secondly, according to the high resolution and the sensitive to inhomogeneities of LPR data, we design a set of processing flow including plane-wave destruction, velocity analysis based on the focusing analysis method and migration imaging based on the velocity continuation. Finally, the results including simulation data and Antarctic fracture data are used to verify the effectiveness of imaging method.

Due to unexpected environmental variations and poor consistencies in land data acquisition, complex near-surface seismograms are usually polluted unreasonably with a low signal-to-noise ratio (SNR). These complicated circumstances bring more challenges in identifying accurate first arrivals for the following wave-equation traveltime (WT) inversion. Recently, the autoencoder (AE) is a typical unsupervised learning network, whose basic principle is to compress the input seismic data for their intrinsic features in the latent space with an encoder and, thereafter, to decipher these features for seismic profiles as the output with a decoder. This process is fully automatic with high stability and is not very sensitive to data quality. In this article, we propose an elastic WT inversion algorithm based on the AE method (AEWT) to invert the$P$-velocity model. Compared with the standard WT, the AEWT method automatically extracts the intrinsic features of the refractions with AE as reference data for the misfit functionals. Feature images in the latent space show similar but intensified sensitivity to the traveltimes with respect to velocity perturbations. We present one synthetic and two field data tests for comparing the proposed AEWT and the standard WT tomograms to investigate the locations of a buried fault and the depth of a buried sinkhole. All these experiments demonstrate that the proposed elastic AEWT method can reduce errors caused by low SNR and obtain a more reliable and stable$P$-velocity tomogram.

Migration can reconstruct the geometric structure of a subsurface object from the ground penetrating radar (GPR) data. However, a GPR antenna is usually simplified as an ideal point/line source of normal migration algorithms, which ignore the influence of the antenna radiation pattern in subsurface soil. In this letter, the back-propagation algorithm is corrected with the analytical half-space far-field radiation pattern of an infinite line source. The superiority of this modified migration algorithm is verified through numerical, laboratory, and field experiments. The results show that the undesired diffractive artifacts at the target edges can be suppressed, while reserving the reflection amplitude in the migrated images with antenna pattern correction, compared with the conventional back-propagation and Kirchhoff algorithms.

The lunar regolith penetrating array radar (LRPR) carried by Chang’E-5 (CE-5) has explored the subsurface regolith structure of the moon and guided the drill sampling procedures. To evaluate LRPR performance in subsurface imaging and physical-parameter estimation, we apply multiscale full-waveform inversion (FWI) with total variation (TV) regularization to the synthetic CE-5 LRPR data. The time-domain multiscale inversion strategy gives a low-frequency update for the deep region and increases the frequency range for updating the shallow area. The TV regularization reduces the image noise and improves the inversion accuracy of local structures. To mimic the actual scenario, we use an LRPR source wavelet obtained from the LRPR instrument prototype for our FWI test. The LRPR source wavelets include the effect of the antenna radiation patterns and signal scattering from the metallic lander. We test the proposed FWI scheme on two heterogeneous models of the lunar regolith and demonstrate that the scheme effectively reduces the signal scattering from the metallic lander and provides a reliable way to image the lunar regolith structures. These images can be used to estimate the regolith physical parameters.

Three upcoming Martian missions will deploy a ground-penetrating radar (GPR) to reveal the fine-resolution subsurface structure and dielectric properties of materials beneath the surface. Numerical forward simulations of radar echo using a model of the near-surface structure at the landing site can provide a valuable reference for processing and interpretation of future radar data collected on Mars. In this study, based on the geological information of the Jezero crater, a detailed stratigraphic model of the near-surface structure is derived, which includes several key features, for example, the randomness of the medium, terrain, and cracks. To identify correctly the reflections of subsurface interfaces and fractures from the radar image, a$v(z$) f-k migration is carried out, the performance of which is evaluated using the GPR data obtained near Antarctic Zhongshan Station since the electrical properties of Antarctic glaciers and Martian materials are to some extent comparable. The results in this work show that compared with common migration algorithm, the$v(z$) f-k method not only improves the clarity of radar image but also provides the permittivity profiles to infer the composition of the substrate, leading to a better understanding of Martian near-surface geology.

The lunar penetrating radar (LPR) carried on the Chang E-3 Yutu Rover observations at 500 MHz successfully reveals the thickness and geological structure of the shallow lunar regolith. Previous work used the calculated permittivity and the migration image to estimate the layer interface and local target. In this letter, a least-squares Kirchhoff migration (LSM) algorithm is presented to reduce the migration artifacts (i.e., recording footprints) due to incomplete data. Both synthetic and CE-3 LPR data are used to test the effectiveness of the LSM method. The numerical results show that LSM can achieve a much superior image quality than Kirchhoff migration and frequency-wavenumber (F-K) migration results. Based on the LSM result of CE-3 LPR data, we can find evident strata reflection and continuous distinct layers in the shallow lunar subsurface below the CE-3 site. It provides a more reliable and robust way to interpret the lunar regolith structure.

Lunar penetrating radar (LPR) is an important way to evaluate the geological structure of the subsurface of the moon. The Chang'E-3 has utilized LPR, which is equipped on the lunar rover named Yutu, to obtain the shallow lunar regolith structure in Mare Imbrium. The previous result provides a unique opportunity to map the subsurface structure and vertical distribution of the lunar regolith with high resolution. In order to evaluate the LPR data, the study of lunar regolith media is of great significance for understanding the material composition of the lunar regolith structure. In this letter, we focus on the lunar regolith quantitative random model and parameter inversion with LPR synthetic data. First, based on the Apollo drilling core data, we build the lunar regolith quantitative random model with clipped Gaussian random field theory. It can be used to model the discrete-valued random field with a given correlation structure. Then, we combine radar wave impedance and stochastic inversion methods to carry out LPR data inversion and parameter estimation. The results mostly provide reliable information on the lunar regolith layer structure and local details with high resolution. This letter presents a further research strategy for lunar probe and deep-space detection with LPR.

In this letter, we apply a time and frequency analysis method based on the complete ensemble empirical mode decomposition (CEEMD) method in ground-penetrating radar (GPR) signal processing. It decomposes the GPR signal into a sum of oscillatory components, with guaranteed positive and smoothly varying instantaneous frequencies. The key idea of this method relies on averaging the modes obtained by empirical mode decomposition (EMD) applied to several realizations of Gaussian white noise added to the original signal. It can solve the mode-mixing problem in the EMD method and improve the resolution of ensemble EMD (EEMD) when the signal has a low signal-to-noise ratio. First, we analyze the difference between the basic theory of EMD, EEMD, and CEEMD. Then, we compare the time and frequency analysis with Hilbert–Huang transform to test the results of different methods. The synthetic and real GPR data demonstrate that CEEMD promises higher spectral–spatial resolution than the other two EMD methods in GPR signal denoising and target extraction. Its decomposition is complete, with a numerically negligible error.

In this paper, we combine the multiple-input-multiple-output (MIMO) array antenna technology with a multipolarization component in a ground penetrating radar (GPR) system to improve target detection accuracy. The MIMO technology introduced in previous literature is widely applied in radar and other wireless communication fields. Here, we apply the MIMO technology with a “plane-wave like” (PWL) source that uses array antennas with small spacing to emit a pulse source at the same time in GPR detection. First, we analyze the physical mechanism of the MIMO GPR system with a “PWL” source to improve the target detection resolution. Then, we carry out a numerical simulation with a finite-difference time-domain method in 1-D and 2-D array antennas to compare the imaging results of the MIMO and traditional GPR systems. Finally, the synthetic data MIMO GPR experiment with a step-frequency GPR system is implemented. Compared with the traditional GPR system, our results demonstrate that the MIMO GPR system with a multipolarization detection mode can overcome the influence of target radar cross sections and antenna radiation directions, and improve target detection accuracy effectively. Meanwhile, the synthetic MIMO GPR system also provides a good idea to improve the system performance and reduce system design requirements and the manufacture cost.

Ultrawideband (UWB) radar technology has emerged as one of the preferred choices for through-wall detection due to its high range resolution and good penetration. The resolution is a result of high bandwidth of UWB radar and helpful for better separation of multiple targets in complex environment. Detection of human targets through a wall is interesting in many applications. One significant characteristic of human is the periodic motion, such as breathing and limb movement. In this letter, we apply the UWB radar system in through-wall human detection and present the methods based on fast Fourier transform and S transform to detect and identify the human's life characteristic. In particular, we can extract the center frequencies of life signals and locate the position of human targets from experimental data with high accuracy. Compared with other research studies in through-wall detection, this letter is concentrated in the processing and identifying of the life signal under strong clutter. It has a high signal-to-noise ratio and simpler to implement in complex environment detection. We can use the method to search and locate the survivor trapped under the building debris during earthquake, explosion, or fire.

The ultra wideband (UWB) radar has greater advantage in estimate positions and shapes of the target in Through Wall Imaging (TWI). One significant characteristic of human beings is the periodic motion, such as respiration and movement of arms. In this paper, we apply the UWB pulse radar to detect the periodic motion in through-wall detection. We present methods based on the FFT and time-frequency analysis to detect periodic motions characters using the TWI data. In particular, we extract the frequency of the periodic motion, characterize time-frequency features, the size and position of the human being from the TWI images. It is straight forward to use the method in other applications such as earthquake and fire rescue.