Application of Ground-Penetrating Radar with the Logging Data Constraint in the Detection of Fractured Rock Mass in Dazu Rock Carvings, Chongqing, China

Ground-penetrating radar (GPR) faces complex challenges in identifying underground rock formations and lithological structures. The diversity, intricate shapes, and electromagnetic properties of subsurface rock formations make their accurate detection difficult. Additionally, the heterogeneity of subsurface media, signal scattering, and non-linear propagation effects contribute to the complexity of signal interpretation. To address these challenges, this study fully considers the unique advantages of convolutional neural networks (CNNs) in accurately identifying underground rock formations and lithological structures, particularly their powerful feature extraction capabilities. Deep learning models possess the ability to automatically extract complex signal features from radar data, while also demonstrating excellent generalization performance, enabling them to handle data from various geological conditions. Moreover, deep learning can efficiently process large-scale data, thereby improving the accuracy and efficiency of identification. In our research, we utilized deep neural networks to process GPR signals, using radar images as inputs and generating structure-related information associated with rock formations and lithological structures as outputs. Through training and learning, we successfully established an effective mapping relationship between radar images and lithological label signals. The results from synthetic data indicate a rock block identification success rate exceeding 88%, with a satisfactory continuity identification of lithological structures. Transferring the network to measured data, the trained model exhibits excellent performance in predicting data collected from the field, further enhancing the geological interpretation and analysis. Therefore, through the results obtained from synthetic and measured data, we can demonstrate the effectiveness and feasibility of this research method.

Section: Methodsmentioning

confidence: 99%

Rock Layer Classification and Identification in Ground-Penetrating Radar via Machine Learning

Xu,

Yan,

Feng

et al. 2024

“…Due to financial and geomorphological restrictions, traditional identification relies on limited boreholes [7]. As a non-destructive investigation method, ground-penetrating radar (GPR) is regarded as a powerful complement to traditional drilling-based methods [8], especially for shallow earth and rock stratigraphic interfaces [9][10][11][12]. The GPR technique has been successfully used in inspecting caverns under roadway pavements, locating pipes underground, and reinforcing bars in piles [13][14][15][16].…”

Section: Introductionmentioning

confidence: 99%

Identification of Complex Slope Subsurface Strata Using Ground-Penetrating Radar

Wang,

Zhang,

et al. 2024

Identification of slope subsurface strata for natural soil slopes is essential to assess the stability of potential landslides. The highly variable strata in a slope are hard to characterize by traditional boreholes at limited locations. Ground-penetrating radar (GPR) is a non-destructive method that is capable of capturing continuous subsurface information. However, the accuracy of subsurface identification using GPRs is still an open issue. This work systematically investigates the capability of the GPR technique to identify different strata via both laboratory experiments and on-site examination. Six large-scale models were constructed with various stratigraphic interfaces (i.e., sand–rock, clay–rock, clay–sand, interbedded clay, water table, and V–shaped sand–rock). The continuous interfaces of the strata in these models were obtained using a GPR, and the depths at different points of the interfaces were interpreted. The interpreted depths along the interface were compared with the measured values to quantify the interpretation accuracy. Results show that the depths of interfaces should be interpreted with the relative permittivity, back-calculated using on-site borehole information instead of empirical values. The relative errors of the depth of horizontal interfaces of different strata range within ±5%. The relative and absolute errors of the V–shaped sand–rock interface depths are in the ranges of [−9.9%, 10.5%] and [−107, 119] mm, respectively. Finally, the GPR technique was used in the field to identify the strata of a slope from Tanglang Mountain in China. The continuous profile of the subsurface strata was successfully identified with a relative error within ±5%.

Study on the Identification Method of Planar Geological Structures in Coal Mines Using Ground-Penetrating Radar

Liu,

Tang,

Yang

et al. 2024

The underground detection environment in coal mines is complex, with numerous interference sources. Traditional ground-penetrating radar (GPR) methods suffer from limited detection range, high noise levels, and weak deep signals, making it extremely difficult to accurately identify geological structures without stable feature feedback. During research, it was found that the detection energy of the same target significantly changes with the antenna direction. Based on this phenomenon, this paper proposes a geological radar advanced detection method using spatial scanning. This method overcomes constraints imposed by the underground coal mine environment on detection equipment, enhancing both detection range and accuracy compared to traditional approaches. Experiments using this method revealed pea-shaped response characteristics of planar geological structures in radar images, and the mechanisms behind their formation were analyzed. Additionally, this paper studied the changes in response characteristics under changes in target inclination, providing a basis for understanding the spatial distribution of geological structures. Finally, application experiments in underground coal mine environments explored the practical potential of this method. Results indicate that, compared to drilling data, this method achieves identification accuracies of 91.88%, 90.42%, and 78.72% for the depth and spatial extent of geological structures, providing effective technical support for coal mining operations.