• Geophysics and Geophysical Exploration
• /
• v.25 no.4
• /
• pp.189-200
• /
• 2022

Ground subsidence on urban roads is a social issue that can lead to human and property damages. Therefore, it is crucial to detect underground cavities in advance and repair them. Underground cavity detection is mainly performed using ground penetrating radar (GPR) surveys. This process is time-consuming, as a massive amount of GPR data needs to be interpreted, and the results vary depending on the skills and subjectivity of experts. To address these problems, researchers have studied automation and quantification techniques for GPR data interpretation, and recent studies have focused on deep learning-based interpretation techniques. In this study, we described a hyperbolic event detection process based on deep learning for GPR data interpretation. To demonstrate this process, we implemented a series of algorithms introduced in the preexisting research step by step. First, a deep learning-based YOLOv3 object detection model was applied to automatically detect hyperbolic signals. Subsequently, only hyperbolic signals were extracted using the column-connection clustering (C3) algorithm. Finally, the horizontal locations of the underground cavities were determined using regression analysis. The hyperbolic event detection using the YOLOv3 object detection technique achieved 84% precision and a recall score of 92% based on AP50. The predicted horizontal locations of the four underground cavities were approximately 0.12 ~ 0.36 m away from their actual locations. Thus, we confirmed that the existing deep learning-based interpretation technique is reliable with regard to detecting the hyperbolic patterns indicating underground cavities.

• Journal of the Korea Society of Computer and Information
• /
• v.26 no.2
• /
• pp.27-37
• /
• 2021

In this paper, we propose Automatic detection system of underground pipe which automatically detects underground pipe to help experts. Actual location of underground pipe does not match with blueprint due to various factors such as ground changes over time, construction discrepancies, etc. So, various accidents occur during excavation or just by ageing. Locating underground utilities is done through GPR exploration to prevent these accidents but there are shortage of experts, because GPR data is enormous and takes long time to analyze. In this paper, To analyze 3D GPR data automatically, we use 3D image segmentation, one of deep learning technique, and propose proper data generation algorithm. We also propose data augmentation technique and pre-processing module that are adequate to GPR data. In experiment results, we found the possibility for pipe analysis using image segmentation through our system recorded the performance of F1 score 40.4%.

• Journal of The Geomorphological Association of Korea
• /
• v.17 no.2
• /
• pp.87-98
• /
• 2010

There have been growing concerns for the sea level rise due to global warming in recent years. Sea level rise is a serious problem to densely populated coastal areas, because it may affect the coastal landforms to be damaged. Especially coastal sand deposits like coastal dunes are more sensitive than the other coastal landforms. In this paper, Ground Penetrating Radar (GPR) and Optically Stimulated Luminescence (OSL) dating method were used to identify the Holocene geomorphic changes of coastal dune field in Shinduri located at the western coast. The main results in this study that are the dunefield in the study area may have begun to form at around 6.8 ka and it has grown seaward thereafter. Then, dunefield appears to have extensively developed since 3.7 ka. This result, together with previous works on the sea level and climatic changes in the western coast of Korea suggest that the dunefield has been affected by the sea level regression since the Holocene high stand in the Holocene at around 6 ka and climatic change from warm and humid to cold and dry conditions occurred at 4.5 ka.

• Journal of the Korean Geotechnical Society
• /
• v.34 no.11
• /
• pp.93-105
• /
• 2018

Precise investigation and interpretation of the ground subsidence risk factors needed to predict and evaluate the settlement problems of the surrounding ground due to the ground excavation. There are various geophysical exploration methods to investigate the ground subsidence risk factors. However, there are factors that influence the characteristics of the underground medium in these geophysical methods, and the actual soil contains complex factors affecting geophysical exploration. Therefore, it is necessary to analyze the effects on the geophysical methods based on the understanding of the geotechnical properties of soil. In this study, a test bed was constructed to consider various complicated factors in the complex ground and the ground behavior was analyzed by numerical analysis. In addition, we analyzed the limitations on investigating the ground subsidence risk factors through ground penetration radar (GPR) survey. As a result, ground subsidence of Open-cut Type Excavation is caused by various factors. Especially, in the case of soft ground condition, it was found that it was greatly influenced by the flow change of groundwater level. At the center frequency of GPR of 250 MHz, the attenuation of the electromagnetic wave is severely attenuated in the clay with high electrical conductivity, making it difficult to penetrate deeply into the ground (4 m below the surface). As the electromagnetic waves pass through the groundwater level below the groundwater, the attenuation of the electromagnetic waves becomes severe.

• Journal of the Korean Association of Geographic Information Studies
• /
• v.26 no.4
• /
• pp.56-66
• /
• 2023

Safety accidents are increasing, such as changes in groundwater levels due to construction work or natural influences, or ground cave-ins caused by soil runoff from old water supply and sewage pipes. In addition, underground facility management agencies must make efforts to improve the accuracy of underground information through continuous investigation and exploration in accordance with the Special Act on Enhanced Underground Safety Management. Accordingly, in this study, we defined the configuration of equipment and data processing method to collect 3D precise exploration underground facility information and developed 3D underground facility information collection technology to ensure accuracy of underground facilities. As a result of verifying the developed technology, the horizontal accuracy improved by an average of 6cm compared to the existing method, making it possible to acquire 3D underground facility information within the error range of the public survey work regulations.

• Geophysics and Geophysical Exploration
• /
• v.19 no.3
• /
• pp.153-163
• /
• 2016

In order to prevent ground collapses by groundwater level drawdown, we need to understand the groundwater flow and also make an analytical approach to the cause of the collapses. In this study, we used the result of the soil lab tests to compare and review the suitability of the various interaction equations about the relation between volumetric water content and the dielectric constant. In addition, using GPR (Ground-Penetrating Radar), we reviewed the possibility of calculating an estimate of dielectric constant. Lastly, we applied seepage analysis and stress-strain analysis to the sandy ground given by ground excavation. In comparison with the previous result of the soil lab tests, we similarly predicted the suction of unsaturated soil from results of stress-strain analysis considered the seepage force for the unsaturated soil.

• Geophysics and Geophysical Exploration
• /
• v.22 no.3
• /
• pp.132-148
• /
• 2019

Recently, safety and environmental concerns have become major social issues. Especially, a special underground-safety law has been made and enacted to prevent ground subsidence around construction sites. For environmental problems, several researches have started or will start on characterization of contaminated sites, in-situ environmental remediation in subsurface, and monitoring of remediation results. As a part of the researches, geophysical surveys, which have been mainly applied to explore mineral resources, geological features or ground, are used to characterize not only contaminated areas but also fluid flow paths in subsurface environments. As a basic study for the application of geophysical surveys to detect contamination in subsurface, this paper analyzes previous researches to understand changes in geophysical properties of contaminated zones by various contaminants such as leachate, heavy metals, and non-adequate phase liquid (NAPL). Furthermore, this paper briefly introduces how geophysical surveys like direct-current electrical resistivity, induced polarization and ground penetration radar surveys can be applied to detect each contamination, before analyzing case studies of the applications in contaminated areas by NAPL, leachate, heavy metal or nitrogen oxides.

• Economic and Environmental Geology
• /
• v.55 no.1
• /
• pp.111-125
• /
• 2022

Since landslide can cause huge damages to many facilities, close characterization of slopes is needed for appropriate reinforcements for the unstable ones in order to prevent the damages. Geophysical surveys, which can characterize a large area at a relatively low cost without disturbing slopes, have been widely employed for the assessment of slope stability in other countries. However, only conventional direct investigation methods are mainly used in Korea. In this paper, we analyzed various cases, which evaluated slope stabilities by characterizing slopes using geophysical exploration. First, we introduced changes in geophysical properties due to unstable media of slope like fracture location, fracture connectivity and distribution of groundwater level, and subsequently discussed the applicability of geophysical methods to the detection of the changes; the methods include electrical resistivity survey, seismic survey, self-potential survey, induced polarization survey and ground penetrating radar. Based on this description, we analyzed how geophysical surveys were performed on various slopes.

• Geophysics and Geophysical Exploration
• /
• v.23 no.3
• /
• pp.117-130
• /
• 2020

Noises can distort acquired geophysical data, leading to their misinterpretation. Potential noises sources include anthropogenic activity, natural phenomena, and instrument noises. Conventional denoising methods such as wavelet transform and filtering techniques, are based on subjective human investigation, which is computationally inefficient and time-consuming. Recently, many researchers attempted to implement neural networks to efficiently remove noise from geophysical data. This study aims to review and analyze different types of neural networks, such as artificial neural networks, convolutional neural networks, autoencoders, residual networks, and wavelet neural networks, which are implemented to remove different types of noises including seismic, transient electromagnetic, ground-penetrating radar, and magnetotelluric surveys. The review analyzes and summarizes the key challenges in the removal of noise from geophysical data using neural network, while proposes and explains solutions to the challenges. The analysis support that the advancement in neural networks can be powerful denoising tools for geophysical data.

• Journal of Korean Tunnelling and Underground Space Association
• /
• v.24 no.4
• /
• pp.341-353
• /
• 2022

Pipelines are buried in urban area, and the position (depth and orientation) of buried pipeline should be clearly identified before ground excavation. Although various geophysical methods can be used to detect the buried pipeline, it is not easy to identify the exact information of pipeline due to heterogeneous ground condition. Among various non-destructive geo-exploration methods, ground penetration radar (GPR) can explore the ground subsurface rapidly with relatively low cost compared to other exploration methods. However, the exploration data obtained from GPR requires considerable experiences because interpretation is not intuitive. Recently, researches on automated detection technology for GPR data using deep learning have been conducted. However, the lack of GPR data which is essential for training makes it difficult to build up the reliable detection model. To overcome this problem, we conducted a preliminary study to improve the performance of the detection model using finite difference time domain (FDTD)-based numerical analysis. Firstly, numerical analysis was performed with homogeneous soil media having single permittivity. In case of heterogeneous ground, numerical analysis was performed considering the ground heterogeneity using fractal technique. Secondly, deep learning was carried out using convolutional neural network. Detection Model-A is trained with data set obtained from homogeneous ground. And, detection Model-B is trained with data set obtained from homogeneous ground and heterogeneous ground. As a result, it is found that the detection Model-B which is trained including heterogeneous ground shows better performance than detection Model-A. It indicates the ground heterogeneity should be considered to increase the performance of automated detection model for GPR exploration.