• Journal of the Korean Geotechnical Society
• /
• v.39 no.6
• /
• pp.5-12
• /
• 2023

Proactive assessment of landslide susceptibility is necessary for minimizing casualties. This study proposes a methodology for classifying the landslide safety factor using a classification algorithm based on machine learning techniques. The high-risk area model is adopted to perform the classification and eight geotechnical parameters are adopted as inputs. Four classification algorithms-namely decision tree, k-nearest neighbor, logistic regression, and random forest-are employed for comparing classification accuracy for the safety factors ranging between 1.2 and 2.0. Notably, a high accuracy is demonstrated in the safety factor range of 1.2~1.7, but a relatively low accuracy is obtained in the range of 1.8~2.0. To overcome this issue, the synthetic minority over-sampling technique (SMOTE) is adopted to generate additional data. The application of SMOTE improves the average accuracy by ~250% in the safety factor range of 1.8~2.0. The results demonstrate that SMOTE algorithm improves the accuracy of classification algorithms when applied to geotechnical data.

• Journal of the Korean Geotechnical Society
• /
• v.32 no.6
• /
• pp.27-40
• /
• 2016

Conventional warning criteria for landslides due to rainfall in broad regions have limitations, because they did not have proper reflection of topography, forest physiognomy, and unsaturated soil properties, et al. This study suggested a new stability model for unsaturated slope analyses during rainfall, considering rainfall pattern, geomorphological characteristics (slope angle, soil depth), engineering properties of unsaturated soils, and tree surcharge and root reinforcement. Stability analysis not considering root reinforcement and tree surcharge tends to over-predict a factor of safety in unsaturated slopes. Developed slope stability model was used to build database on the factor of safety in unsaturated slopes during rainfall, and it was integrated with GIS to do quantitative risk analysis in landslide risk areas specified in Ulju. Landslide risk areas were located at downstream of the point with sudden drop in safety factor, as well as at regions with low safety factor during rainfall.

• Geomechanics and Engineering
• /
• v.22 no.4
• /
• pp.291-303
• /
• 2020

The deformation of the rock surrounding a tunnel manifests due to the stress redistribution within the surrounding rock. By observing the deformation of the surrounding rock, we can not only determine the stability of the surrounding rock and supporting structure but also predict the future state of the surrounding rock. In this paper, we used grey system theory to analyse the factors that affect the deformation of the rock surrounding a tunnel. The results show that the 5 main influencing factors are longitudinal wave velocity, tunnel burial depth, groundwater development, surrounding rock support type and construction management level. Furthermore, we used seismic prospecting data, preliminary survey data and excavated section monitoring data to establish a neural network learning model to predict the total amount of deformation of the surrounding rock during tunnel collapse. Subsequently, the probability of a change in deformation in each predicted section was obtained by using a Bayesian method for detecting change points. Finally, through an analysis of the distribution of the change probability and a comparison with the actual situation, we deduced the survey mark at which collapse would most likely occur. Surface collapse suddenly occurred when the tunnel was excavated to this predicted distance. This work further proved that the Bayesian method can accurately detect change points for risk evaluation, enhancing the accuracy of tunnel collapse forecasting. This research provides a reference and a guide for future research on the probability analysis of tunnel collapse.

• Proceedings of the Korean Geotechical Society Conference
• /
• 2001.03a
• /
• pp.493-500
• /
• 2001

The construction of bored tunnels in soft ground inevitably causes ground movements. In the urban environment these may be of particular significance, because of their influence on buildings, other tunnels and services. The prediction of ground movements and the assessment of the potential effects on the structures is therefore an essential aspect of planning, design and construction of a tunnelling project in the urban environment. In this study, to minimize the effect of tunnelling-Induced ground movements on the adjacent structures, a system for tile settlement risk management was developed. The GIS based risk assessment system for adjacent structures developed in this study consists of several modules such as building information module, settlement evaluation module, potential risk assessment module for adjacent structures, and analysis module for monitoring data. This system focuses on controlling and managing construction processes that may lead to settlement In the surrounding buildings and can contribute to producing the optimum technical and economic design.

• Journal of the Korean GEO-environmental Society
• /
• v.24 no.4
• /
• pp.23-29
• /
• 2023

Ground subsidence shows a mechanism in which the upper ground collapses due to the formation of a cavity due to the movement of soil particles in the ground due to the formation of a waterway because of damage to the water supply/sewer pipes. As a result, cavity is created in the ground and the upper ground is collapsing. Therefore, ground subsidence frequently occurs mainly in downtown areas where a large amount of underground facilities are buried. Accordingly, research to predict the risk of ground subsidence is continuously being conducted. This study tried to present a ground subsidence risk prediction model for two districts of ○○ city. After constructing a data set and performing preprocessing, using the property data of underground facilities in the target area (year of service, pipe diameter), density of underground facilities, and ground subsidence history data. By applying the dataset to the machine learning model, it is evaluated the reliability of the selected model and the importance of the influencing factors used in predicting the ground subsidence risk derived from the model is presented.

• Proceedings of the Korean Geotechical Society Conference
• /
• 2002.03a
• /
• pp.679-686
• /
• 2002

A substantial portion of the cost of a tunnelling project in urban environments is, therefore, devoted to prevent ground movement. Therefore, prediction of ground movements and assessment of risk of damage to adjacent buildings has become an essential part of the planning, design, and construction of a tunnelling project in the urban environments. An internet-based tunnelling-induced ground movements and building damage assessment system (IT-TURIMS) was developed and implemented to Daegu Metro Subway Line tunnel construction project in Korea. This paper describes the concept and implementation of IT-TURIMS. Practical significance of tunnelling risk assessment is also discussed.

• Journal of the Korean Geotechnical Society
• /
• v.21 no.10
• /
• pp.99-112
• /
• 2005

The ground excavation in the urban area induces in general ground movement and subsequent damage on the adjacent building structures. So the essentials in the designing stage are the prediction of ground movement induced by the ground excavation and the damage risk assessment of buildings adjacent to the excavation. A propsed prediction method of the ground movement induced by the strutted excavation has been studied with due consideration of the existing ground movement prediction methods. A building damage risk assessment method based on the angular distortion and the horizontal strain derived from the green-field ground movement is also proposed. These methods have been applied successfully in the on-going deep excavation project in Singapore.

• Journal of the Korean Geotechnical Society
• /
• v.38 no.12
• /
• pp.79-89
• /
• 2022

Every summer in our country, an accident occurs, in which the retaining wall on a steep slope collapses due to torrential rain. According to the data on the results of steep slope risk assessment in 2019, over 780 retaining walls are below grade C; therefore, preparing for countermeasures is urgent. However, due to the limited budget for the repair and reinforcement of these retaining walls, it is necessary to discuss the investment prioritization. In this study, a prioritization method was proposed at the network and project levels along with the review of the revised criteria of disaster risk assessment in the steep slope retaining wall, and an application research in the network level was conducted for six retaining walls. Moreover, it is proposed that the priority index was determined by using the actual cost for repair and reinforcement in determination of the project level prioritization.

• Journal of the Korean Geotechnical Society
• /
• v.31 no.8
• /
• pp.51-62
• /
• 2015

It is not possible to provide resonable evidence for embankment (or dam) overtopping in geotechnical engineering, and conventional analysis by hydrologic design has not provided the evidence for the overflow. However, hydrologic design analysis using Copula function demonstrates the possibility that dam overflow occurs when estimating rainfall probability with rainfall data for 40 years based on fluctuating water level of a dam. Hydrologic dam risk analysis depends on complex hydrologic analyses in that probabilistic relationship needs to be established to quantify various uncertainties associated with modeling process and inputs. The systematic approaches to uncertainty analysis for hydrologic risk analysis have not been addressed yet. In this paper, the initial level of a dam for stability of a dam is generally determined by normal pool level or limiting the level of the flood, but overflow of probability and instability of a dam depend on the sensitivity analysis of the initial level of a dam. In order to estimate the initial level, Copula function and HEC-5 rainfall-runoff model are used to estimate posterior distributions of the model parameters. For geotechnical engineering, slope stability analysis was performed to investigate the difference between rapid drawdown and overtopping of a dam. As a result, the slope instability in overtopping of a dam was more dangerous than that of rapid drawdown condition.

• Journal of the Korean Geotechnical Society
• /
• v.29 no.11
• /
• pp.99-106
• /
• 2013

In this study, the correlation of evaluation items and safety rating for 104 of large-scale slopes along the general national road was analyzed. And, we proposed the regression model to predict the safety rating using the multiple regressions analysis. As the result, it is shown that the evaluation items of slope angle, rainfall and groundwater have a low correlation with safety rating. Also, the regression model suggested by multiple regression analysis shows high predictive value, and it would be possible to apply if the evaluation items of excavation condition and groundwater (rainfall) are not clear.