• The Journal of Engineering Geology
• /
• v.34 no.1
• /
• pp.107-115
• /
• 2024

This study assesses forest fire susceptibility in Gangwon-do, South Korea, which hosts the largest forested area in the nation and constitutes ~21% of the country's forested land. With 81% of its terrain forested, Gangwon-do is particularly susceptible to wildfires, as evidenced by the fact that seven out of the ten most extensive wildfires in Korea have occurred in this region, with significant ecological and economic implications. Here, we analyze 480 historical wildfire occurrences in Gangwon-do between 2003 and 2019 using 17 predictor variables of wildfire occurrence. We utilized three machine learning algorithms—random forest, logistic regression, and support vector machine—to construct wildfire susceptibility prediction models and identify the best-performing model for Gangwon-do. Forest and soil map data were integrated as important indicators of wildfire susceptibility and enhanced the precision of the three models in identifying areas at high risk of wildfires. Of the three models examined, the random forest model showed the best predictive performance, with an area-under-the-curve value of 0.936. The findings of this study, especially the maps generated by the models, are expected to offer important guidance to local governments in formulating effective management and conservation strategies. These strategies aim to ensure the sustainable preservation of forest resources and to enhance the well-being of communities situated in areas adjacent to forests. Furthermore, the outcomes of this study are anticipated to contribute to the safeguarding of forest resources and biodiversity and to the development of comprehensive plans for forest resource protection, biodiversity conservation, and environmental management.

• Korean Journal of Occupational Health Nursing
• /
• v.27 no.4
• /
• pp.235-246
• /
• 2018

Purpose: This study aimed to comprehend the real context of metabolic syndrome-related factors of Korean male blue-collar workers from small-sized companies based on the health belief model. Methods: A total of 37 workers from three companies were interviewed, and three series of focus group interviews were conducted. Data were analyzed using deductive content analysis. Results: Data were classified into four categories: knowledge, perceived susceptibility and severity, perceived barriers, and beliefs. Knowledge referred to low knowledge level; perceived susceptibility and severity referred to unawareness of susceptibility and severity; perceived barriers referred to shift work, overtime work, and a social context including having no choice but to drink; and beliefs referred to believing that health promotion behaviors do not relate to preventing metabolic syndrome, believing that one cannot prevent metabolic syndrome oneself, and believing that professional help is required. Conclusion: To prevent and reduce the risk of metabolic syndrome among Korean male blue-collar workers, interventions should focus on strategies to increase metabolic syndrome-related knowledge and perceptions, social support, and self-efficacy for practicing health behaviors. In addition, it is necessary to develop policies for establishing a healthy drinking culture in companies.

• The Journal of Engineering Geology
• /
• v.33 no.4
• /
• pp.673-687
• /
• 2023

Exploratory data analysis is the process of observing and understanding data collected from various sources to identify their distributions and correlations through their structures and characterization. This process can be used to identify correlations among conditioning factors and select the most effective factors for analysis. This can help the assessment of landslide susceptibility, because landslides are usually triggered by multiple factors, and the impacts of these factors vary by region. This study compared two stages of exploratory data analysis to examine the impact of the data exploration procedure on the landslide prediction model's performance with respect to factor selection. Deep-learning-based landslide susceptibility analysis used either a combinations of selected factors or all 23 factors. During the data exploration phase, we used a Pearson correlation coefficient heat map and a histogram of random forest feature importance. We then assessed the accuracy of our deep-learning-based analysis of landslide susceptibility using a confusion matrix. Finally, a landslide susceptibility map was generated using the landslide susceptibility index derived from the proposed analysis. The analysis revealed that using all 23 factors resulted in low accuracy (55.90%), but using the 13 factors selected in one step of exploration improved the accuracy to 81.25%. This was further improved to 92.80% using only the nine conditioning factors selected during both steps of the data exploration. Therefore, exploratory data analysis selected the conditioning factors most suitable for landslide susceptibility analysis and thereby improving the performance of the analysis.

• Journal of the Korean Society of Surveying, Geodesy, Photogrammetry and Cartography
• /
• v.34 no.4
• /
• pp.443-451
• /
• 2016

Globally, landslides triggered by natural or human activities have resulted in enormous damage to both property and life. Recent climatic changes and anthropogenic activities have increased the number of occurrence of these disasters. Despite many researches, there is no standard method that can produce reliable prediction. This article discusses the process of landslide susceptibility mapping using various methods in current literatures and applies the FR (Frequency Ratio) method to develop a susceptibility map for the 2015 earthquake region of Sindhupalchowk, Nepal. The complete mapping process describes importance of selection of area, and controlling factors, widespread techniques of modelling and accuracy assessment tools. The FR derived for various controlling factors available were calculated using pre- and post- earthquake landslide events in the study area and the ratio was used to develop susceptibility map. Understanding the process could help in better future application process and producing better accuracy results. And the resulting map is valuable for the local general and authorities for prevention and decision making tasks for landslide disasters.

• Geomechanics and Engineering
• /
• v.30 no.4
• /
• pp.393-399
• /
• 2022

The Segregation Potential (SP) is one of the most widely used predictors of frost heave in cold regions. Laboratory step-freezing tests determining a representative SP at the onset of the formation of the last ice lens (near the thermal steady state condition) can predict susceptibility to frost heave. Previous work has proposed empirical semi-log fitting for determination of the representative SP and applied it to several fine-grained soils, but considering only frost-susceptible soils. The presence of fines in coarse-grained soil affects frost susceptibility. Therefore, it is required to evaluate the applicability of the empirical semi-log fitting for both frost-susceptible and non-frost-susceptible soils with fines content. This paper reports laboratory frost heave tests for fines contents of 5%-70%. The frost susceptibility of soil mixtures composed of sand and silt was classified by the representative SP, and the suitability of the empirical semi-log fitting method was assessed. Combining semi-log fitting with simple laboratory frost heave testing using a temperature-controllable cell is shown to be suitable for both frost-susceptible and non-frost-susceptible soils. In addition, initially non-frost-susceptible soil became frost susceptible at a 10%-20% weight fraction of fines. This threshold fines content matched well with transitions in the engineering characteristics of both the unfrozen and frozen soil mixtures.

• Proceedings of the Korean Geotechical Society Conference
• /
• 2002.10a
• /
• pp.499-506
• /
• 2002

The purpose of this study is to develop landslide susceptibility analysis techniques using artificial neural networks and to apply the newly developed techniques for assessment of landslide susceptibility to the study area of Yongin in Korea. Landslide locations were identified in the study area from interpretation of aerial Photographs and field survey data, and a spatial database of the topography, soil type and timber cover were constructed. The landslide-related factors such as topographic slope, topographic curvature, soil texture, soil drainage, soil effective thickness, timber age, and timber diameter were extracted from the spatial database. Using those factors, landslide susceptibility and weights of each factor were analyzed by two artificial neural network methods. In the first method, the landslide susceptibility index was calculated by the back propagation method, which is a type of artificial neural network method. Then, the susceptibility map was made with a GIS program. The results of the landslide susceptibility analysis were verified using landslide location data. The verification results show satisfactory agreement between the susceptibility index and existing landslide location data. In the second method, weights of each factor were determinated. The weights, relative importance of each factor, were calculated using importance-free characteristics method of artificial neural networks.

• Journal of the Korean Society of Surveying, Geodesy, Photogrammetry and Cartography
• /
• v.36 no.2
• /
• pp.59-66
• /
• 2018

This study examined the correlation among topography, forest type, soil and geology in Inje area where landslides occurred during heavy rainfall from July 11 to July 18, 2006 to assess the landslide susceptibility. In order to assess the susceptibility of future landslides, landslides occurred in Inje area were classified into slide type and flow type, and slope angle, aspect, curvature, ridge and valley were extracted from the area. The landslide susceptibility was assessed by applying diameter class, age class, density, and forest type to Bayesianbased LR (Logistic Regression) model and WOE (Weight of Evidence) model, and the fitness of modeling was verified by predict rate curve. As the results of susceptibility assessment, using all landslides without no distintion, it was found that 75% of the LR model and 73% of the WOE model were fit in terms of the top 20% of the landslides. According to slide type and flow type in the top 20% of the landslides, it was found that 71% of the LR model and 69% of the WOE model were fit in terms of the slide type. Whereas, it was found that 86% of the LR model and 82% of the WOE model were fit in terms of the flow type. That is, the results of the LR model showed higher fitness than the results of the WOE model, and the fitness of the flow type was higher than that of the slide type. Consequently, it suggests that it is reasonable to assess and verify the landslide susceptibility according to the types of landslides.

• Tunnel and Underground Space
• /
• v.30 no.2
• /
• pp.149-163
• /
• 2020

This paper presents a logistic regression and GIS based urban ground sink susceptibility assessment using underground facility information considering soil particle loss. In the underground environment, the particle loss due to water flow or groundwater level change leads to the occurrence and expansion of cavities, which directly affect the ground sink. Four different contributory factors were selected according to the two underground facility domains (water pipeline area, sewer pipeline area) and subway line area. The logistic regression method was used to analyze the correlation and to derive the regression equation between the ground sink inventory and the contributory factors. Based on these results, three ground sink susceptibility maps were generated. The results obtained from this study are expected to provide basic data on the area susceptible to ground sink and needed to safety monitoring.

• Geomechanics and Engineering
• /
• v.25 no.1
• /
• pp.1-16
• /
• 2021

Machine learning models have been widely used for landslide susceptibility assessment (LSA) in recent years. The large number of inputs or conditioning factors for these models, however, can reduce the computation efficiency and increase the difficulty in collecting data. Feature selection is a good tool to address this problem by selecting the most important features among all factors to reduce the size of the input variables. However, two important questions need to be solved: (1) how do feature selection methods affect the performance of machine learning models? and (2) which feature selection method is the most suitable for a given machine learning model? This paper aims to address these two questions by comparing the predictive performance of 13 feature selection-based machine learning (FS-ML) models and 5 ordinary machine learning models on LSA. First, five commonly used machine learning models (i.e., logistic regression, support vector machine, artificial neural network, Gaussian process and random forest) and six typical feature selection methods in the literature are adopted to constitute the proposed models. Then, fifteen conditioning factors are chosen as input variables and 1,017 landslides are used as recorded data. Next, feature selection methods are used to obtain the importance of the conditioning factors to create feature subsets, based on which 13 FS-ML models are constructed. For each of the machine learning models, a best optimized FS-ML model is selected according to the area under curve value. Finally, five optimal FS-ML models are obtained and applied to the LSA of the studied area. The predictive abilities of the FS-ML models on LSA are verified and compared through the receive operating characteristic curve and statistical indicators such as sensitivity, specificity and accuracy. The results showed that different feature selection methods have different effects on the performance of LSA machine learning models. FS-ML models generally outperform the ordinary machine learning models. The best FS-ML model is the recursive feature elimination (RFE) optimized RF, and RFE is an optimal method for feature selection.

• Economic and Environmental Geology
• /
• v.34 no.4
• /
• pp.385-394
• /
• 2001

There are serious damage of people and properties every year due to landslides that are occurred by heavy rain. Because these phenomena repeat and the heavy rain is not an atmospheric anomaly, the counter plan becomes necessary. The study area, Ulsan, is one of the seven metropolitan, and largest cities of Korea and has many large facilities such as petrochemical complex and factories of automobile and shipbuilding. So it is necessary assess the landslide hazard potential. In the study. the three steps of landslide hazard assessment techniques such as susceptibility, possibility, and risk were performed to the study area using GIS. For the analyses, the topographic, geologic, soil, forest, meteorological, and population and facility spatial database were constructed. Landslide susceptibility representing how susceptible to a given area was assessed by overlay of the slope, aspect, curvature of topography from the topographic DB, type, material, drainage and effective thickness of soil from the soil DB, lype age, diameter and density from forest DB and land use. Then landslide possibility representing how possible to landslide was assessed by overlay of the susceptibility and rainfall frequency map, Finally, landslide risk representing how dangerous to people and facility was assessed by overlay of the possibil. ity and the population and facility density maps The assessment results can be used to urban and land use plan for landslide hazard prevention.