• Economic and Environmental Geology
• /
• v.43 no.4
• /
• pp.381-391
• /
• 2010

Probabilistic prediction methods of landslides which have been developed in recent can be reliable with premise of detailed survey and analysis based on deep and special knowledge. However, landslide susceptibility should also be analyzed with some reliable and simple methods by various people such as government officials and engineering geologists who do not have deep statistical knowledge at the moment of hazards. Therefore, this study suggests an evaluation chart of landslide susceptibility with high reliability drawn by accurate statistical approaches, which the chart can be understood easily and utilized for both specialists and non-specialists. The evaluation chart was developed by a quantification method based on canonical correlation analysis using the data of geology, topography, and soil property of landslides in Korea. This study analyzed field data and laboratory test results and determined influential factors and rating values of each factor. The quantification analysis result shows that slope angle has the highest significance among the factors and elevation, permeability coefficient, porosity, lithology, and dry density are important in descending order. Based on the score assigned to each evaluation factor, an evaluation chart of landslide susceptibility was developed with rating values in each class of a factor. It is possible for an analyst to identify susceptibility degree of a landslide by checking each property of an evaluation factor and calculating sum of the rating values. This result can also be used to draw landslide susceptibility maps based on GIS techniques.

• Journal of the Korean Society of Surveying, Geodesy, Photogrammetry and Cartography
• /
• v.32 no.4_1
• /
• pp.281-292
• /
• 2014

This study examined the accuracy that produced using various types and combinations of landslide-related factors from landslide susceptibility index maps. A database of landslide-related factors was adopted by the landslide locations that obtained from aerial photographs, and the topographic factors that derived from airborne LiDAR observations and digital maps, and various soil, forest, and land cover. Landslide susceptibility index maps were calculated by logistic regression and frequency ratio from the landslide susceptibility index. The correlation between airborne LiDAR data and digital map was shown strong similarities with one another. Landslide susceptibility index maps indicated the existence of a strong correlation and high prediction accuracy, especially when the frequency ratio and airborne LiDAR were used. Therefore, we concluded that the Airborne LiDAR will contribute to the development of effective landslide prediction methods and damage reduction measures.

• Journal of Korean Society for Geospatial Information Science
• /
• v.25 no.1
• /
• pp.19-27
• /
• 2017

This research was aimed to analyze landslide susceptibility and compare the prediction accuracy using ensemble frequency ratio (FR) and logistic regression at the Inje area, Korea. The landslide locations were identified with the before and after aerial photographs of landslide occurrence that were randomly selected for training (70%) and validation (30%). The total twelve landslide-related factors were elevation, slope, aspect, distance to drainage, topographic wetness index, stream power index, soil texture, soil sickness, timber age, timber diameter, timber density, and timber type. The spatial relationship between landslide occurrence and landslide-related factors was analyzed using FR and ensemble model. The produced LSI maps were validated and compared using relative operating characteristics (ROC) curve. The prediction accuracy of produced ensemble LSI map was about 2% higher than FR LSI map. The LSI map produced in this research could be used to establish land use planning and mitigate the damages caused by disaster.

• Journal of Korean Society for Geospatial Information Science
• /
• v.18 no.4
• /
• pp.61-69
• /
• 2010

The collapse of a slope or cut embankment brings much damage to life and property. Accordingly, it is very important to analyze the spatial distribution by calculating the landslide susceptibility in the estimation of the risk of landslide occurrence. The heuristic, statistic, deterministic, and probabilistic methods have been introduced to make landslide susceptibility maps. In many cases, however, the reliability is low due to insufficient field data, and the qualitative experience and knowledge of experts could not be combined with the quantitative mechanical?analysis model in the existing methods. In this paper, new modeling method for a probabilistic landslide susceptibility analysis combined Bayesian Network with ontology model about experts' knowledge and spatial data was proposed. The ontology model, which was made using the reasoning engine, was automatically converted into the Bayesian Network structure. Through conditional probabilistic reasoning using the created Bayesian Network, landslide susceptibility with uncertainty was analyzed, and the results were described in maps, using GIS. The developed Bayesian Network was then applied to the test-site to verify its effect, and the result corresponded to the landslide traces boundary at 86.5% accuracy. We expect that general users will be able to make a landslide susceptibility analysis over a wide area without experts' help.

• 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.

• The Journal of Engineering Geology
• /
• v.32 no.1
• /
• pp.27-40
• /
• 2022

Every year landslides cause serious casualties and property damages around the world. As the accurate prediction of landslides is important to reduce the fatalities and economic losses, various approaches have been developed to predict them. Prediction methods can be divided into landslide susceptibility analysis, landslide hazard analysis and landslide risk analysis according to the type of the conditioning factors, the predicted level of the landslide dangers, and whether the expected consequence cased by landslides were considered. Landslide susceptibility analyses are mainly based on the available landslide data and consequently, they predict the likelihood of landslide occurrence by considering factors that can induce landslides and analyzing the spatial distribution of these factors. Various qualitative and quantitative analysis techniques have been applied to landslide susceptibility analysis. Recently, quantitative susceptibility analyses have predominantly employed the physically based model due to high predictive capacity. This is because the physically based approaches use physical slope model to analyze slope stability regardless of prior landslide occurrence. This approach can also reproduce the physical processes governing landslide occurrence. This review examines physically based landslide susceptibility analysis approaches.

• 한국지구과학회:학술대회논문집
• /
• 2005.02a
• /
• pp.254-260
• /
• 2005

이 논문에서는 산사태 취약성 분석을 목적으로 확률론적 공간통합의 틀 안에서 범주형 자료와 연속형 자료를 효율적으로 처리할 수 있는 비모수적 우도비 추정 모델과 모수적 예측적 판별 분석 모델을 적용하였다. 적용 모델의 비교를 위해 1998년 여름철 산사태로 많은 피해를 입은 경기도 장흥 지역과 충청북도 보은 지역을 대상으로 사례연구를 수행하였다. 장흥 지역에서는 두 모델이 유사한 예측 능력을 나타내었으나, 보은 지역에서는 모수적 예측적 판별 분석 모델이 상대적으로 높은 예측 능력을 나타내었다. 결론적으로 제안한 두 모델은 산사태 취약성 분석을 위한 연속형 자료 표현에 효율적으로 적용될 수 있으며, 두 모델이 개별적인 연속형 자료 표현의 특성을 가지고 있기 때문에 다른 사례 연구를 통한 검증 작업이 병행되어야 할 것으로 생각된다.

• Economic and Environmental Geology
• /
• v.34 no.2
• /
• pp.205-215
• /
• 2001

The purpose of this study is to analyze the landslide susceptibility, containing the process, which reveals spatial relationships between landslides and geospatial data sets, which occurred in Janghung area in 1998. Landslide locations were detected from remotely sensed image and field survey and topography, soil, forest, and land use data sets were constructed as a spatial database in GIS. As the landslide occurrence factors, slope, aspect, curvature and type of topography, texture, material, drainage and effective thickness of soil, type, age, diameter and density of wood and land use were used. To extract the relationship between landslides and geospatial database, likelihood ratio was calculated and compared with the result of Yongin area. Also, the landslide susceptibility index was calculated by summation of the likelihood ratio and the landslide susceptibility map was generated using the index. As a result, it is expected that spatial relationships between landslides and geospatial database is helpful to explain the characteristics of lilndslide and the landslide susceptibility map is used to reduce associated hazards, and to plan land use and construction.

• Proceedings of the KSEEG Conference
• /
• 2000.04a
• /
• pp.113-114
• /
• 2000

• Economic and Environmental Geology
• /
• v.52 no.2
• /
• pp.199-212
• /
• 2019

In the machine learning techniques, the sampling strategy of the training data affects a performance of the prediction model such as generalizing ability as well as prediction accuracy. Especially, in landslide susceptibility analysis, the data sampling procedure is the essential step for setting the training data because the number of non-landslide points is much bigger than the number of landslide points. However, the previous researches did not consider the various sampling methods for the training data. That is, the previous studies selected the training data randomly. Therefore, in this study the authors proposed several different sampling methods and assessed the effect of the sampling strategies of the training data in landslide susceptibility analysis. For that, total six different scenarios were set up based on the sampling strategies of landslide points and non-landslide points. Then Random Forest technique was trained on the basis of six different scenarios and the attribute importance for each input variable was evaluated. Subsequently, the landslide susceptibility maps were produced using the input variables and their attribute importances. In the analysis results, the AUC values of the landslide susceptibility maps, obtained from six different sampling strategies, showed high prediction rates, ranges from 70 % to 80 %. It means that the Random Forest technique shows appropriate predictive performance and the attribute importance for the input variables obtained from Random Forest can be used as the weight of landslide conditioning factors in the susceptibility analysis. In addition, the analysis results obtained using specific sampling strategies for training data show higher prediction accuracy than the analysis results using the previous random sampling method.