• The Journal of The Korea Institute of Intelligent Transport Systems
• /
• v.21 no.6
• /
• pp.36-56
• /
• 2022

Traffic accidents occur in Korea are calculated with the 「Automobile Accident Negligence Ratio Certification Standard」 prepared by the 'General Insurance Association of Korea' and the insurance company's agreement or judgment is made. However, disputes are frequently occurring in calculating the negligence ratio. Therefore, it is thought that a more effective response would be possible if accident type according to the standard could be quickly identified using traffic accident information prepared by police. Therefore, this study aims to develop a model that learns the accident information prepared by the police and classifies it to match the accident type in the standard. In particular, through data mining, keywords necessary to classify the accident types of the standard were extracted from the accident data of the police. Then, models were developed to derive the types of accidents by learning the extracted keywords through decision trees and random forest models.

• Journal of the Korean Society of Environmental Restoration Technology
• /
• v.10 no.1
• /
• pp.100-113
• /
• 2007

In Korea, there has been no revegetation applicable standard for slopes formed by road construction work up to now, so revegetation work has been done using mostly foreign varieties in the manner of early revegetation. However, foreign varieties have some shortcomings; for example, they tend to be dried to death after construction work. Besides, due to the rift in the supporting soil, these revegetated varieties are often displaced from the slopes. Thus, the Ministry of Construction & Transportation on July, 2005 established revegetation standard on the slopes suited for the natural eco-system of Korea and organized positively recommending directions for using self-sewn plants growing near the slopes in overall consideration of soil, weather, regional conditions. The locations specified in this direction are the slopes at the road construction jobsite like the expressway, highways, and local roads. In addition, the Ministry's standard and directions stipulated that damaged slopes's natural environment and eco-system due to various road construction work should be restored, and thus a feeling of stability and pleasantness should be provided to road users as well. Also, the Ministry tried to select seed plants and revegetation measures suited for surrounding environment to put the environment-friendly slope revegetation measures into practice through the test revegetation work in order to prevent illegal construction practices and to improve the quality of revegetation. According to the direction, revegetation districts aimed at the slopes are divided into three ones in consideration of weather environment, regional environment, and forest environment as follows : national territory's core ecological green-land based district centering on the Taebaek Mountains; coastal ecosystem district including islands off the coast; inland eco-system district. The combination of revegetation plants according to environment revegetation districts, should be executed by dividing into herb-oriented type, woody plant colony type, and bio-species versatility restoration type, and the selection of seeding plants should be done in the presence of a supervisor and through test construction results and technology counseling from a specialist in natural eco-system restoration and revegetation measure seed combination standard according to environment revegetation districts. This direction will be executed in the manner of monitoring until the yea 2008 and 2009 it will be finalized and enforced on December, 2009.

• Journal of Ecology and Environment
• /
• v.32 no.4
• /
• pp.229-236
• /
• 2009

A habitat model was developed to delineate potential habitat of the leopard cat (Prionailurus bengalensis) in a mountainous region of Kangwon Province, Korea. Between 1997 and 2005, 224 leopard cat presence sites were recorded in the province in the Nationwide Survey on Natural Environments. Fifty percent of the sites were used to develop a habitat model, and the remaining sites were used to test the model. Fourteen environmental variables related to topographic features, water resources, vegetation and human disturbance were quantified for 112 of the leopard cat presence sites and an equal number of randomly selected sites. Statistical analyses (e.g., t-tests, and Pearson correlation analysis) showed that elevation, ridges, plains, % water cover, distance to water source, vegetated area, deciduous forest, coniferous forest, and distance to paved road differed significantly (P < 0.01) between presence and random sites. Stepwise logistic regression was used to develop a habitat model. Landform type (e.g., ridges vs. plains) is the major topographic factor affecting leopard cat presence. The species also appears to prefer deciduous forests and areas far from paved roads. The habitat map derived from the model correctly classified 93.75% of data from an independent sample of leopard cat presence sites, and the map at a regional scale showed that the cat's habitats are highly fragmented. Protection and restoration of connectivity of critical habitats should be implemented to preserve the leopard cat in mountainous regions of Korea.

• Proceedings of the Korea Water Resources Association Conference
• /
• 2022.05a
• /
• pp.156-156
• /
• 2022

Explicitly spatially distributed and reliable data on industrial water demand is very much important for both policy makers and researchers in order to carry a region-specific analysis of water resources management. However, such type of data remains scarce particularly in underdeveloped and developing countries. Current research is limited in using different spatially available socio-economic, climate data and geographical data from different sources in accordance to predict industrial water demand at finer resolution. This study proposes a random forest regression (RFR) model to predict the industrial water demand at 0.50× 0.50 spatial resolution by combining various features extracted from multiple data sources. The dataset used here include National Polar-orbiting Partnership (NPP)/Visible Infrared Imaging Radiometer Suite (VIIRS) night-time light (NTL), Global Power Plant database, AQUASTAT country-wise industrial water use data, Elevation data, Gross Domestic Product (GDP), Road density, Crop land, Population, Precipitation, Temperature, and Aridity. Compared with traditional regression algorithms, RF shows the advantages of high prediction accuracy, not requiring assumptions of a prior probability distribution, and the capacity to analyses variable importance. The final RF model was fitted using the parameter settings of ntree = 300 and mtry = 2. As a result, determinate coefficients value of 0.547 is achieved. The variable importance of the independent variables e.g. night light data, elevation data, GDP and population data used in the training purpose of RF model plays the major role in predicting the industrial water demand.

• Korean Journal of Environment and Ecology
• /
• v.25 no.5
• /
• pp.639-648
• /
• 2011

We recorded the movement of wildbirds nine times at Hoam 1st Tunnel, Kkachisan Park, Deungneung pass to compare the movement between eco-corridor and neighboring crossing road from June to September, 2006. Among three areas, birds did not prefer the eco-corridor at pass type such as Kkachisan Park and Deungneung pass, however number of species and individuals were high at the eco-corridor at Hoam 1st Tunnel. Over 90m width and the slope location of eco-corridors can be beneficial for wild birds to enhance the movement along eco-corridors between isolated two patches. Average foliage volume under two meters showed the relation with bush nesters, and that from 7 to 8m had the highest relationship with canopy nesters. In Seoul city, target species should be considered at the construction of eco-corridors according to site characteristics, but Paradoxornis webbianus could be suggested as a main target species at eco-corridors. To enhance the movement of diverse wildbirds, we would implement that eco-corridors could be located at the slope area with the size of 1ha (over 90m width), eco-corridors could be planted and managed with the high foliage volume of shrub layer under twometers and canopy layer over 8 meters.

• Journal of Korean Society of Forest Science
• /
• v.107 no.4
• /
• pp.486-496
• /
• 2018

Pine wilt disease (PWD) in Gyeonggi province was first detected in Gwangju in 2007, and ever since has caused extensive damage. Insect vector and host tree in Gyeonggi province are Monochamus saltuarius and Pinus koraiensis, respectively, which are different from the southern region that consist of Monochamus alternatus and Pinus densiflora. Consequently, spread and mortality characteristics may be different, but our understanding is limited. In this research, we utilized the spatial data of newly infected trees in Gyeonggi province from 2008 to 2015 to analyze how it is related to various environmental and human factors, such as elevation, forest type, and road network. We also analyzed the minimum distance from newly infected tree to last year's closest infected tree to examine the dispersal characteristics based on new outbreak locations. Annual number of newly infected trees rapidly increased from 2008 to 2013, which then stabilized. Number of administrative districts with infected trees was 5 in 2012, 11 in 2013, and 15 in 2014. Most of the infected trees was Pinus koraiensis, with its proportion close to 90% throughout the survey period. Mean distance to newly infected trees dramatically decreased over time, from 4,111 m from 2012 to 2013, to approximately 600 m from 2013 to 2014 and 2014 to 2015. Most new infections occurred in higher elevation over time. Distance to road from newly infected trees continuously increased, suggesting that natural diffusion dispersal is increasingly occurring compared to human-influenced dispersal over time.

• Proceedings of the KSRS Conference
• /
• 2003.11a
• /
• pp.1134-1136
• /
• 2003

In this research, GIS based evaluation methods were applied to habitats of Japanese black bear (Ursus thibetanus japonicus Schlegel) in northern Honshu. The study area was divided into 828 small watershed units , and five GIS indexes, Vegetation Type（V.T.）, Extent of Forest Cover (E.F.C.) Slope Incline (S.I), Average Altitude (A.A.) and Road Density(R.D.), were used to evaluate each watershed unit in terms of suitability as black bear habitat. In addition, Interspersion and Juxtaposition spatial indices were calculated for each watershed unit. The results clearly identified the regions with the most suitable habitats, indicating that this methodology is suitable for application to various environmental planning efforts, such as regional development master plans, project-specific environmental impact assessments, species management plans and biodiversity conservation plans.

• Journal of Korean Society of Forest Science
• /
• v.83 no.3
• /
• pp.322-330
• /
• 1994

The Universal Soil Loss Equation (USLE) has been widely used to predict long-term soil loss by incorporating several erosion factors, such as rainfall, soil, topography, and vegetation. This study is aimed to introduce the LISLE within geographic information system(GIS) environment. The Kwangneung Experimental Forest located in Kyongki Province was selected for the study area. Initially, twelve years of hourly rainfall records that were collected from 1982 to 1993 were processed to obtain the rainfall factor(R) value for the LISLE calculation. Soil survey map and topographic map of the study area were digitized and subsequent input values(K, L, S factors) were derived. The cover type and management factor (C) values were obtained from the classification of Landsat Thematic Mapper(CM) satellite imagery. All these input values were geographically registered over a common map coordinate with $25{\times}25m^2$ ground resolution. The USLE was calculated for every grid location by selecting necessary input values from the digital base maps. Once the LISLE was calculated, the resultant soil loss values(A) were represented by both numerical values and map format. Using GIS to run the LISLE, it is possible to pent out the exact locations where soil loss potential is high. In addition, this approach can be a very effective tool to monitor possible soil loss hazard under the situations of forest changes, such as conversion of forest lands to other uses, forest road construction, timber harvesting, and forest damages caused by fire, insect, and diseases.

• Journal of Korean Society of Disaster and Security
• /
• v.15 no.3
• /
• pp.31-40
• /
• 2022

Domestic disaster risk maps are mainly produced and studied as a single disaster map by grid unit and disaster type. In particular, it is necessary to present an evaluation method of the disaster risk map that is more suitable for the relevant facility (local road) in order to utilize the work of practitioners who are mainly in charge of facility maintenance. In this study, an evaluation method was presented to evaluate the risk with a focus on local roads by using the landslide risk map and debris flow risk map provided by the Korea Forest Service. In addition, the risk was evaluated and verified for the provinces located in Gangwon-do. As a result of the evaluation, it was possible to evaluate the risk of grades 1 to 5 for 1,513 evaluation sections in the evaluation section with a total length of 234.59 km.

• Journal of Korean Society of Forest Science
• /
• v.96 no.6
• /
• pp.652-660
• /
• 2007

The study was intended to investigate the changes of construction types of 216 non-national forest roads, which were completed between 1989 and 2005 in Jeollabuk-do, by analyzing their drawing and specification. It was found that the mean length of yearly construction has been significantly reduced after the Policy of Green Forest Roads compared with before the policy. Soil cut-off of earth work was changed from bulldozer to a combination of bulldozer and excavator. Soils were transported by truck in all design, but establishment of spoil-bank was not designed at all. The design of slope revegetation works was developed from turfing and Bastard indigo planting to seed spray, combination of seed spray and belt-sodding, and mulching with coir net and rice straw. In design of the culvert, the average interval of culvert installation was reduced to 92m in step 3, the dimension of culverts was expanded to over 600 mm after step 2, and all drainpipes were corrugated steel pipes. The design length of concrete pavement increased from 40 m/km of step 1 to 240 m/km of step 3. Thanks to the enormously increased amount of concrete pavement, the stability and functionality of forest roads could be improved. Stone masonry was the main work drawn for slope stability, and concrete retaining wall and gabion have been drawn for same object since 1999.