• Journal of Korean Society of Forest Science
• /
• v.109 no.4
• /
• pp.438-445
• /
• 2020

The characteristics of forest environmental factors were analyzed using the quantification theory (I) for prediction of the suitable area of erosion control dams. The results indicated that sediment discharge in small forest catchments was significantly correlated with dredging passage (0.7495) and age class (0.6000). In contrast, area (0.3416), slope gradient (0.3207), rainfall (0.3160), altitude (0.2990) and soil type (0.2192) were poorly correlated. Following quantification theory (I), we developed a selection decision table for erosion control dams based on sediment discharge rate as class I (highly suitable site, greater than 2.2496), class II (suitable site, 1.1248~2.2495), and class III (poorly suited site, lower than 1.1247).

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.21 no.8
• /
• pp.521-529
• /
• 2020

Forest fires are one of the most important environmental risks that have adverse effects on many aspects of life, such as the economy, environment, and health. The early detection, quick prediction, and rapid response of forest fires can play an essential role in saving property and life from forest fire risks. For the rapid discovery of forest fires, there is a method using meteorological data obtained from local sensors installed in each area by the Meteorological Agency. Meteorological conditions (e.g., temperature, wind) influence forest fires. This study evaluated a Data Mining (DM) approach to predict the burned area of forest fires. Five DM models, e.g., Stochastic Gradient Descent (SGD), Support Vector Machines (SVM), Decision Tree (DT), Random Forests (RF), and Deep Neural Network (DNN), and four feature selection setups (using spatial, temporal, and weather attributes), were tested on recent real-world data collected from Gyeonggi-do area over the last five years. As a result of the experiment, a DNN model using only meteorological data showed the best performance. The proposed model was more effective in predicting the burned area of small forest fires, which are more frequent. This knowledge derived from the proposed prediction model is particularly useful for improving firefighting resource management.

• Journal of Computing Science and Engineering
• /
• v.11 no.4
• /
• pp.142-151
• /
• 2017

Spontaneous intracerebral hemorrhage (sICH) has a high mortality rate. Research has demonstrated that sICH occurrence is related to weather conditions; therefore, this study used the decision tree method to explore the impact of climatic risk factors on sICH at different ages. The Taiwan National Health Insurance Research Database (NHIRD) and other open-access data were used in this study. The inclusion criterion was a first-attack sICH. The decision tree algorithm and random forest were implemented in R programming language. We defined a high risk of sICH as more than the average number of cases daily, and the younger, middle-aged and older groups were calculated as having 0.77, 2.26 and 2.60 cases per day, respectively. In total, 22,684 sICH cases were included in this study; 3,102 patients were younger (<44 years, younger group), 9,089 were middle-aged (45-64 years, middle group), and 10,457 were older (>65 years, older group). The risk of sICH in the younger group was not correlated with temperature, wind speed or humidity. The middle group had two decision nodes: a higher risk if the maximum temperature was >$19^{\circ}C$ (probability = 63.7%), and if the maximum temperature was <$19^{\circ}C$ in addition to a wind speed <2.788 (m/s) (probability = 60.9%). The older group had a higher risk if the average temperature was >$23.933^{\circ}C$ (probability = 60.7%). This study demonstrated that the sICH incidence in the younger patients was not significantly correlated with weather factors; that in the middle-aged sICH patients was highly-correlated with the apparent temperature; and that in the older sICH patients was highly-correlated with the mean ambient temperature. "Warm" cold ambient temperatures resulted in a higher risk of sICH, especially in the older patients.

• Journal of the Korean Institute of Landscape Architecture
• /
• v.33 no.4 s.111
• /
• pp.97-107
• /
• 2005

This study was carried out to construct accurate and scientific system of assessment indicators in selection of National Trust conservation areas, which was new concept of domestic environment movement and offer the raw data of new analytic method by introducing the fuzzy theory and weight for overcoming the uncertainty of ranking decision. To transform the Likert's scale granted to assessment indicators into the type of triangular fuzzy number(a, b, c), there was conversion to each minimum(a), median(b), and maximum(c) in applying membership function, and in using the center of gravity and eigenvalue, there was to decide the ranking. The rankings of converted values applied a mean importance and weight were confirmed that they were generally changed. Therefore, the ranking decision was better to accomplish objective and rational ranking decision by applying weight that was calculated in grouping of indicator than to judge the singular concept and to be useful in assessment of diverse National Trust site. In the future, because AHP, which was general method of calculating weight, was lacked, there was to understand the critical point to fix a pertinent weight, and to carry out the study applying engineering concept like fuzzy integral using $\lambda-measure$.

• Spatial Information Research
• /
• v.17 no.3
• /
• pp.251-259
• /
• 2009

As a result of the current trend towards promoting conservation of the ecosystem, there have been various studies conducted to determine ways to establish an ecological network. The development of analytical methods and an environmental database of GIS has made the creation of this network more efficient. This study focuses on the development of an urban spatial decision support system based on 'Landscape Ecology Theory'. The spatial decision support system suggested in this study consists of four stages. First, landscape patch for the core areas, which are major structures of the ecological network, was determined using the GIS overlay method. Second, a forest habitat was investigated to determine connectivity assessment. Using the gravity model, connectivity assessment at the habitat forest was conducted to select the needed connecting area. Third, the most suitable corridor routes for the eco-network were presented using the least-cost path analysis. Finally, a brief investigation was conducted to determine the conflict areas between the study result and landuse. The results of this study can be applied to urban green network planning. Moreover, the method developed in this study can be utilized to control urban sprawl, promote biodiversity.

• Proceedings of the KSRS Conference
• /
• 2003.11a
• /
• pp.817-819
• /
• 2003

Land degradation is a crucial issue in mountainous areas and is manifested in a variety of processes. For its assessment, application of existing models is not straightforward. In addition, data availability might be a problem. In this paper, a procedure for land degradation assessment is described, which follows a four-step approach: (1) detection, inventory and mapping of land degradation features, (2) assessing the magnitude of soil loss, (3) study of causal factors, and (4) hazard assessment by applying decision trees. This approach is applied to a case study in the Middle Mountain region of Nepal. The study shows that individual mass movement features such as debris slides and slumps can be easily mapped by photo interpretation techniques. Application of soil loss estimation models helps get insight on the magnitude of soil losses. In the study area soil losses are higher in rainfed crops on sloping terraces (highest soil loss is 32 tons/ha/yr) and minimal under dense forest and in irrigated rice fields (less than 1 ton/ha/yr). However there is high frequency of slope failures in the form of slumps in the rice fields. Debris slides are more common on south-facing slopes under rainfed agriculture or in degraded forest. Field evidences and analysis of causal factors for land degradation helps in building decision trees, the use of which for modelling land degradation has the advantage that attributes can be ranked and tested according to their importance. In addition, decision trees are simple to construct, easy to implement and very flexible in adaptations.

• Journal of the Korean Association of Geographic Information Studies
• /
• v.12 no.2
• /
• pp.11-22
• /
• 2009

Recently the integration and development of ST(Spatial Technology) and forest geographic information have been used very efficiently for the forest administration. However, even though many application system related to forest information have been developed and improved, there are still paper based inventories management and hand work for data construction and upgrade. In this study the forest information warehouse, which is mapped and managed at work-site operations, was constructed based GIS technology so that the standardization and consistency of current data could be acquired in real time. In addition, these thematic maps were conducted on high resolution satellite images and managed in web based forest information data warehouse form and finally shared through Internet for the very first-line administration officials. This study shows that the forest information standardization service of municipal governments very first time in the Korea and provides the unified decision making support and enterprise formed forest database so that is expected to be the very successful sample to suggest the prototype of national forest spatial data infrastructure.

• Journal of Forest and Environmental Science
• /
• v.16 no.1
• /
• pp.119-123
• /
• 2000

This paper studies the methods to support decision making for forest management Using GIS. Specially, most important is selecting restrict area to timber harvest suitable on scheduling its harvest in experimental forest of kangwon national university. Because timber harvesting causes water pollution, land sliding and soil erosion, it is necessary to restrict area to be harvest. The study is analyzed with Buffering modules and overlay modules which are an function of Arcinfo 7.1. As a result, restricted area is 52.64ha in total area. Of which Hardwood stand 13.21ha, pinus Pinus koraiensis stand 26.44ha, Larix leptolepis stand 12.38ha and Pinus rigida stand 0.61ha.

• Journal of Korean Society of Forest Science
• /
• v.98 no.3
• /
• pp.311-318
• /
• 2009

This study purposed to construct supply and demand potential map of forest bioenergy with a GIS-based decision support system. The target areas of this study were a part of the forests in Yongdong region, Gangwondo, and most types of forests were pinus densiflora, pinus koreaiansis, and Oak. Data about forest type, age classes, the number of households, regional silviculture planning was stored in GIS to define the potential areas for supplying potential bioenergy from the forests, and to assess biomass available for a household. Theoretical potential biomass energy based on silviculture plan was estimated in average 3,144 Tcal, and this quantity will be enough to supply the quantity of demand of households in that area. However, if it assumed that average collecting rates of Kangwon province were 10%, the available quantity of biomass will be between 6% and 15% of demand. If the collecting rates were 60%, the supply of biomass could exceed the quantity of demand in certain cities.

• Journal of Korean Society of Forest Science
• /
• v.80 no.1
• /
• pp.9-19
• /
• 1991

This paper discusses the applicability of two simulation models for a ten year planning period in order to predict changing forest conditions. Two simulation models therefore were developed and applied to 3,844 ha of a national forest in Kangwondo province, which is managed by Joongbu Forest District Headquaters. Growth functions of three species were derived and used to predict the residual timber volume over time. Two alternative cutting schedules caused 10-14% difference in the residual timber volume in the end of ten year planning period. This suggests the important of correct decision-makings of forest managers in forest management planning.