• Proceedings of the KSRS Conference
• /
• 2005.10a
• /
• pp.450-453
• /
• 2005

A forest fire occurs mainly as natural factor such as wind, temperature or human factor such as light. Recently, the most of forest fire prevention is prediction or prevision against forest fire by using remote sensing technology. However in order to forest fire prevention, the remote sensing has many limitations such as high cost and advanced technologies and so on. Therefore, we need to multisensor integration system that utilize not only remote sensing but also in-situ sensing in order to reduce large damage of forest fire though analysis of happen cause and prediction routing of occurred forest fire. In this paper we propose a multisensor integration system that offers prediction information of factors and route of forest fire by integrates collected data from remote sensor and in-situ sensor for forest fire prevention. The proposed system is based on wireless sensor network for collect observed data from various sensors. The proposed system not only offers great quality information because firstly, raw data level fuse different format of collected data from remote and in-situ sensor but also accomplish information level fusion based on result of first stage. Offered information from our system can help early prevention of factor and early prevision against occurred forest fire which transfer to SMS service or alert service into monitoring interface of administrator.

• Korean Journal of Remote Sensing
• /
• v.35 no.6_2
• /
• pp.1107-1115
• /
• 2019

Satellite data play a major role in supporting knowledge about forest fire by delivering rapid information to map areas damaged. This study, we used 7 Sentinel-2A images to detect change area in forests of Sokcho on April 4, 2019. The process of classify forest fire severity used 7 levels from Sentinel-2A dNBR(differenced Normalized Burn Ratio). In the process of classifying forest fire damage areas, the study selected three areas with high regrowth of vegetation level and conducted a detailed spatial analysis of the areas concerned. The results of dNBR analysis, regrowth of coniferous forest was greater than broad-leaf forest, but NDVI showed the lowest level of vegetation. This is the error of dNBR classification of dNBR. The results of dNBR time series, an area of forest fire damage decreased to a large extent between April 20th and May 3rd. This is an example of the regrowth by developing rare-plants and recovering broad-leaf plants vegetation. The results showed that change area was detected through the change detection of danage area by forest category and the classification errors of the coniferous forest were reached through the comparison of NDVI and dNBR. Therefore, the need to improve the precision Korean forest fire damage rating table accompanied by field investigations was suggested during the image classification process through dNBR.

• Proceedings of the KSRS Conference
• /
• 2005.10a
• /
• pp.687-690
• /
• 2005

Recently there have been a lot of kinds of damages in forest area such as forest fires, forest pest, landslide so that the efficient methods to mange those information and the way to face them are deadly needed. In this study, there were preparing the various vegetation index map and comparing them with the field surveying the tried to figure out which vegetation index algorism is the best proper to present forest fire damaged area. These all were based on Landsat ETM+ satellite image (2000.10.16). The result of this study is to select the high correlation algorism among the various vegetation indexes and then construct the forest fire disaster map, the case of forest fires damaged area.

• Korean Journal of Remote Sensing
• /
• v.38 no.6_1
• /
• pp.1273-1283
• /
• 2022

Recently, forest fires have frequently occurred due to climate change, leading to human and property damage every year. The forest fire monitoring technique using remote sensing can obtain quick and large-scale information of fire-damaged areas. In this study, the Gangneung and Donghae forest fires that occurred in March 2022 were analyzed using the spectral band of Sentinel-2, the normalized difference vegetation index (NDVI), and the normalized difference water index (NDWI) to classify the affected areas of forest fires. The U-net based convolutional neural networks (CNNs) model was simulated for the fire-damaged areas. The accuracy of forest fire classification in Donghae and Gangneung classification was high at 97.3% (f₁=0.486, IoU=0.946). The same model used in Donghae and Gangneung was applied to Uljin and Samcheok areas to get rid of the possibility of overfitting often happen in machine learning. As a result, the portion of overlap with the forest fire damage area reported by the National Institute of Forest Science (NIFoS) was 74.4%, confirming a high level of accuracy even considering the uncertainty of the model. This study suggests that it is possible to quantitatively evaluate the classification of forest fire-damaged area using a spectral band and indices similar to that of the Compact Advanced Satellite 500 (CAS500-4) in the Sentinel-2.

• Journal of the Korean Wood Science and Technology
• /
• v.36 no.4
• /
• pp.84-92
• /
• 2008

Anatomical and physical characteristics of Pinus densiflora woods damaged by forest fire at Yangyang-gun, Kangwon-do were investigated in present study. Even though the bark was severly carbonized, no trace of carbonization in the xylem was found. The amount of resin exudation was different by the degree of fire damage. Green moisture content of sapwood in the damaged wood was lower than that in the sound wood, but vice versa in the heartwood. Green density of heartwood in the damaged wood was higher than that in the sound wood, but there was no significant difference in sapwood. Cambial activities were found stopped in the severely damaged wood but were identified in the lightly damaged wood. In safranine staining process, epithelial and ray parenchyma cell walls in the damaged woods showed darker hue than those in the sound wood. Granular substances were observed in the lumina of ray parenchyma and epithelial cells of the severely damaged wood. Relative crystallinity of the outermost growth ring in the severely damaged wood was slightly higher than that in the sound wood.

• The Journal of Bigdata
• /
• v.6 no.1
• /
• pp.133-144
• /
• 2021

This paper derives the fire risk of buildings in Seoul through the prediction of property damage and the occurrence of fires. This study differs from prior research in that it utilizes variables that include not only a building's characteristics but also its affiliated administrative area as well as the accessibility of nearby fire-fighting facilities. We use Ensemble Voting techniques to merge different machine learning algorithms to predict property damage and fire occurrence, and to extract feature importance to produce fire risk. Fire risk prediction was made on 300 buildings in Seoul utilizing the established model, and it has been derived that with buildings at Level 1 for fire risks, there were a high number of households occupying the building, and the buildings had many factors that could contribute to increasing the size of the fire, including the lack of nearby fire-fighting facilities as well as the far location of the 119 Safety Center. On the other hand, in the case of Level 5 buildings, the number of buildings and businesses is large, but the 119 Safety Center in charge are located closest to the building, which can properly respond to fire.

• Proceedings of the Korean Institute of Electrical and Electronic Material Engineers Conference
• /
• 2007.06a
• /
• pp.523-524
• /
• 2007

Forest fire can give a serious damage to overhead conductors. Therefore, the definite understanding about aging behavior of burned conductor is very important in maintaining the transmission line safely. It is sure that the temperature of conductor itself will be affected by the distance apart from flame. From this point of a view, we monitored the conductor's temperature with distance from flame. As a result, the conductor's temperature decreased as the flame goes away from the conductor gradually. The temperature of conductor was reached up to 55~65% level of its atmospheric temperature. The detailed results will be presented in the text.

• Journal of the Korean Society of Hazard Mitigation
• /
• v.2 no.1 s.4
• /
• pp.161-167
• /
• 2002

Forest fire danger period in nine Provinces (Gangwondo, Kyonggido, Gyeongsangnamdo, Gyeongsangbukdo, Jeollanamdo, Jeollabukdo, Jejudo, Chungcheongnamdo, Chungcheongbukdo) has turned out to be similar to recognize whether there are some differences between each Provinces, we used correlation analysis with number of occurrence and damage area by an interval of ten-day period. Based on this analysis, there was significant numbers of occurrence at all areas wish serious burns except Gyeongsangnamdo and Jejudo Provinces. Since persuasive power is insufficient as danger period of forest fire applies equally to nine Provinces, statistical analysis using number of forest fire occurrence and burned area are executed. And then, a analysis of variance(ANOVA) test of significance by an interval of ten day period is carried out. As a result of this analysis, there showed significant at 1% level for number of occurrence except Jejudo, and is also showed significant at 1% level for burned area except Gangwondo and Chejudo. Through regional correlation analysis for danger period, we classified three parts of Middle region (Gangwondo, Kyonggido, Gyeongsangnamdo, Gyeongsangbukdo, Jeollabukdo, Chungcheongnamdo, Chungcheongbukdo) Southern region (Gyongsangnamdo, Jeollanamdo) and Jejudo region. With respect to forest fire occurrence time, Middle region showed from the middle of February to first of May that amounts to 81% of entire occurrence in this region, and Southern region begins with at the last of January to the middle of April covering 71%. In terms of forest fire burned areas, it appears at the middle of February to the first of May, occupying 98% in Middle region, and Southern region showed burned areas from the last of January to the middle of April amounting to 82% of total occurrences.

• Proceedings of the KSME Conference
• /
• 2007.05b
• /
• pp.3512-3517
• /
• 2007

Nuclear power plant has many external fire hydrants that have to operate in the state of emergency such as facility fire, forest fire. The valve stem of one among them was broken 3 times for 4 years. It had long valve stem and operated under high water pressure. The elongation and the tensile strength for the broken valve stem was measured to examine the defect of material property. And the vibration level and the natural frequencies was detected to check the resonance. As the result of a diagnosis, the cause of this fault is proven buckling of long valve stem.

• Journal of Korean Society of Rural Planning
• /
• v.15 no.2
• /
• pp.81-96
• /
• 2009

This study has found out the status of the environment ecology(topography structure. land-use, flora, plant community structure, wildbird) in 10 uninhabited islands(i.e. Kei island, Hadon island, Sangdon island, Daewa island, Hwanggang island, Naebi island, Oebi island, Prickly castor-oil tree island, Tongin island, Yuk island), Namhae-gun, Gyeongsangnam-do. Moreover, It has suggested ways of improving the environment ecology status by classifying the type of environment ecology about the degree of use and damage that based on the results of environment ecology survey. According to the results of topography structure survey, the survey site altitude was ranged within 1m$\sim$25m, otherwise, the radient was classified the rock area(.i.e. slope of less than $5^{\circ}$ the dead level) and the slope area where is steep slope. Moreover, there was showed evenly a variety of aspect. Land-use were divided the field(Kei island), dry native grasslands(Hadon island), naturalized grasslands(Sangdon island), Pinus thunbergii community(Dacwa island, Hwanggang island, Naebi island, Yuk island), the rock area(Oebi island, Prickly castor-oil tree island, Tongin island). As the results of flora survey, the number of plant species were 30$\sim$115 species and the naturalized species were found 2$\sim$12 species in each site. The results of plant community structure analysis, The dominant species were Pinus thunbergii and Pinus densiflora were in upper tree layer, furthermore, it were Pinus thunbergii, Eurya japonica, Prunus sargentii, Celtis sinensis, Morus bombycis, ect. in cannopy tree layer. In shrub layer, the dominant species were Rosa multiflora, Rubus crataegifolius, Parthenocissus tricuspidata, etc. The status of wildbird bird, had been found 42 species 938 individuals, especially, there were Bubo bubo kiautschensis(natural monument No. 324) and Haematopus ostralegus osculans(natural monument No. 326). According to these synthetic results, we are able to classify the 5 types of environment ecology such as the natural coast forest that composed of Pinus thunbergii and Pinus densiflora(Daewa island, Hwanggang island, Naebi island, Oebi island, Tongin island, Yuk island), the field in vegetation area(Kei island), vegetation succession area of fallow field type(Hadon island), vegetation damage area by the forest fire and disturbance elements(Prickly castor-oil tree island), dominant naturalized species grassland by grazing cattle(Sangdon island).