• 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.

• 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 Society of Surveying, Geodesy, Photogrammetry and Cartography
• /
• v.15 no.2
• /
• pp.215-219
• /
• 1997

It is very difficult to conduct a tracing survey of a forest fire because the affected area is huge and the topology of the mountain defies access of investigators. As a result, remote sensing technique is used to get consecutive information about the range and ecological change of the affected area. Therefore, this study investigates the change of activity condition of vegetation by getting vegetation index, hinted by the fact that activities of plants decline after the fire.

• Proceedings of the Korea Institute of Fire Science and Engineering Conference
• /
• 2012.04a
• /
• pp.468-471
• /
• 2012

본 연구는 삼척시를 중심으로 행정구역별(읍 면 동) 산불발생 현황과 삼척시 지역에 필요한 산불감시카메라의 적정대수 산정에 관하여 연구를 수행하였으며 결과는, 이미 설치되어 있는 개별 카메라는 중첩되는 곳이 있어 가시권이 확보된 곳으로 이동해야 할 것으로 판단하였다. 또한, 감시가 취약한 지역에 신규로 설치할 경우에는 인접한 기관(지자체 및 지방산림청)간의 감시시설과 감시지역 중복여부, 감시시설 위치의 타당성 등은 물론 어디에 우선하여 설치할 것인지를 광역적이고 과학적으로 판단하며 설치해야하며, 삼척시의 경우 설치 적정대수를 산정한 바, 최소한 32대 이상은 되어야 가장 효율적인 산불감시체계가 가능할 것으로 분석되었다.

• Proceedings of the Korea Institute of Fire Science and Engineering Conference
• /
• 2011.04a
• /
• pp.447-452
• /
• 2011

산림 인접 시설은 산불의 발화원이자 주요 보호대상으로써, 이에 대한 관리와 소방 우선 순위의 결정은 인명과 재산의 보호를 위해 매우 중요하다고 할 수 있다. 본 연구에서는 이에 대한 설문조사를 실시하여 인접시설의 대상물과 우선순위에 대한 조사를 실시하였다. 설문조사결과 산불발생 취약대상에 대한 인지도는 높으나, 산불보호 대상에 대한 인지도는 낮으므로, 이에 대한 분류체계 수립과 교육이 필요하며, 산불관련 공무원들은 논밭두렁, 묘지, 과수원을 취약대상으로 인지하며, 문화재와 천연보호림을 보호대상으로 인식하고, 주요 피해 대상은 문화재와 주거 시설이라고 제시하였다.

• The Journal of the Korea Contents Association
• /
• v.13 no.6
• /
• pp.40-47
• /
• 2013

In case of wild fire, early detection of wild fire is the most important factor in minimizing the damages. In this paper, we suggest an effective system that detects wild fire using a panoramic image from a single camera with PAN/TILT head. This enables the system to detect the size and the location of the fire in the early stages. After converting RGB image input to color YCrCb image, the differential image is used to detect changes in movement of the smoke to determine the regions which may be prone to forest fire. Histogram analysis of fire flame is used to determine the possibility of fire in the predetermined regions. In addition, image matching and SURF were used to create the panoramic image. There are many advantages in this system. First of all, it is very economical because this system needs only a single camera and a monitor. Second, it shows the live image of wide view through panoramic image. Third, this system can reduce the quantity of saved data by storing panoramic images.

• Korean Journal of Remote Sensing
• /
• v.33 no.6_1
• /
• pp.1029-1040
• /
• 2017

Wildfires release a large amount of greenhouse gases (GHGs) into the atmosphere. Fire radiative power (FRP) data obtained from geostationary satellites can play an important role for tracing the GHGs. This paper describes an estimation of the Himawari-8 FRP and fire emissions for Samcheock and Gangnueng wildfire in 6 May 2017. The FRP estimated using Himawari-8 well represented the temporal variability of the fire intensity, which cannot be captured by MODIS (Moderate Resolution Imaging Spectroradiometer) because of its limited temporal resolution. Fire emissions calculated from the Himwari-8 FRP showed a very similar time-series pattern compared with the AirKorea observations, but 1 to 3 hour's time-lag existed because of the distance between the station and the wildfire location. The estimated emissions were also compared with those of a previous study which analyzed fire damages using high-resolution images. They almost coincided with 12% difference for Samcheock and 2% difference for Gangneung, demonstrating a reliability of the estimation of fire emissions using our Himawari-8 FRP without high-resolution images. This study can be a reference for estimating fire emissions using the current and forthcoming geostationary satellites in East Asia and can contribute to improving accuracy of meteorological products such as AOD (aerosol optical depth).

• 방재와보험
• /
• s.63
• /
• pp.56-58
• /
• 1994

• Journal of the Korean Association of Geographic Information Studies
• /
• v.7 no.2
• /
• pp.78-86
• /
• 2004

Recently GPS and mobile GIS technologies based on LBS(location based service) have played an important role as DSS(decision supporting system) for domestic forest fire extinguishment policies. In this study forest fire extinguishments information management system based on mobile GIS technique was designed to seize the exact location on wireless network so that it helps to guide the safe and efficient extinguishments affairs and provide the extinguishments environment toward ground fighting teams and the central forest government in real time. Moreover, possibly to operate this system, the foundation technologies by the name of '.gci' such as the spatial data compression method, the spatial data transmission method over wireless network and the spatial analysis interface on PDA should be mainly considered. Especially, in this study the spatial data compression method having high compression rate from 51% to 62% for each polygon, line, and point data, without the loss of data was developed.

• Korean Journal of Remote Sensing
• /
• v.35 no.6_2
• /
• pp.1083-1093
• /
• 2019

The purpose of this study is to detect the burned area change by direct burning of tree canopies and post-fire mortality of trees via analyzing satellite imageries from the Korea multi-purpose satellite-2 and -3 (KOMPSAT-2 and -3) for two large-fires over the Goseong-Sokcho and Gangneung-Donghae regions in April 2019. For each case, the burned area was compared between two dates: the day when the fire occurred and 15-18 days after it. As the results, within these two dates, there was no substantial difference in burned area of sites whose severities were marked as "Extreme", but sites with "High" and "Low" severities showed significant differences in burned area between the two dates. These differences were resulted from the lagged post-fire browning of canopies which was detected by images from in-situ observation,satellite, and the unmanned aerial vehicle. The post-fire browning started after 3-4 days and became apparent after 10-15 days. This study offers information about the timing to quantify the burned area by large fire and about the mechanism of post-fire mortality. Also, the findings can support policy makers in planning the restoration of the damaged areas.