• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.20 no.8
• /
• pp.1581-1586
• /
• 2016

In this paper, we propose a central disaster monitoring system of the forest fire. This system provides the safe-zone and detection to reduce the suppression efforts. In existing system, it has a few providing the predicting of wildfire spread model and speed through topography, weather, fuel factor. This paper focus on the forest fire diffusion model and predictions of the path identified to ensure the safe zone. Also we have considering the forest fire of moving direction and speed for fire suppression and monitering. The proposed algorithm could provide the technique to analyze the attribute information that temperature, wind, smoke measured over time. This proposed central observing monitoring system could provide the moving direction of spred out forecast wildfire. This observing and monitering system analyze and simulation for the moving speed and direction forest fire, it could be able to predict and training the forest fire fighters in a given environment.

• Korean Journal of Remote Sensing
• /
• v.38 no.6_3
• /
• pp.1861-1869
• /
• 2022

Recent climate change can increase the frequency and damage of wildfires worldwide. It can also lead to the deterioration of the forest ecosystem and increase casualties and economic loss. Satellite-based indices for forest damage can facilitate an objective and rapid examination of burned areas and help analyze inaccessible places like North Korea. In this letter, we conducted a detection of burned areas in North Korea using the traditional Normalized Burn Ratio (NBR), the Normalized Difference Vegetation Index (NDVI) to represent vegetation vitality, and the Fire Burn Index (FBI) and Forest Withering Index (FWI) that were recently developed. Also, we suggested a strategy for the satellite-based detection of burned areas in the Korean Peninsula as a result of comparing the four indices. Future work requires the examination of small-size wildfires and the applicability of deep learning technologies.

• Analytical Science and Technology
• /
• v.34 no.5
• /
• pp.231-239
• /
• 2021

Detection of fire accelerants from fire residues is critical to determine whether the case was arson or accidental fire. However, to develop a standardized model for determining the presence or absence of fire accelerants was not easy because of high temperature which cause disappearance or combustion of components of fire accelerants. In this study, logistic regression, random forest, and support vector machine models were trained and evaluated from a total of 728 GC-MS analysis data obtained from actual fire residues. Mean classification accuracies of the three models were 63 %, 81 %, and 84 %, respectively, and in particular, mean AU-PR values of the three models were evaluated as 0.68, 0.86, and 0.86, respectively, showing fine performances of random forest and support vector machine models.

• Journal of Korean Society for Geospatial Information Science
• /
• v.15 no.1 s.39
• /
• pp.23-29
• /
• 2007

Spatial outliers in remotely sensed imagery represent observed quantities showing unusual values compared to their neighbor pixel values. There have been various methods to detect the spatial outliers based on spatial autocorrelations in statistics and data mining. These methods may be applied in detecting forest fire pixels in the MODIS imageries from NASA's AQUA satellite. This is because the forest fire detection can be referred to as finding spatial outliers using spatial variation of brightness temperature. In this paper, we propose a new forest fire detection algorithm which is based on local spatial association analysis, and test the proposed algorithm to evaluate its applicability. In order to evaluate the proposed algorithm, the results were compared with the MODIS fire product provided by the NASA MODIS Science Team, which showed the possibility of the proposed algorithm in detecting the fire pixels.

• Korean Journal of Remote Sensing
• /
• v.38 no.5_3
• /
• pp.967-977
• /
• 2022

The occurrence and intensity of wildfires are increasing with climate change. Emissions from forest fire smoke are recognized as one of the major causes affecting air quality and the greenhouse effect. The use of satellite product and machine learning is essential for detection of forest fire smoke. Until now, research on forest fire smoke detection has had difficulties due to difficulties in cloud identification and vague standards of boundaries. The purpose of this study is to detect forest fire smoke using Level 1 and Level 2 data of Geostationary Environment Monitoring Spectrometer (GEMS), a Korean environmental satellite sensor, and machine learning. In March 2022, the forest fire in Gangwon-do was selected as a case. Smoke pixel classification modeling was performed by producing wildfire smoke label images and inputting GEMS Level 1 and Level 2 data to the random forest model. In the trained model, the importance of input variables is Aerosol Optical Depth (AOD), 380 nm and 340 nm radiance difference, Ultra-Violet Aerosol Index (UVAI), Visible Aerosol Index (VisAI), Single Scattering Albedo (SSA), formaldehyde (HCHO), nitrogen dioxide (NO₂), 380 nm radiance, and 340 nm radiance were shown in that order. In addition, in the estimation of the forest fire smoke probability (0 ≤ p ≤ 1) for 2,704 pixels, Mean Bias Error (MBE) is -0.002, Mean Absolute Error (MAE) is 0.026, Root Mean Square Error (RMSE) is 0.087, and Correlation Coefficient (CC) showed an accuracy of 0.981.

• Proceedings of the KSRS Conference
• /
• 2005.10a
• /
• pp.186-188
• /
• 2005

Because forest fire changes the direction according to the environmental elements, it is difficult to predict the direction of it. Currently, though some researchers have been studied to which predict the forest fire occurrence and the direction of it, using the remote detection technique, it is not enough and efficient. And recently because of the development of the sensor technique, a lot of In-Situ sensors are being developed. These kinds of In-Situ sensor data are used to collect the environmental elements such as temperature, humidity, and the velocity of the wind. Accordingly we need the prediction technique about the environmental elements analysis and the direction of the forest fire, using the In-Situ sensor data. In this paper, as a technique for predicting the direction of the forest fire, we propose the correlation analysis technique about In-Situ sensor data such as temperature, humidity, the velocity of the wind. The proposed technique is based on the clustering method and clusters the In-Situ sensor data. And then it analyzes the correlation of the multivariate correlations among clusters. These kinds of prediction information not only helps to predict the direction of the forest fire, but also finds the solution after predicting the environmental elements of the forest fire. Accordingly, this technique is expected to reduce the damage by the forest fire which occurs frequently these days.

• Proceedings of the KSRS Conference
• /
• 2003.11a
• /
• pp.328-330
• /
• 2003

The land cover of burned area has changed dramatically since Daxinganling forest fire in Northeastern China during May 6 ? June 4, 1987. This research focused on determining the burn severity and assessment of forest recovery. Burned severity was classified into three levels from June 1987 Landsat TM data acquired just after the fire. A regression model was established between the forest canopy closure from 1999 forest stand map and the NDVI values from June 2000 Landsat ETM+ data. The map of canopy closure was got according to the regression model. And vegetation cover was classified into four types according to forest closure density. The change matrix was built using the classified map of burn severity and vegetation recovery. Then the change conversions of every forest type were analyzed. Results from this research indicate: forest recovery status is well in most of burned scars; and vegetation change detection can be accomplished using postclassification comparison method.

• Journal of Korean Society of Forest Science
• /
• v.85 no.1
• /
• pp.15-23
• /
• 1996

Preparing the era of forest resources management requires studies on forest fire. This study attempted to develop forest fire occurrence model using meteorological characteristics for the practical purposes of forecasting forest fire danger rate. To accomplish this goal, the relationships between forest fire occurrence and meteorological characteristics are estimated. In the process, the forest fire occurrence pattern of the study region(Taegu-Kyungpook) is categorized by employing qualification IV method. The study region was divided into three areas such as, Taegu, Andong and Pohang area. The meteorological variables emerged as affective to forest fire occurrence are relative humidity, longitude of sunshine, and duration of precipitation. To estimate the probability of forest fire danger, forest fire occurrence of three areas are regressed on the time series data of affective meteorological variables using logistic and probit model. The effectiveness of the models estimated are tested and showed acceptable degree of goodness. Those models developed would be helpful to increase the efficiency of forest fire management such as detection of forest fire occurrence and effective disposition of forest fire fight equipments.

• Korean Journal of Remote Sensing
• /
• v.37 no.5_3
• /
• pp.1373-1387
• /
• 2021

Forest fire poses a significant threat to the environment and society, affecting carbon cycle and surface energy balance, and resulting in socioeconomic losses. Widely used multi-spectral satellite image-based approaches for burned area detection have a problem in that they do not work under cloudy conditions. Therefore, in this study, Sentinel-1 Synthetic Aperture Radar (SAR) data from Europe Space Agency, which can be collected in all weather conditions, were used to identify forest fire damaged area based on a series of processes including Principal Component Analysis (PCA) and K-means clustering. Four forest fire cases, which occurred in Gangneung·Donghae and Goseong·Sokcho in Gangwon-do of South Korea and two areas in North Korea on April 4, 2019, were examined. The estimated burned areas were evaluated using fire reference data provided by the National Institute of Forest Science (NIFOS) for two forest fire cases in South Korea, and differenced normalized burn ratio (dNBR) for all four cases. The average accuracy using the NIFOS reference data was 86% for the Gangneung·Donghae and Goseong·Sokcho fires. Evaluation using dNBR showed an average accuracy of 84% for all four forest fire cases. It was also confirmed that the stronger the burned intensity, the higher detection the accuracy, and vice versa. Given the advantage of SAR remote sensing, the proposed statistical processing and K-means clustering-based approach can be used to quickly identify forest fire damaged area across the Korean Peninsula, where a cloud cover rate is high and small-scale forest fires frequently occur.

• Journal of Korea Society of Industrial Information Systems
• /
• v.28 no.5
• /
• pp.109-126
• /
• 2023

Early detection of forest fires is essential in preventing large-scale forest fires. Predicting forest fires serves as a vital early detection method, leading to various related studies. However, many previous studies focused solely on climate and geographic factors, overlooking human factors, which significantly contribute to forest fires. This study aims to develop forest fire prediction models that take into account human, weather and geographical factors. This study conducted a comparative analysis of four machine learning models alongside the logistic regression model, using forest fire data from Gangwon-do spanning 2003 to 2020. The results indicate that XG Boost models performed the best (AUC=0.925), closely followed by Random Forest (AUC=0.920), both of which are machine learning techniques. Lastly, the study analyzed the relative importance of various factors through permutation feature importance analysis to derive operational insights. While meteorological factors showed a greater impact compared to human factors, various human factors were also found to be significant.