• Proceedings of the Korean Institute of Industrial Safety Conference
• /
• 1999.06a
• /
• pp.51-59
• /
• 1999

산불발생 요인으로 캐나다와 미국의 경우에는 자연적인 현상이 대부분을 차지하고 있으나 우리나라의 경우에는 입산 자들의 부주의, 농산폐기물소각 등에서 오는 인위적인 원인들이 대부분을 차지하고 있다. 또한 산불발생시 즉시 진화하기 어려운 이유는 우리나라의 지형특성상 구릉지가 많아 발견되기 어렵고, 산불의 진압을 위한 장비와 인력동원에서 오는 지연시간 및 산불확산에 영향을 미치는 요인들의 변화를 예측하기 어렵다는 점에 있다. (중략)

• Journal of Korean Society of Forest Science
• /
• v.97 no.4
• /
• pp.363-367
• /
• 2008

The purpose of this study was to evaluate the change of the amount of soil erosion by comparisons between burned and unburned area after forest fire. The amount of soil erosion in burned area was more high 11.2 times in year of fire, 8.4 times in 1 later year, 2 times in 5 later year and 1.3 times in 10 later year than in unburned area. The ratio of soil erosion in burned area was reduced to 98% of 10 later year as compared to the year of fire. Therefore, the soil erosion in the burned area almost tended to stabilization like unburned area passing ten year after forest fire. The most affecting factors on the amount of soil erosion in burned and unburned area were unit rainfall, number of unit rainfall and number of rainfall accumulated.

• Proceedings of the Korea Water Resources Association Conference
• /
• 2016.05a
• /
• pp.7-7
• /
• 2016

인도네시아 산불에 의한 연무는 동남아시아 인접한 국가들에 있어서 심각한 환경문제 중 하나이다. 국제적으로 심각한 문제를 야기하는 인도네시아의 산불은 건조기에 강수량이 적게 내리는 극심한 가뭄 조건에서 발생한다. 건조기 강수량을 모니터링 하는 것은 산불 발생 가능성을 예측하기 위해 중요하지만 산불을 사전에 예방하고 영향을 최소화하기에는 부족하다. 따라서 산불에 대한 선제적 사전예방을 위해서는 수개월의 선행예측 기간을 갖는 조기경보 시스템이 절실하다. 따라서 본 연구는 인도네시아 산불에 대한 선제적 대응을 위한 강수량 예측시스템을 개발하고 예측성을 평가하여 동남아시아 지역의 화재 연무 조기경보 시스템의 시제품(Prototype)을 개발하는데 있다. 강수량 예측을 위해서 APEC 기후센터의 계절예측정보의 활용 정도에 따라서 4가지 서로 다른 방법을 통합하여 사용하였다. 예측정보 기반의 방법들로는 대상지역의 강수량 예측을 위해서 대상 지역 상공의 계절예측 강수자료를 보정을 통해 직접적으로 사용하는 SBC (Simple Bias Correction) 방법과 대상 지역 상공의 강수 예측자료를 사용하는 대신에 지역 강수량과 높은 상관 관계를 보이는 다른 지역의 대리변수를 예측인자로 사용하는 MWR (Moving Window Regression) 방법이 있다. 또한 예측자료의 사용 없이 과거자료 기반의 기후지수(Climate Index) 중에서 지체시간을 고려하여 지역 강수량과 높은 상관관계를 갖는 경우 예측에 활용하는 관측자료 기반의 CIR (Climate Index Regression) 방법과 예측기반 MWR과 관측기반의 CIR 방법에서 선정된 예측인자를 동시에 활용하는 ITR (Integrated Time Regression) 방법이 사용되었다. 장기 강수량 예측은 보르네오 섬의 4개 지역에서 3개월 이하의 선행예측기간에 대하여 0.5 이상의 TCC (Temporal Correlation Coefficient)의 값을 보여 양호한 예측성능을 보였다. 예측된 강수량 자료는 위성기반 관측 강수량 및 관측 탄소 배출량 관계에서 결정된 강수량의 임계값과의 비교를 통해 산불발생 가능성으로 환산하였다. 개발된 조기경보 시스템은 산불 발생에 가장 취약한 해당지역의 건조기(8월~10월) 강수량을 4월부터 예측해 산불 연무에 대한 조기경보를 수행한다. 개발된 화재 연무조기경보 시스템은 지속적인 개선을 통해 현장 실효성을 높여 동남아국가 정부의 화재 및 산림관리자들에게 보급함으로써 동남아의 화재 연무로 인한 환경문제 해결에 기여할 수 있으리라 판단된다.

• Korean Journal of Agricultural and Forest Meteorology
• /
• v.13 no.3
• /
• pp.148-156
• /
• 2011

The purpose of this study is to analyze the patterns of forest fire possibly related with Asian dust event and carry out a correlation analysis between forest fire occurrence and existence or not of the Asian dust event during dry seasons i.e. February to May in 2000 to 2008. To study the correlation of forest fire and Asian dust, we surveyed information of Asian dust observations, forest fire statistics, fire danger rating index, weather data such as temperature, relative humidity and wind speed of the day occurring the forest fire. As a consequence of analysis, the regional frequency of Asian dust was the highest in Gyeonggi and Chungbuk divisions. Frequencies of forest fire occurrence by the Asian dust events were the highest in the day before three days of the Asian dust event. The highest frequent regions of forest fire occurrence were district of boundary line between Gyeonggi and Western of Gangwon, Chungbuk and Gyeonbuk inland. The correlation between forest fire and fire danger rating index showed the high correlation with the day before three days and after three days of the Asian dust event. These correlation coefficients were 0.50038 and 0.53978 to 1% significance level. The result of analysis between the frequency of forest fire occurrence and wind speed had a highly negative relationship at all the Asian dust days, the day before and after three days. The correlation coefficients had been -0.58623 to -0.61245 to 1% significance level. Relative humidity showed a little of negative relationship with forest fire occurrence in -0.2568(p ${\leq}$ 0.01) for the Asian dust day and -0.35309(p ${\leq}$ 0.01) for next three days. Moreover, at the day before three days of Asian dust events, it was -0.23701 to 1% significance level. However, the mean temperature did not correlate with frequency of forest fire occurrence by Asian dust events at all.

• The Journal of Bigdata
• /
• v.3 no.2
• /
• pp.71-78
• /
• 2018

The study is based on machine learning techniques to increase the accuracy of the forest fire predictive model. It used 14 years of data from 2003 to 2016 in Gang-won-do where forest fire were the most frequent. To reduce weather data errors, Gang-won-do was divided into nine areas and weather data from each region was used. However, dividing the forest fire forecast model into nine zones would make a large difference between the date of occurrence and the date of not occurring. Imbalance issues can degrade model performance. To address this, several sampling methods were applied. To increase the accuracy of the model, five indices in the Canadian Frost Fire Weather Index (FWI) were used as derived variable. The modeling method used statistical methods for logistic regression and machine learning methods for random forest and xgboost. The selection criteria for each zone's final model were set in consideration of accuracy, sensitivity and specificity, and the prediction of the nine zones resulted in 80 of the 104 fires that occurred, and 7426 of the 9758 non-fires. Overall accuracy was 76.1%.

• Journal of the Society of Disaster Information
• /
• v.16 no.4
• /
• pp.691-700
• /
• 2020

Purpose, Methoud: In this study, a survey was conducted on elementary school students in the region of Youngdong, Gangwon Province, to find out their awareness about their forest fire disaster experiences, the occurrence of forest fire, forest fire disaster education and coping behaviors for it. It's meant to provide some information on forest fire education based on the results of the survey. Four research questions were posed: 1. What is the awareness of elementary school students on their own forest fire disaster experiences? 2. What is their awareness on the occurrence of forest fire disaster? 3. What is their awareness on forest fire disaster education? 4. What is their awareness on coping behaviors for it? Result: The findings of the study were as follows: First, as for awareness on forest fire disaster experiences, 95.8 percent of the students that accounted for the majority knew about the meaning of forest fire. The students who knew about the meaning of disaster represented 80.8 percent. Second, as for awareness on the occurrence of forest fire, 35.8 percent thought forest fire broke out the most in summer. The students who had never seen forest fire in person accounted for 79.2 percent, which were the majority. Concerning the route of being aware of forest fire, the largest number of the students learned about it from TV, followed by families, friends, teachers, radio/schools and textbooks. Third, as for learning experiences on forest fire disaster, the students who had received this education accounted for 83.3 percent, which were the majority. This education was mostly provided by schools, and the second most common educational place was fire stations. Fourth, as for coping behaviors for the occurrence of forest fire, 80.5 percent replied they would dial the 119 emergency center, and the second most dominant answer was going up to the mountaintop, followed by quickly coming down to go home and having no idea. Conclusion: Through this study, It is judged that education on forest fire disasters and production of educational materials should be consistent and continuous education should be conducted.

• Journal of Korean Society of Forest Science
• /
• v.101 no.1
• /
• pp.1-6
• /
• 2012

To achieve the forest fire management goals such as early detection and quick suppression, fire resources should be allocated at high probability area where forest fires occur. The objective of this study was to develop and validate models to estimate spatially distributed probabilities of occurrence of forest fire. The models were builded by exploring relationships between fire ignition location and forest, terrain and anthropogenic factors using logistic regression. Distance to forest, cemetery, fire history, forest type, elevation, slope were chosen as the significant factors to the model. The model constructed had a good fit and classification accuracy of the model was 63%. This model and map can support the allocation optimization of forest fire resources and increase effectiveness in fire prevention and planning.

• Proceedings of the Korea Society for Simulation Conference
• /
• 1998.10a
• /
• pp.51-56
• /
• 1998

본 연구는 산림, 기상, 지형, 소방 정보 등을 토대로 최적의 산불 진화 전략 수립을 위한 산불 진화 전문가 시스템의 설계 방법론 제시를 주목적으로 한다. 기존의 산불 정보 시스템들은 GIS 데이터와 기상 관련 데이터, 산불 발생 지점에 대한 지형 데이터를 이용하여, 산불 확산에 따른 피해 정도 및 확산 범위에 예측을 목표로 접근하고 있다. 그러나, 이를 활용하여 최적의 진화 전략을 생성시킬 수 있는 연구는 아직까지 제시된 바가 없다. 따라서 본 연구에서는 기존의 산불 정보 시스템을 기반으로 이산 사건 모델링 및 시뮬레이션 기법, 규칙기반 SES (RUSES: Rule-based System Entity Structure), 그리고 유전 알고리즘 등을 이용하여 최적의 산분 진화 전략을 생성할 수 있는 산불 진화 전문가 시스템의 설계 방법론을 제안한다.

• Journal of Korea Water Resources Association
• /
• v.54 no.3
• /
• pp.145-156
• /
• 2021

Forest fires have frequently occurred around the world, and the damages are increasing. In Korea, most forest fires are initiated by human activities, but climate factors such as temperature, humidity, and wind speed have a great impact on combustion environment of forest fires. In this study, therefore, based on statistics of forest fires in Gyeonggi-do over the past five years, meteorological and hydrological factors (i.e., temperature, humidity, wind speed, precipitation, and drought) were selected in order to quantitatively investigate causal relationships with forest fire. We applied a partial least squares structural equation model (PLS-SEM), which is suitable for analyzing causality and predicting latent variables. The overall results indicated that the measurement and structural models of the PLS-SEM were statistically significant for all evaluation criteria, and meteorological factors such as humidity, temperature, and wind speed affected by amount of -0.42, 0.23 and 0.15 of standardized path coefficient, respectively, on forest fires, whereas hydrological factor such as drought had an effect of 0.23 on forest fires. Therefore, as a practical method, the suggested model can be used for analyzing and evaluating influencing factors of forest fire and also for planning response and preparation of forest fire disasters.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2021.05a
• /
• pp.104-107
• /
• 2021

전 세계적으로 건조한 지역이 늘어남에 따라 산불 발생 빈도가 증가하고 있다. 이에 대한 대안으로 센서를 이용한 산불 감지 시스템의 연구가 이루어지고 있다. 기존의 서버가 센서의 작동시간 설정값을 보내는 방식은 산불 발생 빈도가 높은 환경에서는 산불 감지가 늦어지고 산불 발생 빈도가 낮은 환경에서는 불필요한 산불 감지로 센서의 생명주기 낮아지는 비효율적인 면이 있다. 이에 본 논문에서는 센서 기반 산불 감지 시스템을 위한 향상된 센싱 주기 기법을 제안한다. 제안하는 센싱 주기 기법은 환경 요인, 센서의 작동시간 알고리즘을 이용하여 환경에 맞는 센서의 작동시간 설정값을 결정한다. 그 후 센서의 화재 감지 알고리즘을 통해 센서는 서버로부터 설정값을 받아 운용모드로 전환하여 화재상황이 났을 시에 서버로 메세지를 보낸 후 생명주기를 위해 저전력모드로 전환한다. 성능평가를 통해 기존의 방식보다 평균 18.1분 빠르게 화재상황을 감지할 수 있고 소모전력도 2.2mA만큼 낮았다. 향우 실제 화재환경에서의 성능평가가 필요하다.