• Journal of the Society of Disaster Information
• /
• v.16 no.3
• /
• pp.430-439
• /
• 2020

Purpose: As the frequency of impact typhoons increases and the form of damage becomes more complicated, the need for information to help disaster response workers recognize the typhoon situation in advance is growing. In this study, Definitions and implementation measures for information utilized at each stage of the task were proposed in carrying out typhoon response tasks that occur every year. Method: In 2019, the government classified information that was used for each step of work and conducted analysis on necessary information for the situation. Based on the analyzed information, typhoon status information was established through an opinion survey by central and local government officer. Result: The task of typhoon situations was the most important part of monitoring weather conditions and sharing damage situations, and the information utilized was analyzed to require information derived through the convergence of historical and situation information. Conclusion: As the correlation between work and information between the response departments increases as the typhoon situation progresses, information about typhoon situation should be applied to the actual typhoon situation in the future to enhance information and establish a related system.

• Korean Journal of Artificial Intelligence
• /
• v.10 no.1
• /
• pp.1-7
• /
• 2022

In this paper, a study was conducted to predict natural disasters in Afghanistan based on machine learning. Natural disasters need to be prepared not only in Korea but also in other vulnerable countries. Every year in Afghanistan, natural disasters(snow, earthquake, drought, flood) cause property and casualties. We decided to conduct research on this phenomenon because we thought that the damage would be small if we were to prepare for it. The Azure Machine Learning Studio used in the study has the advantage of being more visible and easier to use than other Machine Learning tools. Decision Forest is a model for classifying into decision tree types. Decision forest enables intuitive analysis as a model that is easy to analyze results and presents key variables and separation criteria. Also, since it is a nonparametric model, it is free to assume (normality, independence, equal dispersion) required by the statistical model. Finally, linear/non-linear relationships can be searched considering interactions between variables. Therefore, the study used decision forest. The study found that overall accuracy was 89 percent and average accuracy was 97 percent. Although the results of the experiment showed a little high accuracy, items with low natural disaster frequency were less accurate due to lack of learning. By learning and complementing more data, overall accuracy can be improved, and damage can be reduced by predicting natural disasters.

• Journal of the Society of Disaster Information
• /
• v.10 no.3
• /
• pp.366-372
• /
• 2014

As the disaster becomes bigger and more complicated and causes massive damage in the society, it becomes important to educate and exercise the people for the disaster response and safety. In this study, the effect of the disaster and safety education on the disaster risk assessment was evaluated. Disaster risk was calculated by the likelihood and consequences. The expert survey was used to evaluate the effect of the education on the likelihood and consequences. The inquiries were divided by the education target which makes different results of the survey. As a result, the disaster risk was reduced upto almost 48% when all people including the government workers and students were educated regularly. The result needs to be verified by the field data analysis. However, it provides the reason why the disaster and safety education is important.

• Journal of the Society of Disaster Information
• /
• v.13 no.4
• /
• pp.511-518
• /
• 2017

In this study, a research on disaster countermeasures to strengthen the disaster management field of rural areas. The purpose of this study is to investigate the measures to cope with the disaster in order to enhance the rural disaster management capacity. For this purpose, social and environmental characteristics of the rural area were examined and the characteristics of rural disaster perspective were derived. As for social characteristics, we analyzed the direct and indirect damage of disaster through interviews with residents affected by disaster. In the case of environmental characteristics, the factors that threaten the safety in the rural area were extracted based on the geographical and geographical characteristics of the rural area and quantitative analysis of the difference of the disaster response infrastructure compared with the city was conducted. In addition, it is necessary to further study the priority of disaster prevention in order to apply the disaster prevention method to rural areas.

• Journal of the Korean Institute of Educational Facilities
• /
• v.13 no.4
• /
• pp.31-42
• /
• 2006

This study is about an analysis of the relation between the degree of cognition of student's acts within limits when coping with several types of disaster and the degree of cognition of damage by disasters in the method of multiple regression analysis. The dependent variable is the degree of cognition of student's acts within limits and the independent variable is the degree of cognition of damage by disasters such as heavy snow, typhoon, heavy rain, heat, and yellow sand. A survey of graduates of metropolitan area high-schools has found that there are no difference between girls and boys of the degree of cognition of student's acts within limits when coping with disasters. This study finds that the independent variable, which are playgrounds, animals and plants, streets and roads, altitude and incline, gives positive effect to the degree of cognition of student's acts within limits when coping with typhoon or heavy rain in order. The study also finds that the degree of cognition of student's acts within limits when coping with heavy snow is affected positively by streets and roads, playgrounds, altitude and incline in order. It also shows that there are factors that has an effect to the degree of cognition of student's acts within limits when coping with yellow sand and heat. This study proposes suggestions to facility plans based on these facts discovered.

• Journal of Korean Society for Geospatial Information Science
• /
• v.20 no.4
• /
• pp.135-143
• /
• 2012

Remote sensing which observes repeatedly the whole Earth and GIS-based decision-making technology have been utilized widely in disaster management such as early warning monitoring, damage investigation, emergent rescue and response, rapid recovery etc. In addition, various countermeasures of national level to collect timely satellite imagery in emergency have been considered through the operation of a satellite with onboard multiple sensors as well as the practical joint use of satellite imagery by collaboration with space agencies of the world. In order to respond heavy snowfall disaster occurred on the east coast of the Korean Peninsula in February 2011, snow-covered regions were analyzed and detected in this study through NDSI(Normalized Difference Snow Index) considering reflectance of wavelength for MODIS sensor and change detection algorithm using satellite imagery collected from International Charter. We present the application case of National Disaster Management Institute(NDMI) which supported timely decision-making through GIS spatial analysis with various spatial data and snow cover map.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.21 no.9
• /
• pp.238-250
• /
• 2020

This study investigated the long-term measures to minimize flood damage in the event of flooding in urban areas. The relationship between urban spatial factors and the impact of flood damage was analyzed, focusing on non-structural measures. The urban spatial factors were categorized into three parts: open space, disaster prevention facilities, and urbanization sectors. Multiple regression analysis was used to investigate how urban spatial factors influence flood damage. As a result of the analysis, the crucial factors, such as the reduced green areas and parks included in the open space sectors, resulted in an increased flood damage potential. The posterior factors, such as the population density and GRDP included in the urbanization sector concurrently led to an increase in the flood damage potential. Therefore, to better adapt to climate change, it is necessary to establish urban spatial plans strategically, such as green areas and parks. Meanwhile, the population density and GRDP are also the main factors causing flood damage. Therefore, when used appropriately in terms of resilience, it will serve as adaptations and recovery.

• Journal of Korean Society of Disaster and Security
• /
• v.14 no.2
• /
• pp.43-50
• /
• 2021

In Korea, the frequency of soil disasters has soared recently due to increased torrential rains caused by abnormal weather conditions. In particular, soil generated from mountainous areas is flowing into small rivers along valleys, depositing rivers and adding to flood damage. In order to prevent damage from such soil disasters, it is important to predict sediments and to quantitatively identify bed load. In this work, we conducted an experiment to indirectly measure acoustic sensor-based bed load collision sounds using pipe hydrophones, and compared them with raw data by applying denoising methods to improve the reliability of the measured data. As a result, we derive results in a more clear analysis of bed load estimation by correcting noise when the denoising method is applied to raw data.

• Journal of Ocean Engineering and Technology
• /
• v.18 no.2
• /
• pp.25-32
• /
• 2004

We surveyed the coastal structure damage created by typhoon ‘Maemi’, which heavily struck the Korean peninsula on September 12, 2003. The survey revealed that high tides and strong winds induced by the typhoon were the main causes of the coastal damage, especially in the Busan areas. Though some experimental real-time coastal monitoring stations captured the typhoon movements at the critical time, more systematic and complete system should be implemented to save human lives and property from huge typhoon disasters.

• 한국신재생에너지학회:학술대회논문집
• /
• 2009.06a
• /
• pp.561-564
• /
• 2009

In order to reduce damage from natural disasters, prevention activities through analysis and predicting based on meteorological factor and damage data is required. Other countries already have continuously studied on natural disasters and developed reducing disasters damage. But the risk assessment model for natural disaster is not to Korea. Therefore, a previous model of hurricane, Florida Public Hurricane Loss Model(FPHLM), is the basis and is applying to domestic situation. Accordingly, this study introduces the variables selecting process because input variables should be selected under Korea present state and be used. The estimating representative damage method would be necessary along with selecting housing types representing relevant areas because estimating damage amount of all over relevant areas housing was very hard during damage estimating process. But there is no exact representative housing types in the Korea. Therefore, we select housing types applicable to risk assessment model for natural disasters representing the Korea through previous studies and literature reviews. We using ASCE 7-98(Minimum Design Loads for Buildings and Other Structures, 1998) standard which estimated wind load using 3-second gust. ASCE 7-98 divided Main Wind Force Resistance System(MWFRS) and Component and Cladding(C&C) and it estimated wind load. Therefore, we estimate wind load affected by 3-second gust of a typhoon Maemi through calculating wind load process using selected representative detached house types in the process of selecting input variables for previous disaster predict model. The result of houses damage amount is about 230 hundred million won. This values are limit the 1-story detached dwelling, 19~29pyeong(62.81~95.56 $m^2$) of total area and flat roof. Therefore, this process is possible application to other type houses.