• Journal of the Korea Society of Computer and Information
• /
• v.28 no.11
• /
• pp.13-20
• /
• 2023

In this paper, we propose a water temperature prediction method using feature extraction and reconstructed data based on LSTM-Autoencoder. We used multivariate time series data such as sea surface water temperature in the Naksan area of the East Sea where the cold water zone phenomenon occurred, and wind direction and wind speed that affect water temperature. Using the LSTM-Autoencoder model, we used three types of data: feature data extracted through dimensionality reduction of the original data combined with multivariate data of the original data, reconstructed data, and original data. The three types of data were trained by the LSTM model to predict sea surface water temperature and evaluated the accuracy. As a result, the sea surface water temperature prediction accuracy using feature extraction of LSTM-Autoencoder confirmed the best performance with MAE 0.3652, RMSE 0.5604, MAPE 3.309%. The result of this study are expected to be able to prevent damage from natural disasters by improving the prediction accuracy of sea surface temperature changes rapidly such as the cold water zone.

• Korean journal of communication and information
• /
• v.70
• /
• pp.246-276
• /
• 2015

From a historical perspective of risk communication, risks can be classified by their associated level of responsibility. In the case of technical risks such as hazardous chemical accidents, people perceive that risk-related organizations have a high level of responsibility; however, they do not in traditional risks such as natural disasters. This study aims to examine risk information seeking and processing, as seen in two types of risk, based on the Risk Information Seeking and Processing(RISP) model. For this purpose, hypotheses and a research question are developed with current domestic risk issues, and the results show significant differences in risk information seeking and processing between the two types of risk. Specifically, in the case of the chemical spill accident, negative emotion against relevant institutions makes different information seeking and processing compared to the natural disaster. The low level responsibility risk such as typhoon comparatively follows the flow of the original RISP model. However, the high level responsibility risk such as the hydrofluoric acid spill did not match with the RISP model. Based on the research results, theoretical implications were discussed.

• Journal of The Geomorphological Association of Korea
• /
• v.20 no.1
• /
• pp.85-96
• /
• 2013

This study collected national secondary and tertiary nationwide natural environment survey data of the National Institute of Environmental Research as well as the National Park's secondary and tertiary natural resource research data executed by the Korea National Park Service. The data collection is aimed at reclassification the geomorphological landscape resources of each park in varying types. The results generated a total of 3,169 geomorphological landscape resources within all the national parks. Among all the geomorphological landscape resources, 794 landscape resources were judged as Level I, which accounts for 36.9%. Next, 546 landscape resources were judged as Level II, or 25.3%, and 459 landscape resources judged as Level III, or 21.3%. Lastly, 191 landscape resources were judged as Level IV, having the lowest conservation level, or 8.9%. The number of Level I landscape resources for each national park includes 207 sites on Seoraksan, 92 sites on Dadohaehaesang Park, 84 sites on Jirisan, and 60 sites at the Taeanhaean, respectively. Dadohaehaesang National Park, Seoraksan National Park, Taeanhaean National Park, Jirisan National Park, Songnisan National Park, and Gyeryongsan National Park were evaluated as national parks having excellent landscape resources. To use these excellent landscape resources, there is a need to increase visitors' satisfaction and increase their interest in and understanding of landscape resources. To achieve this, a landscape viewpoint map must be composed and installed at the entrance or at certain points to provide visitors with useful information regarding the geomorphological landscape resources.

• Journal of Korean Society of Disaster and Security
• /
• v.6 no.3
• /
• pp.9-17
• /
• 2013

Geospatial information data came recently in use to build the location-based service in various fields. These data were shown via a 2-D map in the past but now can be viewed as a 3-D map due to the dramatic evolution of IT technology, thus improving efficiency and raising practicality to a greater extent by providing a more realistic visualization of the field. In addition, many previous GIS applications have been provided under desktop environment, limiting access from remote sites and reducing its approachability for less experienced users. The latest trend offers service with web-based environment, providing efficient sharing of data to all users, both unknown and specific internal users. Therefore, real-time information sensors that have been installed on steep slopes are to be integrated with 3-D geospatial information in this study. It is also to be developed with web-based environment to improve usage and access. There are three steps taken to establish this system: firstly, a 3-D GIS database and 3-D terrain with higher resolution aerial photos and DEM (Digital Elevation Model) have been built; secondly, a system architecture was proposed to integrate real-time sensor information data with 3D Web-based GIS; thirdly, the system has been constructed for Gangwon Province as a test bed to verify the applicability.

• Korean Journal of Remote Sensing
• /
• v.39 no.5_4
• /
• pp.1075-1084
• /
• 2023

Satellite-derived data is collected by observing the Earth and is used in various fields such as national defense, natural disasters, location-based services, infrastructure, environment, energy, marine, and insurance. This study aims to present the virtuous cycle structure of the satellite information data industry and the business ecosystem model of the industry. As a research method, cases were collected and categorized from the following areas: literature, online, application, and content. The results show that the ecosystem model of the satellite information data industry provides an approach to content services in public and commercial areas, and develops various algorithmic technologies to facilitate content production and services at the level of complex general-purpose technologies. Second, in terms of content typology, satellite information data can be subdivided into monitoring content, urban space monitoring content, and satellite information content. Third, the consumption value of satellite content could be subdivided into informational value, environmental, social and governance (ESG) value, educational value, and content value. In order to expand the global content market, Korea will need to focus on creating an ecosystem for the satellite information industry and discovering differentiated content. It will also need to increase the popularization and accessibility of data to the general public and promote the Korean K-Satellite Information Data Industry ecosystem through government support, policy efforts, and policies such as establishing legal systems, increasing investment, and training human resources.

• Journal of Korea Water Resources Association
• /
• v.57 no.8
• /
• pp.509-518
• /
• 2024

Flash drought is a rapid-onset drought that occurs rapidly over a short period due to abrupt changes in meteorological and environmental factors. In this study, we utilized satellite-based soil moisture product from the Advanced Microwave Scanning Radiometer-2(AMSR2) ascending X-band to calculate the weekly Flash Drought Intensity Index (FDII). We also analyzed the characteristics of flash droughts on the Korean Peninsula over a 10-year period from 2013 to 2022. The analysis of monthly spatial distribution patterns of the irrigation period across the Korean Peninsula revealed significant variations. In North Korea (NK), a substantial increase in the rate of intensification (FD_INT) was observed due to the rapid depletion of soil moisture, whereas South Korea (SK) experienced a significant increase in drought severity (DRO_SEV). Additionally, regional time series analysis revealed that both FD_INT and DRO_SEV were significantly high in the Gangwon province of both NK and SK. The estimation of probability density by region revealed a clear difference in FD_INT between NK and SK, with SK showing a higher probability of severe drought occurrence primarily due to the high values of DRO_SEV. As a result, it is inferred that the occurrence frequency and damage of flash droughts in NK are higher than those in SK, as indicated by the higher density of large FDII values in the NK region. We analyzed the correlation between DRO_SEV and the Evaporative Stress Index (ESI) across the Korean Peninsula and confirmed a positive correlation ranging from 0.4 to 0.6. It is concluded that analyzing overall drought conditions through the average drought severity holds high utility. These findings are expected to contribute to understanding the characteristics of flash droughts on the Korean Peninsula and formulating post-event response plans.

• Journal of the Korean Society of Hazard Mitigation
• /
• v.8 no.5
• /
• pp.71-76
• /
• 2008

The purposes of this study were to examine the coping behavior of the elderly in the warning phase of disaster and to explore factors influencing the coping behavior of the elderly. Data were collected from 130 senior citizens aged over 60 who are residing in Pyungchang and Injae of Kangwon province which had damaged by flood disaster in 2006. Perry & Lindell (1997)'s index, a series of six categories that represent coping behaviors which progressively approximate the action of evacuating in the warning phase of disasters was used. Results showed that respondents have high coping skills. Although Activities of Daily Living (ADL) has positive influence on the coping behavior, length of residence has negative effect on the coping behavior of the elderly. This finding proves the elderly are not uncompliant or uncooperative population in the warning phase of disaster. This result also emphasizes the importance of rapid and accurate giving of public warning system of disaster and necessity of prior notification of useful information about natural disaster and effective evacuation plan for the elderly.

• Journal of the Korean Association of Geographic Information Studies
• /
• v.17 no.3
• /
• pp.104-115
• /
• 2014

A levee is defined as an man-made structure protecting the areas from temporary flooding. This paper suggests a methodology for establishing the levee GIS database using the airborne topographic LiDAR(Light Detection and Ranging) data taken in the Nakdong river basins and the WAMIS(WAter Management Information System) information. First, the National Levee Database(NLD) established by the USACE(United States Army Corps Engineers) and the levee information tables established by the WAMIS are compared and analyzed. For extracting the levee information from the LiDAR data, the DSM(Digital Surface Model) is generated from the LiDAR point clouds by using the interpolation method. Then, the slope map is generated by calculating the maximum rates of elevation difference between each pixel of the DSM and its neighboring pixels. The slope classification method is employed to extract the levee component polygons such as the levee crown polygons and the levee slope polygons from the slope map. Then, the levee information database is established by integrating the attributes extracted from the identified levee crown and slope polygons with the information provided by the WAMIS. Finally, this paper discusses the advantages and limitations of the levee GIS database established by only using the LiDAR data and suggests a future work for improving the quality of the database.

• Korean Journal of Remote Sensing
• /
• v.39 no.5_2
• /
• pp.743-754
• /
• 2023

The global occurrence of myriad natural disasters and incidents, catalyzed by climate change and extreme meteorological conditions, has engendered substantial human and material losses. International organizations such as the International Charter have established an enduring collaborative framework for real-time coordination to provide high-resolution satellite imagery and geospatial information. These resources are instrumental in the management of large-scale disaster scenarios and the expeditious execution of recovery operations. At the national level, the operational deployment of advanced National Earth Observation Satellites, controlled by National Geographic Information Institute, has not only catalyzed the advancement of geospatial data but has also contributed to the provisioning of damage analysis data for significant domestic and international disaster events. This special edition of the National Disaster Management Research Institute delineates the contemporary landscape of major disaster incidents in the year 2023 and elucidates the strategic blueprint of the government's national disaster safety system reform. Additionally, it encapsulates the most recent research accomplishments in the domains of artificial satellite systems, information and communication technology, and spatial information utilization, which are paramount in the institution's disaster situation management and analysis efforts. Furthermore, the publication encompasses the most recent research findings relevant to data collection, processing, and analysis pertaining to disaster cause and damage extent. These findings are especially pertinent to the institute's on-site investigation initiatives and are informed by cutting-edge technologies, including drone-based mapping and LiDAR observation, as evidenced by a case study involving the 2023 landslide damage resulting from concentrated heavy rainfall.

• Journal of Climate Change Research
• /
• v.2 no.1
• /
• pp.43-54
• /
• 2011

Recently, due to severe rainfall by the global climate change, natural disasters such as landslide had also been increased rapidly all over the world. Therefore, it has been very necessary to assess vulnerability of landslide and prepare adaptation measures to future climate change. In this study, we employed sensitivity, exposure and adaptative capacity as criteria for assessing the vulnerability of landslide due to climate change. Spatial database for the criteria was constructed using GIS technology. And vulnerability maps on the entire Korea of past and future were made based on the database. As a result, highly vulnerable area for landslide was detected in most area of Gangwon-do, the east of Gyeonggi-do, and southeast of Jeollanam-do, and the southwest of Gyeongsangnam-do. The result of landslide vulnerability depends on time shows that degree of very low class and low class were decreased and degree of moderate, high, and very high were increase from past to the future. Especially, these three classes above low class were significantly increased in the result of far future.