• Korean Journal of Remote Sensing
• /
• v.38 no.3
• /
• pp.265-282
• /
• 2022

Sea surface temperature (SST) is a factor that greatly influences ocean circulation and ecosystems in the Earth system. As global warming causes changes in the SST near the Korean Peninsula, abnormal water temperature phenomena (high water temperature, low water temperature) occurs, causing continuous damage to the marine ecosystem and the fishery industry. Therefore, this study proposes a methodology to predict the SST near the Korean Peninsula and prevent damage by predicting abnormal water temperature phenomena. The study area was set near the Korean Peninsula, and ERA5 data from the European Center for Medium-Range Weather Forecasts (ECMWF) was used to utilize SST data at the same time period. As a research method, Long Short-Term Memory (LSTM) algorithm specialized for time series data prediction among deep learning models was used in consideration of the time series characteristics of SST data. The prediction model predicts the SST near the Korean Peninsula after 1- to 7-days and predicts the high water temperature or low water temperature phenomenon. To evaluate the accuracy of SST prediction, Coefficient of determination (R²), Root Mean Squared Error (RMSE), and Mean Absolute Percentage Error (MAPE) indicators were used. The summer (JAS) 1-day prediction result of the prediction model, R²=0.996, RMSE=0.119℃, MAPE=0.352% and the winter (JFM) 1-day prediction result is R²=0.999, RMSE=0.063℃, MAPE=0.646%. Using the predicted SST, the accuracy of abnormal sea surface temperature prediction was evaluated with an F1 Score (F1 Score=0.98 for high water temperature prediction in summer (2021/08/05), F1 Score=1.0 for low water temperature prediction in winter (2021/02/19)). As the prediction period increased, the prediction model showed a tendency to underestimate the SST, which also reduced the accuracy of the abnormal water temperature prediction. Therefore, it is judged that it is necessary to analyze the cause of underestimation of the predictive model in the future and study to improve the prediction accuracy.

• Journal of Korea Water Resources Association
• /
• v.49 no.2
• /
• pp.155-164
• /
• 2016

Algal blooms not only destroy fish habitats but also diminish biological diversity of ecosystem which results into water quality deterioration of 4 major rivers in South Korea. The relationship between algal bloom and environmental factors had been analyzed through the cross-correlation function between concentration of chlorophyll a and other environmental factors. However, time series of cross-correlations can be affected by the stochastic structure such auto-correlated feature of other controllers. In order to remove external effect in the correlation analysis, the pre-whitening procedure was implemented into the cross correlation analysis. The modeling process is consisted of a series of procedure (e.g., model identification, parameter estimation, and diagnostic checking of selected models). This study provides the exclusive correlation relationship between algae concentration and other environmental factors. The difference between the conventional correlation using raw data and that of pre-whitened series was discussed. The process implemented in this paper is useful not only to identify exclusive environmental variables to model Chl-a concentration but also in further extensive application to configure causality in the environment.

• Proceedings of the Korea Water Resources Association Conference
• /
• 2016.05a
• /
• pp.323-323
• /
• 2016

최근 강우강도 등의 기후변화로 인한 표토침식량이 증가하고 있고, 이에 따른 사회적 환경적 문제가 부각되고 있다. 특히 표토는 인류에게 식량생산의 기반이 되고, 정주공간을 제공할 뿐만 아니라 에너지 생산, 수자원 함양, 기후변화 대응, 생물 다양성 유지, 생태계의 건전성, 자원함양 및 순환, 오염물질 정화 등 소중한 생명자원이다. 이에 환경부에서는 2012월 12월 표토의 침식현황에 관한 고시를 제정하고, 표토 유실 대책 방안을 수립하기 위한 노력을 기울이고 있다. 이에 자원으로서의 표토를 보전하기 위한 단기적 관점의 대책 수립을 위한 웹GIS 기반 단일 강우에 의한 표토침식량을 예측하는 시스템을 개발하였다. 본 연구는 크게 표토침식 예측 모듈 개발과 정확성 평가를 위한 시험포 단위 모니터링 그리고 모듈을 적용한 웹GIS 시스템 개발, 시범적용을 위한 강원도 홍천군 자운리 DB 구축으로 구분된다. 표토침식예측 모듈의 정확성을 검증하기 위하여 가로 4m ${\times}$ 세로 22m, 경사도 3%, 9% 시험포 2개를 조성, 2015년 5월 11일부터 2015년 11월 23일까지 강우량, 유출량, 표토침식량을 조사하였으며, 웹 GIS 시스템은 Open Source Software인 Geoserver, PostGIS, OpenLayers를 활용하여 개발하였다. 마지막으로 개발된 웹GIS 표토침식예측시스템의 시범적용을 위하여 강원도 홍천군 자운리의 농경지 경계, 경사도, 경사장, 작물특성 등에 대한 GIS DB를 구축하였다. 시험포 모니터링 결과 강우발생일수는 총 64일로 관측되었고, 이중 유출은 총 30회가 발생되었다. 이 결과를 활용하여 표토침식 예측 모듈을 검증한 결과 3 % 시험포의 유출량 NSE : 0.88, $R^2$ : 0.91, 표토침식량 NSE : 0.87, $R^2$ : 0.90, 9 % 시험포의 유출량 NSE : 0.76, $R^2$ : 0.82, 표토 침식량 NSE : 0.82, $R^2$ : 0.88로 나타났다. 웹GIS 표토침식 예측 시스템은 Layer 정보, 맵, GIS tool, 경작기 정보, 날씨 정보 등으로 구성되어 있으며, 기상청 Open API와 연동하여 당일의 강수량 예보 데이터와 표토침식량 산정 모듈을 이용하여 예측 표토 침식량 데이터를 제공한다. 하루가 지나면 기상청에서 실측한 강수량 데이터를 이용하여 표토 침식량 산정모듈이 자동적으로 수행된 뒤 실측 강우량에 대한 표토침식량 정보가 제공된다 본 연구에서 개발된 웹GIS기반 표토침식 예측 시스템은 시범 대상 유역인 강원도 홍천군 자운리 유역을 대상으로 구축되었으며, 지속적으로 대상유역을 확대할 계획이다.

• Korean Journal of Remote Sensing
• /
• v.38 no.3
• /
• pp.299-309
• /
• 2022

Recently, The sea water temperature around Korean Peninsula is steadily increasing. Water temperature changes not only affect the fishing ecosystem, but also are closely related to military operations in the sea. The purpose of this study is to suggest which model is more suitable for the field of water temperature prediction by attempting short-term water temperature prediction through various prediction models based on deep learning technology. The data used for prediction are water temperature data from the East Sea (Goseong, Yangyang, Gangneung, and Yeongdeok) from 2016 to 2020, which were observed through marine observation by the National Fisheries Research Institute. In addition, we use Long Short-Term Memory (LSTM), Bidirectional LSTM, and Gated Recurrent Unit (GRU) techniques that show excellent performance in predicting time series data as models for prediction. While the previous study used only LSTM, in this study, the prediction accuracy of each technique and the performance time were compared by applying various techniques in addition to LSTM. As a result of the study, it was confirmed that Bidirectional LSTM and GRU techniques had the least error between actual and predicted values at all observation points based on 1 hour prediction, and GRU was the fastest in learning time. Through this, it was confirmed that a method using Bidirectional LSTM was required for water temperature prediction to improve accuracy while reducing prediction errors. In areas that require real-time prediction in addition to accuracy, such as anti-submarine operations, it is judged that the method of using the GRU technique will be more appropriate.

• Korean Association of Arts Management
• /
• no.58
• /
• pp.205-239
• /
• 2021

This study explores the importance of semantic web-based network construction in art data archiving, as well as its meaning and value in the context of arts management along with its potential for future application. The study focuses on oral history obtained from the Arko Arts Archives that contained records of the lives and artistic views of early artists. In this study, the possibility of applying semantic web-based technology to materials concerning culture and the arts was discussed in five aspects based on the results of the case analysis. First, checking the relationship and discovering hidden artists are possible by revealing relationships between characters. Second, understanding and studying society and culture at a given time is possible by interpreting the contextual meaning of information. Third, art exploration can be done broadly and deeply, encompassing various genres from the perspective of the consumer. Fourth, through art construction, history can be reconstructed using a new and rich method. Fifth, expanding the scope beyond the boundaries of art is possible through convergence and collaboration of programs that handle big data. The network data can be used in various methods, such as art history research, art planning, and creation, throughout the art ecosystem. The results of the study suggest that digitizing a large quantity of data concerning culture and the arts is meaningful in arts management as well as identifying and analyzing the relationship network among data clusters using semantic web-based technology.

• Journal of Platform Technology
• /
• v.11 no.4
• /
• pp.19-34
• /
• 2023

In order to identify the trends and insights of 'startups' in the global era, we conducted an in-depth trend analysis of the global startup ecosystem using Google Trends, a big data analysis platform. For the validity of the analysis, we verified the correlation between the keywords 'startup' and 'global' through BIGKinds. We also conducted a network analysis based on the data extracted using Google Trends to determine the frequency of searches for the keyword or term 'startup'. The results showed a strong positive linear relationship between the keywords, indicating a statistically significant correlation (correlation coefficient: +0.8906). When exploring global startup trends using Google Trends, we found a terribly similar linear pattern of increasing and decreasing interest in each country over time, as shown in Figure 4. In particular, startup interest was low in the range of 35 to 76 from mid-2020 due to the COVID-19 pandemic, but there was a noticeable upward trend in startup interest after March 2022. In addition, we found that the interest in startups in each country except South Korea is very similar, and the related topics are startup company, technology, investment, funding, and keyword search terms such as best startup, tech, business, invest, health, and fintech are highly correlated.

• The Journal of the Convergence on Culture Technology
• /
• v.9 no.3
• /
• pp.167-181
• /
• 2023

This study utilized TEXTOM, a social network analysis program to analyze changes in current tourism behavior after travel restrictions were eased after the outbreak of COVID-19. Data on the keywords 'domestic travel' and 'overseas travel' were collected from blogs, cafes, and news provided by Naver, Google, and Daum. The collection period was set from April to December 2022 when social distancing was lifted, and 2019 and 2020 were each set as one year and compared and analyzed with 2022. A total of 80 key words were extracted through text mining and centrality analysis was performed using NetDraw. Finally, through the CONCOR, the correlated keywords were clustered into 4. As a result of the study, tourism behavior in 2022 shows tourism recovery before the outbreak of COVID-19, segmentation of travel based on each person's preferred theme, prioritization of each country's corona mitigation policy, and then selecting a tourist destination. It is expected to provide basic data for the development of tourism marketing strategies and tourism products for the newly emerging tourism ecosystem after COVID-19.

• Korean Journal of Agricultural and Forest Meteorology
• /
• v.8 no.2
• /
• pp.86-96
• /
• 2006

Ecoclimap-1, a new complete surface parameter global database at a 1-km resolution, was previously presented. It is intended to be used to initialize the soil-vegetation- atmosphere transfer schemes in meteorological and climate models. Surface parameters in the Ecoclimap-1 database are provided in the form of a per-class value by an ecoclimatic base map from a simple merging of land cover and climate maps. The principal objective of this ecoclimatic map is to consider intra-class variability of life cycle that the usual land cover map cannot describe. Although the ecoclimatic map considering land cover and climate is used, the intra-class variability was still too high inside some classes. In this study, a new strategy is defined; the idea is to use the information contained in S10 NDVI SPOT/VEGETATION profiles to split a land cover into more homogeneous sub-classes. This utilizes an intra-class unsupervised sub-clustering methodology instead of simple merging. This study was performed to provide a new ecolimatic map over Northeast Asia in the framework of Ecoclimap-2 global database construction for surface parameters. We used the University of Maryland's 1km Global Land Cover Database (UMD) and a climate map to determine the initial number of clusters for intra-class sub-clustering. An unsupervised classification process using six years of NDVI profiles allows the discrimination of different behavior for each land cover class. We checked the spatial coherence of the classes and, if necessary, carried out an aggregation step of the clusters having a similar NDVI time series profile. From the mapping system, 29 ecosystems resulted for the study area. In terms of climate-related studies, this new ecosystem map may be useful as a base map to construct an Ecoclimap-2 database and to improve the surface climatology quality in the climate model.

• Journal of the Korean association of regional geographers
• /
• v.15 no.3
• /
• pp.421-433
• /
• 2009

The impervious ratio was frequently employed as a fundamental attribute will be used as a proxy of the total environmental burden in the urban area since it may contribute as much or more on a cumulative basis to the overall environmental condition. This research proposes a comparative evaluation framework in a more objective and Quantitative way for an impervious ratio in the university campus, using the Google Earth. Two university campuses (Kyungpook National University: KNU, Hong Kong University: HKUJ were selected as survey objectives in order to evaluate the potential of Google Earth in monitoring impervious conditions in the campus. The 61cm resolution of Quickbird data combined with digital map realistically identified the major type of impervious surface such as road, building and parking lots in the study area by large scale spatial precision. The impervious zones with persistently high road density and parking space were specifically identified over the KNU campus while the HKC campus was intensively covered by tree, resulting in almost twice (31%). as compared to KNU (18.4%), The methods of characterizing impervious surface used in this study are easily replicable using data that are primarily publicly available, and therefore the collection of impervious coverage data via Google Earth is, therefore, proposed as a practical alternative.

• Journal of Software Engineering Society
• /
• v.28 no.2
• /
• pp.1-6
• /
• 2019

There are various stakeholders in the blockchain ecosystem. Since the emergence of Ethereum, many transactions have been made using smart contracts, and a wider range of stakeholders are participating, including not only developers, but also investors, banks, companies, and general users. However, various stakeholders have a problem in that it is difficult and complicated to check the state of smart contracts. If it becomes difficult to check the state, the reliability of the smart contract will be lowered and the utilization will be lowered. Also, if the state check is difficult and complicated for the developer, it will be difficult to provide high quality due to the difficulty of testing and debugging the smart contract developed by the developer. In this research, we propose a design and implementation method of the Ethereum Smart Contract State Monitoring System that enables various stakeholders and developers to easily and continuously check the state of smart contracts and analyze them using historical data.