• Korean Journal of Remote Sensing
• /
• v.38 no.6_1
• /
• pp.1329-1341
• /
• 2022

Destroying the marine environment and marine ecosystem and causing marine accidents, marine debris is generated every year, and among them, submerged marine debris is difficult to identify and collect because it is on the seabed. Therefore, deep-learning-based semantic segmentation was experimented on waste fish nets and waste ropes using underwater images to identify efficient collection and distribution. For segmentation, a high-resolution network (HRNet), a state-of-the-art deep learning technique, was used, and the performance of each optimizer was compared. In the segmentation result fish net, F1 score=(86.46%, 86.20%, 85.29%), IoU=(76.15%, 75.74%, 74.36%), For the rope F1 score=(80.49%, 80.48%, 77.86%), IoU=(67.35%, 67.33%, 63.75%) in the order of adaptive moment estimation (Adam), Momentum, and stochastic gradient descent (SGD). Adam's results were the highest in both fish net and rope. Through the research results, the evaluation of segmentation performance for each optimizer and the possibility of segmentation of marine debris in the latest deep learning technique were confirmed. Accordingly, it is judged that by applying the latest deep learning technique to the identification of submerged marine debris through underwater images, it will be helpful in estimating the distribution of marine sedimentation debris through more accurate and efficient identification than identification through the naked eye.

• 한국공간정보시스템학회:학술대회논문집
• /
• 2004.12a
• /
• pp.169-181
• /
• 2004

SK Telecom has already constructed GIMS system as the base common framework of LBS/GIS service system based on OGC(OpenGIS Consortium)'s international standard for the first mobile vector map service in 2002, But as service content appears more complex, renovation has been needed to satisfy multi-purpose, multi-function and maximum efficiency as requirements have been increased. This research is for preparation ion of GML3-based platform to upgrade service from GML2 based GIMS system. And with this, it will be possible for variety of application services to provide location and geographic data easily and freely. In GML 3.0, it has been selected animation, event handling, resource for style mapping, topology specification for 3D and telematics services for mobile LBS multimedia service. And the schema and transfer protocol has been developed and organized to optimize data transfer to MS(Mobile Stat ion) Upgrade to GML 3.0-based GIMS system has provided innovative framework in the view of not only construction but also service which has been implemented and applied to previous research and system. Also GIMS channel interface has been implemented to simplify access to GIMS system, and service component of GIMS internals, WFS and WMS, has gotten enhanded and expanded function.

• The Journal of the Korea Contents Association
• /
• v.20 no.1
• /
• pp.142-151
• /
• 2020

The reason why today's public actively uses social communication is that the necessary information is collected and classified under the name of social big data through the web space to create the big data era, an ecosystem of information. In order for big data information to be used by the public, it is necessary to visualize it easily. This study categorized the types of visualization according to the information of social big data, and targeted the experienced students including the related majors and the general public who need to directly utilize and study the actual big data visualization as an experience evaluation target. As a result of analyzing the experiences of the experienced people, important implications for the visualization method for managing, analyzing, and utilizing the data were derived. The big data visualization strategy is to be expressed in a way that fits the data environment and user's eye level on SNS. In the future, if big data visualization is applied to product service or social trend, it will be an important data in terms of broadening its role, scope of application, and application.

• Journal of Environmental Impact Assessment
• /
• v.24 no.3
• /
• pp.233-243
• /
• 2015

The ecosystem fragmentation due to transportation infrastructure causes road-kill phenomenon. When making policy for reducing road-kill it is important to select target-species in order to enhance its efficiency. However, many corridors installed in Korea have been raised issues about their effectiveness due to lack of considerations such as target-species selection, site selection, and management, etc. In this study, we are to grasp relationship between road-kill area and habitat patches and suggest that spatial location of habitat patches should be considered as one of the important factors when making policy for reducing road-kill. Habitat patches were presumed from overlying suitability index that chosen by literature review and road-kill hotspot was determined by Getis-Ord $G_i^*$ analysis. Afterwards, we performed a correlation analysis between $G_i$ Z-score and the distance from habitat patches to the roads. As a result, there is a negative correlation between two variables, It affects the $G_i^*$ Z-score going up if the habitat patches and the roads become closer.

• Journal of Wetlands Research
• /
• v.13 no.1
• /
• pp.45-52
• /
• 2011

Seawater circulations between a bay and the open sea play an important role to make the ecosystem healthy, providing nutrient and oxygen to the benthic environments and cleaning up pollutions. The health of the benthic environment in a bay is closely related to the flushing characteristics of seawater. In this study, to estimate the seawater distribution and circulation characteristics of benthic environment in the Geunso bay, we calculated the hydraulic turn-over time by a hydro-hypsographic analysis. Digital elevation model (DEM) which was generated using waterline method based upon remotely sensed data and water depth of the subtidal zone estimated by echo-sounding survey was applied to the hydro-hypsograhic analysis through a geographic information system (GIS) spatial analysis. The results showed that 95% of the total area of the bay was tidal flat and the hydraulic turn-over time was 1.03 tidal cycle, which indicated that the flushing characteristics of the Geunso bay was very good. Geunso bay was revealed to occupy relatively wide area of benthic environment and to have relatively big tidal range over other domestic and foreign coastal environment, therefore it could have a better seawater circulation characteristics. This result can be effectively applied as fundamental information to establish the system for a quantitative estimate of health of coastal environment in the west coast of Korea and manage the ecosystem in benthic environments.

• Korean Journal of Remote Sensing
• /
• v.37 no.5_1
• /
• pp.1043-1059
• /
• 2021

Forest and agricultural land are very important factors in the environmental ecosystem and securing food resources. Forest and agricultural land should be monitored regularly. CAS500-4 data are expected to be effectively used as a supplement of monitoring forest and agricultural land. Prior to the launch of the CAS500-4, the relative canopy height error analysis of the digital elevation model on South Korea was performed to determine the vertical target accuracy. Especially, by considering area of interest of the CAS500-4 (mountainous or agricultural area), it is conducted that vertical error analysis according to the slope and canopy. For Gongju, Jeju, and Samcheok, the average root mean squared differences were calculated compared to the drone LiDAR digitalsurface models, which were filmed in autumn and winter and the 5 m digital elevation model from the National Geographic Information Institute. As a result, the Shuttle radar topography mission digital elevation model showed a root mean squared differences of about 8.35, 8.19, and 7.49 m, respectively, while the Copernicus digital elevation model showed a root mean squared differences of about 5.65, 6.73, and 7.39 m, respectively. In addition, the root mean squared difference of shuttle radar topography mission digital elevation model and the Copernicus digital elevation model according to the slope angle were estimated on South Korea compared to the 5 m digital elevation model from the National Geographic Information Institute. At the slope angle of between 0° to 5°, root mean squared differences of the Shuttle radar topography mission digital elevation model and the Copernicus digital elevation model showed 3.62 and 2.52 m, respectively. On the other hands root mean squared differences of the Shuttle radar topography mission digital elevation model and the Copernicus digital elevation model respectively showed about 10.16 and 11.62 m at the slope angle of 35° or higher.

• 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 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 Korean Society for Geospatial Information Science
• /
• v.23 no.1
• /
• pp.101-111
• /
• 2015

Stream restoration projects have become threats to riparian ecosystem in Rep. of korea. Riparian wildlife becomes isolated and the animals are often experience difficulties in crossing riparian corridors. The purposes of this study is to select suitable wildlife passages for wild animals crossing riparian corridors. Maximum entropy model and snow tracking data on embankment in winter seasons were used to develop species distribution models to select suitable wildlife passages for water deer. The analysis suggests the following. Firstly, most significant factors for water deer's habitat in area nearby riparian area are shown to distance to water, age-class, land cover, slope, aspect, digital elevation model, tree density, and distance to road. For the riparian area, significant factors are shown to be land cover, size of riparian area, distance to tributary, and distance to built-up. Secondly, the suitable wildlife passages are recommended to reflect areas of high suitability with Maximum Entropy model in riparian areas and the surrounding areas and moving passages. The selected suitable areas are shown to be areas with low connectivity due to roads and vertical levee although typical habitats for water deer are forest, grassland, and farmland. In addition, the analysis of traces on snow suggests that the water deer make a detour around the artificial structures. In addition, the water deer are shown to make a detour around the fences of roads and embankment around farmland. Lastly, the water deer prefer habitats around riparian areas following tributaries. The method used in this study is expected to provide cost-efficient and functional analysis in selecting suitable areas.

• Korean Journal of Agricultural and Forest Meteorology
• /
• v.25 no.4
• /
• pp.427-435
• /
• 2023

Changes in flowering time due to weather fluctuations impact plant growth and ecosystem dynamics. Accurate prediction of flowering timing is crucial for effective forest ecosystem management. This study uses a process-based model to predict flowering timing in 2023 for five major tree species in Korean forests. Models are developed based on nine years (2009-2017) of flowering data for Abeliophyllum distichum, Robinia pseudoacacia, Rhododendron schlippenbachii, Rhododendron yedoense f. poukhanense, and Sorbus commixta, distributed across 28 regions in the country, including mountains. Weather data from the Automatic Mountain Meteorology Observation System (AMOS) and the Korea Meteorological Administration (KMA) are utilized as inputs for the models. The Single Triangle Degree Days (STDD) and Growing Degree Days (GDD) models, known for their superior performance, are employed to predict flowering dates. Daily temperature readings at a 1 km spatial resolution are obtained by merging AMOS and KMA data. To improve prediction accuracy nationwide, random forest machine learning is used to generate region-specific correction coefficients. Applying these coefficients results in minimal prediction errors, particularly for Abeliophyllum distichum, Robinia pseudoacacia, and Rhododendron schlippenbachii, with root mean square errors (RMSEs) of 1.2, 0.6, and 1.2 days, respectively. Model performance is evaluated using ten random sampling tests per species, selecting the model with the highest R². The models with applied correction coefficients achieve R² values ranging from 0.07 to 0.7, except for Sorbus commixta, and exhibit a final explanatory power of 0.75-0.9. This study provides valuable insights into seasonal changes in plant phenology, aiding in identifying honey harvesting seasons affected by abnormal weather conditions, such as those of Robinia pseudoacacia. Detailed information on flowering timing for various plant species and regions enhances understanding of the climate-plant phenology relationship.