다목적실용위성 광학영상을 활용한 AI 학습용 도로 검출 데이터셋

이훈희,오한 (사)지오에이아이데이터학회 2022 GEO DATA Vol.4 No.1

인공위성의 광학영상에 보이는 도로의 형태 및 종류 정보는 수치적 지도 제작 및 도로 변화 감시에 유용하다. 다목적실용위성 3호와 3A호에 탑재된 광학 카메라로부터 수집되는 광학영상 데이터를 가공하고 구조화하면 도로 검출 알고리즘의 개발과 이러한 분석 도구를 이용한 도로 정보 산출 작업을 가속화할 수 있다. 특히, 딥러닝(Deep Learning) 학습 기술을 적용할 수 있도록 준비된 AI (Artificial Intelligence)용 학습 데이터셋으로구축되면 컴퓨터 과학 분야의 최신 인공지능 기술을 위성영상 기반 도로 검출 분야에 스핀오프(Spin-off)하여폭넓은 분석을 시도할 수 있다. 한국항공우주연구원은 국내 여러 업체와 함께 위성 광학영상을 이용하여 AI 학습용 도로 영상 데이터셋을 구축하였으며 본 논문에서는 이 데이터셋의 활용 예시와 함께 데이터셋의 종류, 규모 등에 관하여 설명한다. 구축된 데이터는 aihub.or.kr 웹사이트를 통해 이용할 수 있다.

다목적실용위성 5호 GNSS 전파 엄폐 데이터 운영

정옥철,성재동,이명신,정대원 (사)지오에이아이데이터학회 2022 GEO DATA Vol.4 No.3

The Korea Aerospace Research Institute launched KOMPSAT-5 on August 22, 2013, and has been operating for 10 years. KOMPSAT-5 has SAR (Synthetic Aperture Radar) for earth observation missions, and collects data necessary for earth atmosphere analysis through GNSS RO (Radio Occultation) receivers. RO data can be used for numerical weather forecast model based on temperature, pressure, and humidity by calculating the vertical distribution of atmospheric information. As a part of the Korea-US science and technology cooperation, KARI has been providing RO data of KOMPSAT-5 to the United States NOAA (National Oceanic and Atmospheric Administration) in near-real time since 2018. To this end, KARI receives telemetry data from the satellite about 12 times a day using 3 ground stations from Daejeon, Alaska in the U.S., and Sodankyla in Finland. The pre-processed data is being provided to both the UCAR (University Corporation for Atmospheric Research) in the U.S. and the KASI (Korea Astronomy and Space Science Institute). In this paper, radio occlusion data of KOMPSAT-5 is introduced, and system configuration, operation concepts for providing near-real time data and its application are also presented. 한국항공우주연구원은 2013년 8월 22일 다목적실용위성 5호를 발사하여 10년차 운영을 수행하고 있다. 다목적실용위성 5호는 SAR (Synthetic Aperture Radar)를 이용하여 지구관측 임무를 수행하면서 동시에 GNSS (Global Navigation Satellite System) 전파 엄폐(Radio Occultation, RO) 수신기를 통해 지구대기 분석에 필요한 데이터를 수집하고 있다. 전파 엄폐 데이터는 대기정보의 연직분포 산출을 통해 온도, 압력, 습도 등을 파악할 수 있어 기상예보를 위한 수치모델에 활용 가능하다. 한국항공우주연구원은 한-미 과학기술 협력의 일환으로 2018년부터 미국 국립해양대기청(National Oceanic and Atmospheric Administration, NOAA)에 다목적실용위성 5호의 대기 엄폐 데이터를 준-실시간으로 제공하고 있다. 이를 위해 한국항공우주연구원에서는 대전 지상국, 미국 알래스카(Alaska) 지상국, 핀란드 소단킬라(Sodankyla) 지상국을 이용하여 하루 약 12회 위성으로부터 텔레메트리 데이터를 수신하여 전처리 후 전파 엄폐 데이터를 미국 기상연구대학연합(University Corporation for Atmospheric Research, UCAR)과 한국천문연구원에 동시에 제공하고 있다. 본 논문에서는 다목적실용위성 5호의 전파 엄폐 데이터를 소개하고, 준-실시간 자료 제공을 위한 시스템 구성 및 운영개념, 그리고 데이터 활용 사례를 제시하였다.

온실가스 지중저장 적지 탐사 데이터 구축: 지질단면도 데이터를 중심으로

고보균,Park, Sungjae,이사로 (사)지오에이아이데이터학회 2023 GEO DATA Vol.5 No.3

In this study, the most basic data, underground geological structure data, that is, geological cross-section data, were established to select a candidate site for underground storage of greenhouse gases based on AI. As a target area, the Gyeongsang Basin, where a large amount of sedimentary rocks are distributed, was selected as the greenhouse gas can be stored most effectively in sedimentary rocks. To this end, the acquisition and edit step, the refinement step, and the labeling step were carried out in the order of raw data collection, source data and labeling data construction to construct the geological cross-section data. This data can be downloaded through the AI hub site (https://aihub.or.kr/aihubdata/data/view.do?curr Menu=115&topMenu=100&aihubDataSe=realm&dataSetSn=71390) operated by the Korea Institute for Intelligent Information Society Promotion.

해양과학 데이터저장소 JOISS는 FAIR한가?

송태윤,이지윤,김우람,박소예나,노태근 (사)지오에이아이데이터학회 2022 GEO DATA Vol.4 No.2

As the global open science movement has recently proven its effectiveness in responding to the coronapandemic, research on disciplinary or institutional data repositories and establishing service platforms for theopen and sharing research data are also active in Korea. The purpose of the research data repository is not tomanage data per se but to discover and innovate knowledge and to integrate and reuse subsequent data andknowledge. Therefore, recent repository-related studies emphasize implementing the FAIR principle in thiscollaborative process, from observation to data documentation, data combination, quality control, and datapublication. In particular, high-level data interoperability through the FAIR implementation of the repository is송태윤 · 이지윤 · 김우람 · 박소예나 · 노태근GEO DATA [4.2]: 47–56 (2022) 48essential for ocean observation that requires multidisciplinary collaborative research. In Korea, ocean observatoryorganizations have repositories, including the ocean science data repository, JOISS; however, no studies evaluatethe establishment and operation of data repositories in the FAIR principle. Therefore, this study aims to examinethe construction process and data management status of the JOISS repository and the main functions andservices of the web platform in terms of the data lifecycle and evaluate The FAIR principle of Open Science worksin such an operating system and its limitations. The study provides implications for the improvement direction ofdata management and services of domestic marine repositories, including the JOISS, in an environment where thediversity and volume of data are rapidly increasing along with the evolution of ocean observation

드론 다분광영상을 활용한 하천 수심조사 연구

권영화,김동수,권시윤 (사)지오에이아이데이터학회 2023 GEO DATA Vol.5 No.3

River basin surveys are conducted with the aim of providing essential foundational information for the formulation of water management policies, as mandated by relevant laws and regulations. These surveys cover key investigation areas necessary for river basin management, including basic conditions, water conveyance, dimensions, environmental ecology, and more. Among the survey methods, the utilization of remote sensing data, such as drone monitoring imagery and satellite imagery, is employed for various purposes such as the safety management of hydraulic structures like dams and embankments, water quality monitoring, river terrain surveys, and assessments of changes in riverbeds. Recently, research in river basin studies has been conducted using hyperspectral imagery, which includes hundreds of spectral bands, in addition to standard RGB imagery. Hyperspectral imagery offers the advantage of high spectral resolution, making it suitable for multi-parameter assessments. However, it comes with the drawback of large initial data volumes and complex preprocessing requirements due to the abundance of spectral information. On the other hand, multispectral imagery, which collects spectral information from fewer than ten bands, is widely used, especially in agriculture and forestry. It allows for immediate monitoring of parameters like the normalized difference vegetation index (NDVI) using just two bands and facilitates the analysis of crop growth status and more. Research on bathymetric estimation using hyperspectral imagery has traditionally relied on the Optimal Band Ratio Analysis (OBRA), which utilizes band ratios highly correlated with depth to construct bathymetric maps. In this study, we applied the existing hyperspectral bathymetric estimation technique to multispectral imagery to assess the feasibility of bathymetric estimation using reduced spectral bands. We captured multispectral imagery and constructed bathymetric maps to evaluate the applicability of multispectral imagery in river basin applications. Furthermore, to overcome the limitations of traditional OBRA, we employed Gaussian mixture models for image clustering to improve the accuracy of bathymetric estimation.

한국 수산시장에서 판매되는 뱀장어속(Anguilla) 어류의 진위판별법 개발 및 유통실태

장요순 (사)지오에이아이데이터학회 2022 GEO DATA Vol.4 No.1

This study was carried out to identify the mislabeling of Japanese eel (Anguilla japonica) sold on the fish marketsin Korea and to develop a method for determining the authenticity of fresh and trimmed eels. Between January andDecember 2018, 31 test samples were collected from restaurants and fish markets in Seoul, South Korea, and the collectedsamples were analyzed. The results showed that over two-thirds of the samples tested were mislabeled. Molecularidentification of 31 test samples revealed that 10 Anguilla japonica, 9 Anguilla Anguilla, 2 Anguilla rostrate, 1 Anguillamarmorata, 7 Ophichthus remiger, 1 Brachysomophis crocodilinus, and 1 Conger myriaster. We have developed the NdeⅠPCR-RFLP assay for determining the authentication of fresh and trimmed eels sold on the fish markets in Korea, andthis assay enables rapidly and accurately identify the genus Anguilla. 본 연구는 우리나라 수산시장에서 유통되는 뱀장어(Japanese eel, Anguilla japonica)의 허위정보 표시 실태를파악하고, 뱀장어 선어 및 손질·가공품의 진위판별법을 개발하기 위하여 수행되었다. 2018년 1월부터 12월까지서울지역의 장어 전문식당과 수산시장에서 조사샘플 31개를 수집하여 분석한 결과, 67.74%에 해당하는 21개장어샘플이 허위정보 표시로 유통되고 있음을 확인하였다. 31개의 조사샘플을 분자동정한 결과, 극동산뱀장어(Anguilla japonica) 10개, 유럽산 뱀장어(Anguilla Anguilla) 9개, 미국산 뱀장어(Anguilla rostrate) 2개,무태장어(Anguilla marmorata) 1개, Ophichthus remiger 7개, Brachysomophis crocodilinus 1개, 붕장어(Conger myriaster)1개로 확인되었다. 이와 같은 뱀장어 오표시 유통 실태 조사결과를 근거로 본 연구에서는 선어 또는손질가공품으로 판매되는 뱀장어가 Anguilla 속 어류에 속하는지 여부를 빠르게 판별할 수 있는 NdeⅠ PCR-RFLP분석법을 개발하였다.

토양물리 및 지형, 수문학적 개념을 도입한 기계학습 기반의 C-band Synthetic Aperture Radar 토양수분 산정 연구

정지훈,이용관,김진욱,장원진,김성준 (사)지오에이아이데이터학회 2023 GEO DATA Vol.5 No.3

In this study, we applied machine learning to estimate soil moisture levels in South Korea by harnessing data from the Sentinel-1 C-band synthetic aperture radar (SAR). Our approach incorporated not only the relationship between backscattering coefficients and soil moisture but also diverse physical characteristics. This encompassed topographic information, soil physics data, and antecedent precipitation which is a hydrological factor influencing the initial condition of soil moisture. We applied a variety of machine-learning techniques and conducted a comprehensive analysis to compare the performance of each model.

충청·전라 권역 해안사구의 외래종 및 생태계교란식물 분포 현황

이성훈,강지현,황현수 (사)지오에이아이데이터학회 2023 GEO DATA Vol.5 No.4

This study was conducted to provide the coastal sand dunes flora of vascular plants in Chungcheong to Jeolla region based national coastal dune natural environment survey from 2018 to 2019. In the study area, a total 631 taxa, consisting of 119 family, 372 genera, 566 species, 8 subspecies, 50 varieties, and 7 forma, were found. Among them, there were 95 taxa with 23 family, 66 genera, 99 species and 5 varieties as alien species. The number of alien species ranged from 7 to 45 on each coastal sand dune. The largest number was recorded in Sinjimyeongsa dune, while the lowest was in Namujeon dune. Moreover, ecosystem disturbing species had mainly existed on Sinhap dune. Japanese hop (Humulus japonicus) were distributed most widely on 17 coastal sand dune, and bur cucumber (Sicyos angulatus) was only found on Sinhap dune. The spatial status of flora of coastal sand dune in our data can be basic ecological information for the conservation and management of the coastal dune plant species diversity.

Synthetic Aperture Radar 펄스의 통계적 특성을 이용한 호소 부유 폐기물 탐지

윤동현,유하은,이명진 (사)지오에이아이데이터학회 2023 GEO DATA Vol.5 No.3

This study developed the European Space Agency (ESA) Setinel-1 Ground Range Detected (GRD) time series analysis model for monitoring floating debris in lake areas through Google Earth Engine Application Programming Interface. The study aims to monitor floating debris caused by heavy rainfall efficiently. Regarding water resources and water quality management, floating debris from multipurpose dams requires continuous monitoring from the initial generation stage. In the study, a Synthetic Aperture Radar (SAR) time series analysis model that is easy to identify water bodies was developed due to low accessibility in large areas. Although SAR satellite images could be used to observe inland water environments, debris detection on water surface surfaces has yet to be studied. For the first time, this study detected floating debris patches in a wide range of lakes from GRD imagery acquired by ESA’s Sentinel-1 satellite. It demonstrated the potential to distinguish them from naturally occurring materials such as invasive floating plants. In this study, the case of Daecheong Dam, in which predicted floating debris was detected after heavy rain using Sentinel-1 GRD data, is presented. It could quickly detect various floating debris flowing into dams used as a source of drinking water and serve as a reference for establishing a collection plan.

녹조 면단위 관측 및 머신러닝 분석을 통한 신규댐 저수지의 위성영상 기반 녹조추정 기술 정확도 개선 연구

이혜숙,최성화,김동균,김호준 (사)지오에이아이데이터학회 2023 GEO DATA Vol.5 No.3

Algal blooms are major issues and an ongoing cause of water quality problems in inland waters globally. In the case of harmful algal blooms, the water temperature rises after nitrogen and phosphorus inflow, which occurs in the summer, is the main cause of the algae bloom. In South Korea, algae monitoring methods have been performed by collecting water in point monitoring stations. Recently, in order to overcome the limitations of these existing monitoring methods, spatial monitoring methods using hyperspectral images and satellite images has been researched. We used satellite images for analysis of the spatial algal variation. The accuracy of algal identification is imperative for effective spatial monitoring of algal blooms in the context of ecological health and assessment. In this study, we generated algal big-data with simultaneously observed chlorophyll-a concentrations based on fluorescence measurement and predicted chlorophyll-a concentrations using 13- band satellite images derived from Sentinel-2. In order to validate the values from the satellite images, we compared them with simultaneously observed chlorophyll-a concentrations based on fluorescence measurement. The goal of this study is to improve the accuracy of predictions induced from satellite images. The analytical techniques were comparatively evaluated. The results showed that Artificial Neural Networks exhibited the best performance among them, improving more than 30% accuracy compared to that of multiple linear regression. Furthermore, the accuracy of identifying algal blooms has been shown to increase at high algal concentrations. In the end, it was successful to create algal bloom maps using a new algorithm to analyze algal bloom management.