GEO DATA

Data Articles

GeoAI Dataset for Industrial Park Segmentation from Sentinel-2 Satellite Imagery and GEMS: Sung-Hyun Gong, Hyung-Sup Jung, Geun-han Kim, Geun-Hyouk Han, Il-Hoon Choi, Jin-Sung Hong; GEO DATA. 2025;7(1):36-44. Published online February 13, 2025; DOI: https://doi.org/10.22761/GD.2024.0054

474 View
49 Download

Abstract PDF: Air pollution in East Asia presents critical environmental and health challenges, particularly in industrial regions affected by domestic and cross-border emissions. This study developed a GEO AI dataset specifically for industrial park segmentation, integrating Sentinel-2 satellite imagery, Geostationary Environment Monitoring Spectrometer (GEMS) geostationary satellite data, and Air Quality Monitoring Network data. Optimized for semantic segmentation tasks with labeled data specifically for industrial park classification, this dataset serves as a foundational asset for the precise identification and spatial tracking of major air pollution sources. We validated the dataset’s applicability using a modified U-Net model, achieving a mean intersection over union of 0.8146 and pixel accuracy of 0.9608, thereby demonstrating its potential as a tool for detecting and monitoring pollutant sources in industrial areas. With future expansion through additional temporal data and diverse pollutant measurements, this dataset is anticipated to support regional air quality monitoring efforts and inform strategies for pollution control across East Asia.

Status of Mammals Entrapment in Open Irrigation Canals: Jiyoun Kim, Hanbi Lee, Kihyun Kim, Sehee Kim, Euigeun Song; GEO DATA. 2024;6(4):411-419. Published online December 31, 2024; DOI: https://doi.org/10.22761/GD.2024.0062

202 View
11 Download

Abstract PDF: Linear infrastructure such as roads, railways, and irrigation canals causes habitat fragmentation and disrupts wildlife movement, negatively impacting ecosystems. This study investigated the physical characteristics of 80 artificial structures across South Korea and analyzed the status of wildlife entrapment prevention facilities and mammal entrapment incidents within irrigation canals. The surveyed structures, including irrigation canals, drainage canals, and roadside ditches, had an average length of 2.57 km, width of 3.34 m, and height of 1.4 m. Most structures (88.8%) were concrete, while 11.3% were mixed concrete and earthen canals. Wildlife entrapment prevention facilities, including escape facilities, cross-movement structures, and avoidance guidance facilities, were installed at low rates. Mammals entrapment incidents were observed 620 cases, with Korean water deer (Hydropotes inermis) and common raccoon dog (Nyctereutes procyonoides) being the most frequently observed. Additionally, entrapment incidents involving the endangered Eurasian otter (Lutra lutra) and leopard cat (Prionailurus bengalensis) were also recorded. Escape facilities and guidance facilities showed no significant difference in the average occurrence rates of mammals, but the maximum occurrence rates were lower in sections where these facilities were installed. This study provides essential baseline data for policy development and management strategies aimed at mitigating wildlife entrapments and improving ecological connectivity in artificial linear infrastructure.

GeoAI Dataset for Urbanized Area Segmentation from Landsat 8/9 Satellite Imagery and GEMS: Sung-Hyun Gong, Hyung-Sup Jung, Geun-Han Kim, Geun-Hyouk Han, Il-Hoon Choi, Jin-Sung Hong; GEO DATA. 2024;6(4):478-486. Published online December 31, 2024; DOI: https://doi.org/10.22761/GD.2024.0053

275 View
23 Download
1 Citations

Abstract PDF

In South Korea, air pollution has emerged as a pressing social issue, necessitating data-driven approaches to monitor sources of air pollutants. This study constructed a GEO AI dataset for detecting air pollution sources in urbanized areas, utilizing Landsat 8/9 satellite imagery, Geostationary Environment Monitoring Spectrometer geostationary satellite data, and air quality monitoring network data. The dataset is optimized for semantic segmentation tasks, including labeled data for urban area segmentation, and is designed to enable precise detection of pollution sources within urban regions by integrating satellite imagery and air quality information. Using this dataset, we applied a modified U-Net model to classify pollutant sources in urbanized areas, achieving high performance with an mIoU of 0.8592 and pixel accuracy of 0.9433. These results demonstrate the effectiveness of the GEO AI dataset as a tool for identifying and managing major pollution sources, providing foundational data for air quality monitoring and policy development across South Korea and East Asia. With further integration of additional air pollution data, this dataset is expected to contribute to long-term air quality management and the mitigation of health impacts associated with pollution.

Citations

Citations to this article as recorded by

Semantic Segmentation of Urbanized Areas Using Multi-Encoder U-Net Based on Multi-Modal Data
Sung-Hyun Gong, Hyung-Sup Jung, Geun-Han Kim, Geun-Hyouk Han, Il-Hoon Choi, Jin-Sung Hong
Korean Journal of Remote Sensing.2025; 41(2): 461. CrossRef

GeoAI Dataset for Urban Water Body Detection Using TerraSAR-X Satellite Radar Imagery: Eu-Ru Lee, Jun-Hyeok Jung, Ki-Chang Kim, Seong-Jae Yu, Hyung-Sup Jung; GEO DATA. 2024;6(4):435-450. Published online December 31, 2024; DOI: https://doi.org/10.22761/GD.2024.0046

372 View
25 Download

Abstract PDF: This study presents the generation of a GeoAI dataset for urban water body detection using TerraSAR-X satellite synthetic aperture radar (SAR) imagery. The study area includes urban regions in Seoul and Gyeonggi Province, chosen for their complex structures and frequent flooding, which pose challenges for SAR analysis. The data preprocessing involved generating Sigma0 images, image co-registration, median filtering for speckle noise reduction, decibel conversion, and orthorectification using Copernicus DEM for precise geometric correction. Label data were created using the global river widths from Landsat dataset combined with the Otsu thresholding method and fine-tuned with Google Map imagery. Annotation guidelines were meticulously designed to account for SAR-specific phenomena such as layover, corner reflections, and side lobe effects, ensuring consistent and accurate labeling across different orbits and observation conditions. The resulting dataset supports deep learning models in learning geometric characteristics of SAR imagery, enhancing water body detection capabilities. This work provides a foundational resource for future applications in urban water management and climate-resilient disaster response.

The Funga of Higher Fungi of Mountain Minjuji in Korea: Eunsu Park, Sangyoung Park, Sohee Kim, Eunjin Kim, Hwa-Yong Lee, Ju-Kyeong Eo; GEO DATA. 2024;6(4):330-339. Published online December 31, 2024; DOI: https://doi.org/10.22761/GD.2024.0037

174 View
14 Download

Abstract PDF: In this study, we conducted basic research on the classification and ecology of higher fungi as part of the 2023 biomimicry research. These fungal strains will be used in mycofabrication research for the development of textile materials. We investigated the biodiversity of higher fungi in Mountain Minjuji from May to October 2023. We identified two divisions, seven classes, 19 orders, 52 families, 95 genera, and 181 species of fungi. We divided the Ascomycota strains into four classes, seven orders, 12 families, 14 genera, and 17 species, and the Basidiomycota strains into three classes, 12 orders, 39 families, 81 genera, and 164 species. The top three most frequently discovered taxa were Russula Pers., with a total of 19 species identified, followed by Amanita Pers., with 12 species, and Lactarius Pers., with 11 species. Our results provide basic data on the higher fungi of Mountain Minjuji and will assist with fungal monitoring research.

Analysis of the Geographic Environment Characteristics of Mountain Wetlands in Gyeongsangnam-do: Mi-Jeong Kim, Yeon Hui Jang, Jong-Hak Yun, Soo-Dong Lee; GEO DATA. 2024;6(4):280-289. Published online December 31, 2024; DOI: https://doi.org/10.22761/GD.2024.0029

250 View
17 Download

Abstract PDF: Wetlands are transitional zones between terrestrial and aquatic ecosystems and are among the most nutrient-rich and productive ecosystems on Earth. This study analyzed the topographical and ecological characteristics of mountain wetlands in Gyeongsangnam-do to provide essential data for their conservation and management. The results indicated that mountain wetlands in Gyeongsangnam-do are primarily distributed in areas with slopes ranging from 5° to 15°. Bog (M1) and fen (M2), which possess significant ecological value, were found to be situated in areas over 700 m above sea level. In contrast, swamp (M4) was distributed across a wider range of altitudes and slopes, with some wetlands exhibiting signs of ecological degradation due to anthropogenic disturbances. These findings can serve as critical data for developing management plans aimed at the sustainable conservation of mountain wetlands.

Study on Grain Size, Physical Properties and Organic Matter Characteristics of Tidal Flat Surface Sediments: May 2022 Hwangdo Tidal Flat Dataset, Cheonsu Bay: Jun-Ho Lee, Hoi-Soo Jung, Huigyeong Ryu, Keunyong Kim, Joo-Hyung Ryu, Yeongjae Jang; GEO DATA. 2024;6(3):159-174. Published online September 30, 2024; DOI: https://doi.org/10.22761/GD.2024.0011

1,103 View
59 Download

Abstract PDF: This study analyzes the geological and geochemical features of surface sediments in the Hwangdo Tidal Flat, located on Korea’s West Coast. The tidal flat experiences semi-diurnal tides, impacting organic matter decomposition and nutrient cycling. Ninety one sediment samples were collected and analyzed for physical and chemical properties including grain size, density, water content, organic carbon, and nitrogen. Sediments consist mainly of sand and silt, with coarser sediments near the main channel and finer sediments towards the west. Sediment grain size averages 4.12 Φ with a sorting coefficient of 1.96 Φ, indicating diverse energy environments. Total organic carbon and nitrogen correlate positively with grain size and density, reflecting sediment origin and environment. Kriging maps sediment grain size distribution, while correlation and linear regression analyses show relationships between variables. High correlations exist between various parameters, aligning with tidal flat characteristics and aiding understanding of sediment transport and deposition. The study provides baseline data for understanding the tidal flat’s geological, geochemical, and physical aspects, valuable for remote sensing validation and environmental monitoring. The dataset is freely available for research and management purposes.

Original Papers

The Cheonji Lake GeoAI Dataset based in Optical Satellite Imagery: Landsat-5/-7/-8 and Sentinel-2: Eu-Ru Lee, Ha-Seong Lee, Sun-Cheon Park, Hyung-Sup Jung; GEO DATA. 2024;6(1):14-23. Published online March 28, 2024; DOI: https://doi.org/10.22761/GD.2023.0055

2,341 View
73 Download
1 Citations

Abstract PDF

The variations in the water area and water level of Cheonji, the caldera lake of Baekdu Mountain, serve as reliable indicators of volcanic precursors. However, the geographical and spatial features of Baekdusan make it impossible to directly observe the water area and water level. Therefore, it is crucial to rely on remote sensing data for monitoring purposes. Optical satellite imagery employs different spectral bands to accurately delineate the boundaries between water bodies and non-water bodies. Conventional methods for classifying water bodies using optical satellite images are significantly influenced by the surrounding environment, including factors like terrain and shadows. As a result, these methods often misclassify the boundaries. To address these limitations, deep learning techniques have been employed in recent times. Hence, this study aimed to create an AI dataset using Landsat-5/-7/-8 and Sentinel-2 optical satellite images to accurately detect the water body area and water level of Cheonji lake. By utilizing deep learning methods on the dataset, it is reasonable to consistently observe the area and level of water in Cheonji lake. Furthermore, by integrating additional volcanic precursor monitoring factors, a more accurate volcano monitoring system can be established.

Citations

Citations to this article as recorded by

Performance Comparison of Water Body Detection from Sentinel-1 SAR and Sentinel-2 Optical Imagery Using Attention U-Net Model
Il-Hoon Choi, Eu-Ru Lee, Hyung-Sup Jung
Korean Journal of Remote Sensing.2024; 40(5-1): 507. CrossRef

The Cheonji Lake GeoAI Dataset Based in Synthetic Aperture Radar Images: TerraSAR-X, Sentinel-1 and ALOS PALSAR-2: Eu-Ru Lee, Ha-Seong Lee, Ji-Min Lee, Sun-Cheon Park, Hyung-Sup Jung; GEO DATA. 2023;5(4):251-261. Published online December 29, 2023; DOI: https://doi.org/10.22761/GD.2023.0056

1,624 View
52 Download
2 Citations

Abstract PDF

The fluctuations in the area and level of Cheonji in Baekdu Mountain have been employed as significant indicators of volcanic activity. Monitoring these changes directly in the field is challenging because of the geographical and spatial features of Baekdu Mountain. Therefore, remote sensing technology is crucial. Synthetic aperture radar utilizes high-transmittance microwaves to directly emit and detect the backscattering from objects. This weatherproof approach allows monitoring in every climate. Additionally, it can accurately differentiate between water bodies and land based on their distinct roughness and permittivity characteristics. Therefore, satellite radar is highly suitable for monitoring the water area of Cheonji. The existing algorithms for classifying water bodies using satellite radar images are significantly impacted by speckle noise and shadows, resulting in frequent misclassification. Deep learning techniques are being utilized in algorithms to accurately compute the area and boundary of interest in an image, surpassing the capabilities of previous algorithms. This study involved the creation of an AI dataset specifically designed for detecting water bodies in Cheonji. The dataset was constructed using satellite radar images from TerraSAR-X, Sentinel-1, and ALOS-2 PALSAR-2. The primary objective was to accurately detect the area and level of water bodies. Applying the dataset of this study to deep learning techniques for ongoing monitoring of the water bodies and water levels of Cheonji is anticipated to significantly contribute to a systematic method for monitoring and forecasting volcanic activity in Baekdu Mountain.

Citations

Citations to this article as recorded by

Performance Comparison of Water Body Detection from Sentinel-1 SAR and Sentinel-2 Optical Imagery Using Attention U-Net Model
Il-Hoon Choi, Eu-Ru Lee, Hyung-Sup Jung
Korean Journal of Remote Sensing.2024; 40(5-1): 507. CrossRef
GeoAI Dataset for Urban Water Body Detection Using TerraSAR-X Satellite Radar Imagery
Eu-Ru Lee, Jun-Hyeok Jung, Ki-Chang Kim, Seong-Jae Yu, Hyung-Sup Jung
GEO DATA.2024; 6(4): 435. CrossRef

Research on Building AI Learning Dataset for Synthetic Aperture Radar Waterbody Detection through Optical Satellite Image Fusion: Joonhyuk Choi, Ki-mook Kang, Euiho Hwang; GEO DATA. 2023;5(3):177-184. Published online September 27, 2023; DOI: https://doi.org/10.22761/GD.2023.0029

1,043 View
33 Download
1 Citations

Abstract PDF

For the spatiotemporal analysis of water resources and disasters, water body detection using satellite imagery is crucial. Recently, AI-based methods have been widely employed in water body detection using satellite imagery. To use these AI techniques, a substantial amount of training data is required. When creating training data for water body detection, optical imagery and synthetic aperture radar (SAR) imagery have their respective strengths and weaknesses. To use the advantages of both, this study proposes a water body detection method through the fusion of optical and SAR imagery. The results of the proposed model show an Intersection over Union of 0.612 and an F1 score of 0.759, which is better compared to using either optical or SAR imagery alone. This research presents a method that can easily generate a large amount of water body data, making it promising for use as AI training data for water body detection.

Citations

Citations to this article as recorded by

A Comprehensive Review of Remote Sensing for Water-Related Disaster Management in South Korea: Focus on Floods and Droughts
Eui-Ho Hwang, Jin-Gyeom Kim, Jang-Yong Sung, Ki-Mook Kang
Korean Journal of Remote Sensing.2024; 40(5-2): 833. CrossRef

Estimation of Equivalent Rainfall for Ungauged Reservoir Using Satellite-Based High-Resolution Terrain Data: Jin Gyeom Kim, Kimook Kang, Chanyoung Son, Gibeom Nam, Euiho Hwang; GEO DATA. 2023;5(3):170-176. Published online September 27, 2023; DOI: https://doi.org/10.22761/GD.2023.0028

2,298 View
37 Download
1 Citations

Abstract PDF

Equivalent rainfall refers to the amount of precipitation required to reach a specific water level from the current water level in a reservoir. It serves as a flood forecasting and warning system that allows for the rapid assessment of the reservoir’s maximum water level at the moment of rainfall forecast. In reservoirs where terrain and survey data can be obtained, deriving equivalent rainfall is not difficult. However, without terrain data, satellite imagery and global topographic data are the only available options. In this study, high-resolution topographic data based on satellites were utilized to estimate the equivalent rainfall in the ungauged reservoir, Hwanggang Dam, located in the upper stream of the Imjin River in North Korea. To calculate the inflow into the reservoir, the Natural Resources Conservation Service-Curve Number method was used to determine the effective rainfall, taking into account the antecedent conditions, as the inflow into the reservoir can be changed for the same amount of rainfall depending on the soil moisture content of the watershed.

Citations

Citations to this article as recorded by

A Study on the Rainfall-Storage Volume-Target Water Level Curve for Flood Control on the Small Size Dam: Case study for Goesan Dam
Soojun Kim, Jaewon Kwak, Hui-Seong Noh, Narae Kang, Seokhwan Hwang
Journal of the Korean Society of Hazard Mitigation.2024; 24(2): 105. CrossRef

Construction of Exploration Data for Greenhouse Gas Geologic Storage: Focusing on Geological Cross-section Data: Bokyun Ko, Sungjae Park, Saro Lee; GEO DATA. 2023;5(3):222-229. Published online September 26, 2023; DOI: https://doi.org/10.22761/GD.2023.0023

1,227 View
107 Download

Abstract PDF: 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.

Comparative Study of Machine Learning and Deep Learning Models Applied to Data Preprocessing Methods for Dam Inflow Prediction: Youngsik Jo, Kwansue Jung; GEO DATA. 2023;5(2):92-102. Published online June 30, 2023; DOI: https://doi.org/10.22761/GD.2023.0016

1,244 View
57 Download

Abstract PDF: In this study, we employed representative machine learning (ML) and deep learning (DL) models previously utilized in the fields of rainfall and runoff analysis in the water resources sector. We not only performed hyperparameter tuning of the models but also considered the characteristics of the model and the combination and preprocessing (such as lag-time and moving average) of meteorological and hydrological data. We then compared and evaluated the performance of the models according to various scenarios of data characteristics and ML & DL model combinations for predicting daily water inflow. To accomplish this, we utilized meteorological and hydrological data collected from 1974 to 2021 in the Soyang River Dam Basin to examine 1) precipitation, 2) inflow, and 3) meteorological data as primary independent variables. We then employed a total of 36 scenario combinations as input data for ML & DL, applying a) lag-time, b) moving average, and c) component separation conditions for inflow. To identify the most suitable data combination characteristics and ML & DL models for predicting daily inflow, we compared and evaluated 10 different ML & DL models: 1) Linear Regression, 2) Lasso, 3) Ridge, 4) Support Vector Regression, 5) Random Forest (RF), 6) Light Gradient Boosting Model, 7) XGBoost for ML, and 8) Long Short-Term Memory (LSTM) models, 9) Temporal Convolutional Network (TCN), and 10) LSTM-TCN for DL.

Note

Is the ocean science data repository, JOISS able to be FAIR?: Tae Yoon Song, Ji Yoon Lee, Woo Ram Kim, Soyeona Park, Tae Keun Rho; GEO DATA. 2022;4(2):47-56. Published online June 30, 2022; DOI: https://doi.org/10.22761/DJ2022.4.2.005

1,461 View
40 Download

Abstract PDF: As the global open science movement has recently proven its effectiveness in responding to the corona pandemic, research on disciplinary or institutional data repositories and establishing service platforms for the open and sharing research data are also active in Korea. The purpose of the research data repository is not to manage data per se but to discover and innovate knowledge and to integrate and reuse subsequent data and knowledge. Therefore, recent repository-related studies emphasize implementing the FAIR principle in this collaborative process, from observation to data documentation, data combination, quality control, and data publication. In particular, high-level data interoperability through the FAIR implementation of the repository is essential for ocean observation that requires multidisciplinary collaborative research. In Korea, ocean observatory organizations have repositories, including the ocean science data repository, JOISS; however, no studies evaluate the establishment and operation of data repositories in the FAIR principle. Therefore, this study aims to examine the construction process and data management status of the JOISS repository and the main functions and services of the web platform in terms of the data lifecycle and evaluate The FAIR principle of Open Science works in such an operating system and its limitations. The study provides implications for the improvement direction of data management and services of domestic marine repositories, including the JOISS, in an environment where the diversity and volume of data are rapidly increasing along with the evolution of ocean observation.

Article

Construction of a Training Dataset for Vessel Distribution Prediction: The Northern Seas of Jeju Island: Yonggil Park, Taehoon Kim, Hyeon-Gyeong Han, Cholyoung Lee; GEO DATA. 2022;4(2):37-46. Published online June 30, 2022; DOI: https://doi.org/10.22761/DJ2022.4.2.004

1,526 View
77 Download

Abstract PDF: Recently, interest in maritime accidents and safety-related research, such as preventing collisions between marine vessels, detecting illegal vessels, and predicting vessel routes, is increasing. Vessel location data-based vessel distribution map can support decision-making for maritime safety management, and if the vessel distribution can be predicted, it is possible to take a preemptive response for maritime security such as fishing safety management and illegal fishing prevention. In this study, a training dataset for vessel distribution prediction was constructed by collecting V-Pass data, weather warnings, and marine environment data. The result of resampling of reporting interval of vessel location data was mapped to grid data to evaluate the vessel density, and a total of 1,314,000 of training data were constructed for the study area. In the future, research to evaluate the accuracy by performing vessel distribution prediction modeling should be conducted.

First
Prev
Page of 2
Next
Last

Search