GEO DATA

Original Paper

A Study on C-band Synthetic Aperture Radar Soil Moisture Estimation Based on Machine Learning Using Soil Physics, Topography, and Hydrological Information: Jeehun Chung, Yonggwan Lee, Jinuk Kim, Wonjin Jang, Seongjoon Kim; GEO DATA. 2023;5(3):137-146. Published online September 22, 2023; DOI: https://doi.org/10.22761/GD.2023.0026

Abstract PDF: 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.

Articles

The Dataset of Sedimentary Environments at Hwangdo Tidal Flat on the Western Coast of Korea (2004 to 2013): Kye-Lim Kim, Jong-Kuk Choi, Joo-Hyung Ryu; GEO DATA. 2020;2(2):26-35. Published online December 30, 2020; DOI: https://doi.org/10.22761/DJ2020.2.2.005

Abstract PDF: The Hwangdo tidal flat has been subjected to local hydrodynamic changes caused by the construction of seawalls and bridges, which are changing the distribution of sediments and topographic characteristics. These changes would affect the sedimentary environments. It is essential to establish sedimentary environments dataset such as sediment distributions and elevation in order to understand the sedimentary environments and the pattern of change in the tidal flat. Therefore, between 2004 and 2013, data on sedimentary environmental factors such as surface sedimentary facies and elevation were obtained through the field survey, and soil moisture content of each sediment was measured to analysis the correlation between seawater and optical reflectance in the tidal flat. As a result, 12 sedimentary facies were distributed in the Hwangdo tidal flat, and the sand content and elevation gradually increased between 2004 and 2013. It was also shown that the amount of seawater present in the surface decreased as elevation and grain size increased. These data will be useful for understanding the changes in the sedimentary environments and for establishing plans for change and conservation management in Hwangdo tidal flat.

Ground-based data from wheat cropping fields in Australia for development of soil moisture retrieval algorithm using satellite images: SeungJae Lee, SunGu Lee, Dongryeol Ryu; GEO DATA. 2020;2(2):1-4. Published online December 30, 2020; DOI: https://doi.org/10.22761/DJ2020.2.2.001

Abstract PDF: Soil moisture is an important data which can be used for crop growth estimation, drought prediction, irrigation, and development of hydrological model. However, it is difficult to obtain soil moisture data from inaccessible area or very large area using only general field campaign. For this reason, many soil moisture retrieval algorithms have been developed based on satellite remote sensing technique. It should be noted that both satellite images and ground-based data for the region of interest are required to effectively develop the soil moisture retrieval algorithm using satellite images. Thus, Korea aerospace research institute, KARI, have collected ground-based data containing soil moisture, soil temperature, and crop height in collaboration with the university of Melbourne from wheat cropping fields in Australia which are suitable for the development of soil moisture retrieval algorithm. The ground-based data was collected from wheat cropping fields containing various types of soils for about 7 months from May 2019 to November 2019.

Search