• Korean Journal of Remote Sensing
• /
• v.39 no.6_1
• /
• pp.1341-1352
• /
• 2023

The normalized difference vegetation index (NDVI) derived from satellite images is a crucial tool to monitor forests and agriculture for broad areas because the periodic acquisition of the data is ensured. However, optical sensor-based vegetation indices(VI) are not accessible in some areas covered by clouds. This paper presented a synthetic aperture radar (SAR) based approach to retrieval of the optical sensor-based NDVI using machine learning. SAR system can observe the land surface day and night in all weather conditions. Radar vegetation indices (RVI) from the Sentinel-1 vertical-vertical (VV) and vertical-horizontal (VH) polarizations, surface elevation, and air temperature are used as the input features for an automated machine learning (AutoML) model to conduct the gap-filling of the Sentinel-2 NDVI. The mean bias error (MAE) was 7.214E-05, and the correlation coefficient (CC) was 0.878, demonstrating the feasibility of the proposed method. This approach can be applied to gap-free nationwide NDVI construction using Sentinel-1 and Sentinel-2 images for environmental monitoring and resource management.

• Korean Journal of Remote Sensing
• /
• v.39 no.5_3
• /
• pp.997-1008
• /
• 2023

Ship detection at sea can be performed in various ways. In particular, satellites can provide wide-area surveillance, and Synthetic Aperture Radar (SAR) imagery can be utilized day and night and in all weather conditions. To propose an efficient ship detection method from SAR images, this study aimed to apply the You Only Look Once Version 5 (YOLOv5) model to Sentinel-1 images and to analyze the difference between individual vs. integrated models and the accuracy characteristics by polarization. YOLOv5s, which has fewer and lighter parameters, and YOLOv5x, which has more parameters but higher accuracy, were used for the performance tests (1) by dividing each polarization into HH, HV, VH, and VV, and (2) by using images from all polarizations. All four experiments showed very similar and high accuracy of 0.977 ≤ AP@0.5 ≤ 0.998. This result suggests that the polarization integration model using lightweight YOLO models can be the most effective in terms of real-time system deployment. 19,582 images were used in this experiment. However, if other SAR images,such as Capella and ICEYE, are included in addition to Sentinel-1 images, a more flexible and accurate model for ship detection can be built.

• Journal of Korea Water Resources Association
• /
• v.56 no.12
• /
• pp.919-928
• /
• 2023

Rainfall characteristics in Korea are concentrated during the summer flood season. In particular, when a large amount of turbid water flows into the dam due to the increasing trend of concentrated rainfall due to abnormal rainfall and abnormal weather conditions, prolonged turbid water phenomenon occurs due to the overturning phenomenon. Much research is being conducted on turbid water prediction to solve these problems. To predict turbid water, turbid water data from the upstream inflow is required, but spatial and temporal data resolution is currently insufficient. To improve temporal resolution, the development of the Turbidity-SS conversion equation is necessary, and to improve spatial resolution, multi-item water quality measurement instrument (YSI), Laser In-Situ Scattering and Transmissometry (LISST), and hyperspectral sensors are needed. Sensor-based measurement can improve the spatial resolution of turbid water by measuring line and surface unit data. In addition, in the case of LISST-200X, it is possible to collect data on particle size, etc., so it can be used in the Turbidity-SS conversion equation for fraction (Clay: Silt: Sand). In addition, among recent remote sensing methods, the spatial distribution of turbid water can be presented when using UAVs with higher spatial and temporal resolutions than other payloads and hyperspectral sensors with high spectral and radiometric resolutions. Therefore, in this study, the Turbidity-SS conversion equation was calculated according to the fraction through laboratory analysis using LISST-200X and YSI-EXO, and sensor-based field measurements including UAV (Matrice 600) and hyperspectral sensor (microHSI 410 SHARK) were used. Through this, the spatial distribution of turbidity and suspended sediment concentration, and the turbidity calculated using the Turbidity-SS conversion equation based on the measured suspended sediment concentration, was presented. Through this, we attempted to review the applicability of the Turbidity-SS conversion equation and understand the current status of turbid water occurrence.