High-Resolution Water Body Detection Using CAS500 in Korean Peninsula

The effective management and monitoring of water resources is imperative for the ecosystem and environmental conservation. Satellite remote sensing data is an efficient tool for detecting water resources such as rivers, reservoirs, and lakes. In addition, it is crucial for the management and prevention of water disasters. Optical satellite data can be used to detect water bodies with high accuracy using Near-Infrared (NIR) imagery and Normalized difference water index (NDWI). Optical satellite images used for water body detection are mainly medium-resolution satellite images such as those Landsat series and Sentinel-2. However, there is a limitation that the medium-resolution satellite images are less effective in detecting small water bodies and boundaries due to their spatial resolution constraints. To address this, high-resolution satellite imagery and advanced analytical techniques, such as deep learning, can be utilized. In this study, deep learning techniques were applied to CAS 500 images with 2 m resolution to detect water bodies. The water body detection performance was validate using manual mask data and evaluation metrics based on a confusion matrix. Furthermore, water body detection performance was compared with Sentinel-2 (10 m) and Planet Scope (3.7 m) satellite imageries. The results of this study are expected to provide high accuracy water body detection results under various environmental conditions.

 

Keywords: Water Body Detection, High-Resolution, CAS500, Deep Learning

 

Acknowledgement

This research was supported by the BK21 FOUR (Fostering Outstanding Universities for Research) funded by the Ministry of Education (MOE, Korea) and National Research Foundation of Korea (NRF). This work is financially supported by Korea Ministry of Land, Infrastructure and Transport (MOLIT) as 「Innovative Talent Education Program for Smart City」. This work was supported by Korea Environment Industry & Technology Institute (KEITI) through Research and Development on the Technology for Securing the Water Resources Stability in Response to Future Change Project, funded by Korea Ministry of Environment (MOE)(RS-2024-00332300). This work was supported by the National Research Foundation of Korea (NRF) grant funded by the Korea government (MSIT) (RS-2024-00416443). This work was supported by the National Research Foundation of Korea (NRF) grant funded by the Korea government (MSIT) (NRF-2022R1A2C2010266). This work was supported by Korea Environment Industry & Technology Institute (KEITI) through Water Management Program for Drought Project, funded by Korea Ministry of Environment (MOE) (RS-2023-00230286).