Riparian monitoring using SAR image-based water body detection technique

Abstract

Sandbars on the riparian are ecologically important as they provide and protect habitats for organisms and act as natural septic tanks to filter and purify pollutants. In recent years, the role of sandbars in water pollution in rivers has been highlighted, and monitoring of the riparian is required. Sandbars are common in the lower reaches of deltas and at downstream of rivers, especially where the river is wide, and the flow velocity is relatively slow so that remote sensing can be used effectively. Synthetic Aperture Radar (SAR) imagery is an effective tool for spatial monitoring of the riparian because it provides high resolution and can detect regardless of weather conditions. In recent years, research has been conducted to use SAR imagery with AI to improve accuracy of detecting both riparian and sandbars. In this study, we utilized Sentinel-1 SAR (VV, VH polarized backscatter coefficient imagery), Sentinel-2 optical imagery Normalized Difference Water Index (NDWI), and Normalized Difference Vegetation Index (NDVI) data to identify changes of riparian and sandbars using AI-based clustering techniques. The confusion matrix is performed to validate the performance of deep learning techniques and waterbody detection. Technological advances in remote sensing will improve the data resolution of SAR and optical imagery, allowing detailed features to be observed. In further study is expected to improve the monitoring and management of sandbars on the riparian as monitoring technology advances. Keywords: Riparian, sandbars, Water body detection, Sentinel-1, Sentinel-2, Deep learning AcknowledgementThis work was supported by the “Development of Application Technologies and Supporting System for Microsatellite Constellation”project through the National Research Foundation of Korea(NRF) grant funded by the Korea government(MSIT) (No. 2021M1A3A4A11032019). 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」