Spatiotemporal Variation of Algae
in Saemangeum Lake Using Satellite Data

Currently, large-scale algal blooms (green tides) occur irregularly in Saemangeum Lake every year. Traditional water quality monitoring systems, which rely on ground-based observation networks, have limitations due to an insufficient number of monitoring points. This study aims to establish an effective in-lake chlorophyll monitoring system by utilizing deep learning models with input data that combine GOCI satellite imagery and ground-based observations. Through this approach, we can visualize deep learning-based chlorophyll concentration maps. Future research will focus on integrating chlorophyll concentration maps with in-lake and external water quality and hydrological data to analyze algal bloom occurrence and spread. Additionally, we aim to identify key factors affecting water quality and propose effective management strategies for water quality control and algal bloom prevention.