Development of a Smart Coastal Environment Management System in Incheon Using Remote Sensing and AI-based Analysis of Marine Debris Distribution Jeon H., Cho H., Jang S.T., Yoon D.H., Choi K.S., Lee S.W., Kim T.H.
Ocean Convergence Division, Underwater Survey Technology 21. Inc., Korea
Aviation Center, Incheon Technopark, Korea
Aviation Department, Incheon Metropolitan City, Korea
Abstract
Marine Debris, a byproduct of human activities, is often discharged, dumped, or abandoned along coastlines. This not only leads to the destruction of marine habitats but also causes significant economic losses by hindering vessel navigation, reducing fisheries productivity, and degrading coastal landscapes, thereby negatively impacting the tourism industry. To address the issue of marine debris, the international community is actively advancing monitoring systems that utilize advanced technologies such as satellite remote sensing, drones, and AI-based analysis. This technology-driven approach moves beyond conventional methods reliant on visual observation or uncertain estimations, enabling more precise and systematic responses through high-resolution spatial data and temporal change analysis. Korea is also actively promoting the adoption of monitoring systems utilizing advanced technologies. Through this approach, the country aims to establish strategic debris collection measures-such as the designation of priority management areas and the determination of optimal collection periods-based on scientific evidence. Located in the mid-northern part of the Yellow Sea, Incheon is a semi-enclosed coastal area where sea water exchange is limited, creating conditions that allow external inputs such as marine debris to accumulate easily. These environmental characteristics make it well-suited for applying image-based detection technologies and analyzing spatiotemporal variation patterns. This suitability makes Incheon an ideal location for demonstrating national marine debris policies and introducing advanced monitoring technologies, which is why it has been selected as a target site for various pilot projects. In this study, high-resolution SkySat satellite imagery (spatial resolution: ~0.5 m) was used to develop a machine learning model based on the spectral reflectance characteristics of two target materials-white styrofoam and orange buoys. The model was applied to detect and classify beach litter in island regions of Ongjin County, Incheon, on a monthly basis, with the aim of analyzing the spatiotemporal changes in litter distribution over time. In addition, simulated beach litter larger than 1 meter in size was placed along the shoreline, and spectral data were acquired using a hyperspectral camera mounted on an unmanned aerial vehicle (UAV). This field-based assessment aimed to explore more precise detection and analysis of beach litter compared to high-resolution satellite imagery. The detection results obtained using remote sensing technology and machine learning models are provided through the Marine Keeper platform(http://mk.helios.pe.kr) as time-series graphs of beach litter by type, along with map-based location information. The accumulated monthly detection results are used to generate spatiotemporal distribution forecasts through AI-based prediction technology. Such AI-driven spatiotemporal analysis and prediction are expected to support data-driven decision-making and serve as a foundation for establishing monitoring standards, ultimately contributing to the improved efficiency of coastal environmental management strategies.
