Shoreline Extraction using High Resolution Satellite Imagery at Start Bay, UK

Coastlines are under pressure from the threat of future Sea Level Rise (SLR). Coastal engineers need a way to monitor shorelines changes over short- and long-term timescales, for the current and future protection of coastal communities. This study looks at the capabilities of high-resolution satellite imagery from Sentinel-2 (10m) and how a method can be developed to be able to extract consistent shorelines using coastal indicators as a proxy line. Start Bay, UK was used in this study to extract shoreline features using the Machine Learning (ML) techniques: Classification and Regression Trees (CART) and Artificial Neural Networks (ANN). The results highlight that the shoreline indicator, the wet/dry boundary can be extracted using the ML techniques with medium resolution satellite imagery with an average of <15m from validation datasets.