| Due to global warming, the Global Mean Sea Level (GMSL) has been rising at a faster rate over the past 200 years. Human quality of life is directly linked to sea level, as any increment in the GMSL has significant impacts on natural disasters, e.g., floods and storms. In the past, entire civilizations have vanished due to rising sea levels. Changes in coastlines resulting from rising sea levels can dramatically alter landscapes, causing coastal erosion and land loss, posing threats to human life and property. The changing geometry of a coast-line can be well understood through periodic physical surveys or satellite remote sensing, which is an efficient method for monitoring coastline fluctuations. In this paper, we focus on the calculation of the intrusion of the sea onto land over time using deep learning methods. The purpose of our work is to develop a model capable of segmenting water and land bodies through remote sensing satellite imagery, with the output applied to the calculation of coastal fluctuations over time. This model provides precise detection of shoreline changes, enabling accurate assessments of coastal dynamics, particularly in scenarios where satellite-based approaches face limitations. The success of this model will contribute to a better understanding of the dynamics of coastal regions, aiding in environmental monitoring. We expose the benefits of the approach by presenting results upon real satellite images and detect the potential use of the proposed system. |
*** Title, author list and abstract as submitted during Camera-Ready version delivery. Small changes that may have occurred during processing by Springer may not appear in this window.