•  
  •  
 

Abstract

The coastline stands as a critical domain encompassing industry and the environment. The escalating global warming, leading to elevated sea levels and intensified wave-current interactions, has given rise to substantial coastal erosion. This predicament, in conjunction with excessive human development and Taiwan's coastal areas' extreme climatic impact, accentuates the perceptibility of coastal beach alterations. As a result, coastal erosion has emerged as a pressing issue necessitating resolution. Traditional methodologies for assessing coastline changes have conventionally relied on manual measurements. However, owing to the fluctuating distance of coastlines, influenced by tidal patterns, extended measurement processes over several months are susceptible to temporal influences, thereby yielding errors. This approach incurs substantial time, costs, and human resources. Hence, the rapid and accurate prediction of shoreline locations, their dynamic changes, and future trends is pivotal for aquatic cultivation, development, navigation, and transportation in coastal realms. In this study, a coastal transformation model based on a deep learning framework is developed to predict coastline alterations by analyzing satellite images, thereby conserving time, effort, and expenses. The research outcomes indicate that the Gated Recurrent Unit (GRU) achieves the most favorable results in terms of error rates. The mean absolute percentage error and root mean square error are notably low, standing at 1.28×10−404 and 187.9291, respectively. This network demonstrates an average prediction time of 4.658 seconds, thus showcasing elevated velocity and precision. The aforementioned network can be used to explore the effects of comprehensive coastal protection schemes on coastal erosion and to analyze future shoreline changes to facilitate policymaking by relevant governmental organizations.

Download
COinS