Artificial Intelligence-based Spatiotemporal Assessment of Historical and Future Shoreline Dynamics: Case Study of Benin Republic

Abstract

Global Sea Level Rise (SLR), especially caused by global warming, highly threatens the coastal countries by causing coastal erosions, biodiversity loss, coastal flooding, etc. The study of shoreline dynamics is a key aspect of coastal area management, and is useful for reducing risk and vulnerability to climate change within coastal ecosystems. Artificial Intelligence (AI) is an efficient approach to this type of problem because of its advanced multidimensional data extraction and computational tools. This study uses AI methodologies combined with Remote Sensing (RS) and Geographic Information Systems (GIS) tools to perform a spatiotemporal analysis of the shoreline dynamics of the Republic of Benin from 2001 to 2021. Preprocessed multispectral and multitemporal Landsat 5, 7 and 8 surface reflectance images as well as the NASA Shuttle Radar Topography Mission (SRTM) digital elevation data were extracted from the Data Catalog of Google Earth Engine (GEE). Then, the cloud computing platform of GEE was used to perform binary (Sea Water / Non-Sea Water) supervised image classification. The Machine Learning algorithms used were Support Vector Machines (SVM) and Random Forest (RF). QGIS was used to extract historical shorelines from the respective classified images in 5-year intervals. Net Shoreline Movement (NSM), End Point Rate (EPR), Linear Regression Rate (LRR) and Weighted Linear regression Rate (WLR) were the shoreline change statistics derived from Digital Shoreline Analysis System (DSAS), a plugin of ArcGIS. Then, the Kalman Filter model, implemented in the DSAS plugin, was used to provide a “beta” forecast of the shoreline shape respectively for the years 2031 and 2041, with a confidence interval of 90%. A geostatistical analysis of the results mainly showed, for the study period, a clear coastal erosion trend at average rates of -2.17 ± 0.28 m (EPR), -1.51 ± 1.68 m (LRR). A sectorial and deeper analysis revealed that, in terms of NSM, the West side of the Port infrastructure underwent more accretion (41.67% against 25.71% at the East) while the East side experienced more erosion (74.29% against 58.33% at the West). Assuming a Business-as-Usual (BaU) scenario, the projected highest erosion values were found to be -226.42 m (2031) and -146.14 m (2041) in the locality of Avloh plage (Grand-Popo), -68.11 m (2031) and -182.55 m (2041) in the locality of Hillacondji (Grand-Popo), -146.14 m (2031) and -307.30 m (2041) in the locality of Agblangandan (Cotonou). Finally, a web application was designed and implemented to facilitate an easy data access and visualization of results by non-experts and decision makers.