Advancing Coastal Monitoring: Integrating Spatiotemporal Analyses and Machine Algorithms in G-CAS

Oyedotun, T.D.T.; Hamer, E.; Nedd, A.G., and Burningham, H., 2024. Advancing coastal monitoring: Integrating spatiotemporal analyses and machine algorithms in G-CAS. In: Phillips, M.R.; Al-Naemi, S., and Duarte, C.M. (eds.), Coastlines under Global Change: Proceedings from the International Coastal Symposium (ICS) 2024 (Doha, Qatar). Journal of Coastal Research, Special Issue No. 113, pp. 315-320. Charlotte (North Carolina), ISSN 0749-0208 The diverse role that climate change plays in coastal environments includes changing spatiotemporal patterns in flood and erosion risk which impacts vital coastal infrastructure supporting significant coastal populations, and critical habitats supporting important species. The intricate interplay between climate change and coastal areas necessitates comprehensive adaptation strategies and more sustainable development practices, that should be supported with near-real-time monitoring that can mitigate the adverse effects on, and improve the resilience of, these critical regions. This study explores the application of spatial analyses, data fusion, time-series methodologies, and machine algorithms in the development of the Guyana Coastal Analysis System (G-CAS). G-CAS, a prototype online system, is being designed for the monitoring and analysis of coastal dynamics in a local region of Guyana. The primary objective is to enhance the understanding of complex coastal processes and provide a tool for coastline management and conservation. Here, the spatial analyses undertaken in G-CAS facilitate the fusion of geospatial data, enabling a comprehensive understanding of the dynamic interplay between various environmental factors. By incorporating time-series methodologies and machine learning algorithms, the prototype system being developed in Google Earth Engine captures temporal trends, facilitating the identification of short- and long-term patterns and anomalies of coastlines critical for informed decision-making. Findings from this research show the potential of this low-cost online tool for coastal monitoring, serving as a model for other coastal areas facing similar challenges.