Coupling environmental chemistry with Artificial Intelligence for coastal hazard risk assessment under climate change

Climate change represents a big threat to the coastal regions across the world, as they include hazards such as coastal erosion cycles, storm surges, and the increase in sea level, there by affecting people, infrastructure, and the ecosystem. This research paper seeks to design an integrated framework that will utilize the emerging technologies and predictive modeling to evaluate the risks that are caused by climate change in coastal areas. This approach combines machine learning algorithms (Random Forest (RF), Extreme Gradient Boosting (Boost), and K Nearest Neighbor (KNN)) with GIS to thoroughly assess the risks of hazards in coastal areas of United States - taking into account the impact of sea level rise, climate change scenarios, regional climate models and other environmental metrics. Based on ML and ArcGIS, the research will provide hazard predictions and their effects and project a probability map of risks that will establish areas of priority when it comes to interventions and allocation of resources on safety as well as risk mitigation efforts. Finally, the result of this study is a decision support tool that will improve coastal resilience through resource allocation decisions, safety planning, and risk mitigation approaches related to the rising rate of climate change.