Strengthening Coastal Communities’ Resilience Through Better Forecasting and Projecting Compound Flood Risk

‘Soft-path’ measures, such as early warning and early action systems, real-time emergency management, insurance, and disaster financial risk hedging mechanisms, are examples of short-term solutions to increase coastal communities’ resilience to climate change. Long-term solutions for coastal community protection and increased resilience rely on ‘hard-path’ measures. Among these measures is the construction of coastal protection structures, including barriers, seawalls, and revetments, the reinforcement of houses and infrastructures, and the implementation of nature-based solutions, such as land use planning to reduce impervious surfaces and restore coastal ecosystems.

Hard infrastructures and nature-based solutions, while effective, face practical challenges. They necessitate huge and risky investments while subject to significant uncertainty regarding climate risk, government financial capacity, infrastructure investment decisions, and local land use regulation. These challenges can be overcome by modulating investments in time, integrating hard-path measures with soft-path solutions as hedging mechanisms, and using decision analytics methods and climate data to identify robust and optimal pathways.

Climate Services (CS) provide flood risk forecasts and projections to support these actions aimed at increasing coastal community resilience in the short and long term. Yet, many challenges hinder the uptake of current climate services for policy and decision-making, including forecasts and projections uncertainties, the limited skill of forecasts or the lack of understanding of the accuracy associated with the existing models and data, institutional barriers, and local technical/capacity limitations.

During his AXA Fellowship at Politecnico di Milano (Italy), Dr. Andrea Ficchì will use machine learning to address these various issues to better predict compound flood risk and identify the areas at highest risk. His research will focus mainly on Mozambique, one of the world’s most natural disaster-prone countries, with a high risk of compound floods caused by tropical cyclones. A multi-source flood extent and impact database will be used to assess the skill of current state-of-the-art predictions and guide the machine learning algorithms for their enhancements. The potential value of existing climate services and of the improved predictions will be demonstrated by focusing on their capacity to support humanitarian emergency management and weather-based insurance, considering the needs and preferences of local stakeholders and users of climate services.

Improving compound flood forecasting and better understanding uncertainties in future projections will help support humanitarian action, mitigate and better manage natural disaster risks, and make coastal communities more resilient to climate risk.

November 2022