Review article: Harnessing data-driven methods for climate multi-hazard and multi-risk assessment

Abstract

In recent years, interest in data-driven methods, such as machine learning and multivariate statistics for multi-hazard and multi-risk assessment has surged, due to their ability to integrate vast amounts of data in modelling complex non-linear relationships between hazard and risk factors. This review explores data-driven methods in climate multi-hazard and risk assessment, focusing on four themes: (i) data processing and collection; (ii) hazard identification, prediction and analysis; (iii) risk assessment; and (iv) future risk scenarios under climate change. Key findings highlight the extensive use of machine learning to combine Earth observations and climate data for downscaling and land use and land cover characterisation; the application of deep learning for hazard prediction; the use of ensemble methods for risk assessment; and the growing emphasis on explainable AI frameworks. Supervised machine learning approaches trained on historical impact data to project future climate risks have also emerged as a significant research area. Future research in this area should focus on modelling multi-hazard interactions, particularly triggering and cascading effects, integrating dynamic vulnerability and exposure factors, and addressing uncertainties associated with using machine learning for extrapolation. Advancements in Earth observations and textual data integration, alongside the development of open-access disaster catalogues, will also be crucial for improving multi-risk assessments and supporting AI-driven early warning systems tailored to regional needs.