Global Flood Projection and Socioeconomic Implications Under a Deep Learning Framework

Abstract

As the planet warms, the frequency and severity of weather-related hazards such as floods are intensifying, posing substantial threats to communities around the globe. Rising flood peaks and volumes claim lives, damage infrastructure, and compromise access to essential services. However, the physical mechanisms behind global flood evolution are still uncertain, and their implications for socioeconomic systems remain unclear. In this study, we leverage a supervised machine learning technique to identify the dominant factors influencing daily streamflow. We then develop a physics-constrained cascade model chain which assimilates water and heat transport processes to project the bivariate risk of flood peak and volume, along with its socioeconomic consequences. To achieve this, we develop a hybrid deep-learning-hydrological model with bias-corrected outputs from 20 global climate models from CMIP6 under four shared socioeconomic pathways. Our results project considerable increases in flood risk under the medium to high-end emission scenario (SSP3-7.0) over most catchments of the globe. The median future joint return period decreases from 50 years to around 27.6 years, with 186 trillion USD and 4 billion people exposed. Downwelling shortwave radiation is identified as the dominant factor driving changes in daily streamflow, accelerating both terrestrial evapotranspiration and snowmelt. As future scenarios project enhanced global warming along with an increase in precipitation extremes, a heightened risk of widespread flooding is foreseen. This study aims to provide valuable insights for policymakers developing proactive strategies to mitigate the risks associated with river flooding under climate change.