Mapping Post-Rainfall Recovery in Arid Regions Using a Hierarchical U-Net

Abstract. The United Arab Emirates (UAE) experienced an extreme rainfall event between April 15 and 17, 2024, and that resulted in severe flooding in its coastal regions. Dubai was among the most affected regions. This study applies a hierarchical deep learning model on PlanetScope imagery to detect flood inundation, quantify flood extent by land cover, and examine short-term recovery dynamics. While earlier work detailed the methodological development of a hierarchical U-Net model (Hong et al., in press), here we emphasize its application for monitoring resilience trajectories in an arid urban environment. Results show that approximately 22 km² of land was flooded, with bare ground and built area most affected, while vegetation demonstrated greater resilience. Recovery dynamics reveal that vegetation and built area recovered rapidly within the first week, whereas bare ground recovered more slowly but continued to improve through the ten-day monitoring period. These findings highlight the importance of integrating fine-resolution satellite monitoring with deep learning approaches to better understand disaster recovery and inform urban resilience planning in desert cities.