In recent years, precipitation extremes in China have increased due to global warming, posing a significant threat to human life and property. It is thus crucial to understand the changes in population exposure to precipitation extremes and the causes of these changes, since complex terrain areas are not accurately simulated by rain gauge interpolation data. Thus, we first used three satellite-based precipitation products—TRMM 3B42, CHIRPS, and CMORPH—combined with population data to analyze the spatiotemporal changes of precipitation extremes and population exposure from 1998 to 2019 in the Beijing–Tianjin–Hebei (BTH) region. In addition, the contributions of population, climate, and composite factors were quantified. The results showed that TRMM 3B42 outperformed the other two datasets in the BTH region. Over the past 22 years, the precipitation extremes in the central and northeastern regions, especially in Beijing, reached 2.5 days per decade, while the northern and southern regions showed a downward trend. The highest population exposure was mainly concentrated in central Beijing, most areas of Tianjin, and the urban centers of cities in southeastern Hebei province. Compared to the 2000s, a significant increase in exposure was observed in Beijing, Tianjin, and Zhangjiakou in the 2010s, whereas other regions showed negligible changes during this period. Climatic factors had the greatest influence on population exposure in most cities such as Qinhuangdao and Hengshui, where their climatic contribution exceeded 70%. While population change was more responsible for the increase in population exposure in the densely populated cities such as Tianjin, Handan, and Langfang, these cities contributed over 60% of the population. The interaction effect in Beijing and Tianjin was relatively obvious. The results of this study can provide a scientific basis for formulating targeted disaster risk management measures against climate change in the BTH region.

Urban pluvial flooding shows clear temporal accumulation, delayed response, and spatial heterogeneity. Better flood-depth prediction from a spatiotemporal coupling perspective can support urban flood risk identification and refined management. This study develops a spatiotemporal prediction model that integrates a Transformer and graph neural network (GNN). The Transformer module captures temporal dependencies in rainfall processes and flood-depth evolution. The graph attention network (GAT) represents spatial associations constrained by terrain, drainage networks, and neighboring spatial relationships. A fusion attention mechanism then adaptively couples temporal and spatial features. This study uses multi-source data, including hourly meteorological observations, terrain, land cover, drainage networks, and water-system data. It selects the heavy rainfall event caused by Typhoon In-Fa in Huai’an City in July 2021 as a typical case. The study analyzes the temporal evolution of regional average flood depth and the spatial differentiation of inundated grid cells at the municipal scale. The results show three main findings. First, during the typical heavy rainfall event, regional average flood depth follows a continuous process of low-level stability, sustained rise, rapid increase, delayed peak, slow recession at a high level, and rapid recession. The flood peak lags behind the rainfall peak by about 3 h. This result indicates clear accumulation and delayed response in urban pluvial flooding. Second, at the municipal scale, inundated grid cells show a pattern of concentrated distribution in urban built-up areas, secondary distribution in county-level built-up areas, and scattered distribution in non-construction land. Different depth grades also show clear hierarchical differentiation. Mild and moderate inundation covers a wider area. Medium-high inundation concentrates locally. High-grade inundation appears as a small number of nested high-value cells. Third, the spatial differentiation of medium- and high-grade inundated grid cells does not result from low-lying terrain or construction land alone. It forms under the combined effects of low-lying terrain, local relative depressions, and impervious surfaces in construction land. This pattern shows clear built-up-area clustering, grade differentiation, and land-cover correspondence. The results provide methodological support and decision references for urban flood risk identification, grid-based risk management, and emergency dispatch during extreme rainfall.