Forecasting the deformation and movement of cumulus clouds provides an important basis for ultra-short-term solar irradiance nowcasting in photovoltaic (PV) power generation. Existing methods mainly use two-dimensional (2D) ground-based sky images for forecasting, which have limited ability to represent the three-dimensional (3D) spatial structure of cumulus clouds and the influence of wind on cloud motion. In this study, we propose a wind-aware ultra-short-term spatiotemporal forecasting model for 3D cumulus clouds, termed three-dimensional Cloud Long Short-Term Memory with Wind Gate Recurrent Unit (3dCLSTM + WindGRU). The model uses 3dCLSTM to learn the spatial structure and temporal evolution of 3D voxel cumulus cloud sequences, and embeds a WindGRU unit between 3dCLSTM layers to introduce wind speed and wind direction information for wind-driven transient motion modeling. Experiments were conducted on 1-min and 10-min 3D cumulus cloud datasets reconstructed from ground-based sky image datasets collected at sites in California and Colorado, USA. All voxel sequences were resampled to 64 × 64 × 64, with five-step prediction for the 1-min dataset and three-step prediction for the 10-min dataset. The results show that 3dCLSTM achieved a structural similarity index measure (SSIM) of 0.7913 on the 1-min dataset, while 3dCLSTM + WindGRU achieved the best performance on the 10-min dataset, with an SSIM of 0.3512 and a peak signal-to-noise ratio (PSNR) of 18.3625. Compared with 3dCLSTM, introducing WindGRU improved the SSIM by 4.8% on the 10-min dataset, with a more evident improvement under relatively high wind-speed conditions. These results indicate that wind-aware volumetric spatiotemporal modeling can support ultra-short-term 3D cumulus cloud forecasting and provide a useful technical basis for solar irradiance nowcasting.
Multi-scenario flood simulation supports urban flood-risk assessment, but scenario-specific outputs are difficult to use to identify facility-level risk evolution and critical risk conditions. This study proposes a multi-scenario flood risk reasoning method for critical urban facilities based on facility–scenario risk chains (FSRCs). The method constructs internally comparable rainfall–inundation scenario subsets, anchors each facility to a fixed triangular mesh cell, and organizes inundation depths and depth-based risk states into ordered chains. Boundary-crossing reasoning is then used to derive scenario-context-dependent critical rainfall threshold (CRT) estimates and ordered risk-state transition sequences. The method was evaluated in the Hexi drainage area of Nanjing, China, using 184 rainfall–inundation scenarios and 241 critical facilities. The results show that accumulated rainfall alone is insufficient for consistent risk ordering across different rainfall durations, while facility risk states vary across comparable rainfall-ordered scenario sequences. Representative facilities exhibited distinct CRT positions and transition intervals. Sensitivity analysis showed that CRT estimates varied with scenario spacing, while a computational consistency assessment confirmed the reproducibility of boundary-crossing results. The proposed method transforms discrete flood simulation outputs into structured object-level risk knowledge, supporting facility-level risk screening, risk-state comparison, and subsequent knowledge-driven applications.