Rapid urbanization can change local climate by increasing land surface temperature (LST), particularly in metropolitan regions. This study uses two decades of remote sensing data to investigate how urbanization-induced changes in land use/land cover (LULC) affect LST in the Beijing Region, China. By focusing on the key issue of LST and its contributing variables through buffer zones, we determined how variables influence LST across buffer zones—core, transit, and suburban areas. This approach is crucial for identifying and prioritizing key variables in each zone, enabling targeted, zone-specific measures that can more effectively mitigate LST rise. The main driving variables for the Beijing Region were determined, and the spatial-temporal relationship between LST and driving variables was investigated using a geographically weighted regression (GWR) model. The results demonstrate that the Beijing Region’s LST climbed from 2002 to 2022, with increases of 0.904, 0.768, and 0.248 °C in core, transit, and suburban areas, respectively. The study found that human-induced variables contributed significantly to the increase in LST across core and transit areas. Meanwhile, natural variables in suburban areas predominated and contributed to stabilizing local climates and cooling. Over two decades and in all buffer zones, GWR models slightly outperformed ordinary least squares (OLS) models, suggesting that the LST is highly influenced by its local geographical location, incorporating natural and human-induced variables. The results of this study have substantial implications for designing methods to mitigate LST across the three buffer zones in the Beijing Region.

Global warming profoundly affects hydrological processes and regional aridity. However, the shifts in the arid–humid transition zone and its relationship to divergent surface and subsurface hydrological responses remain not fully understood. This study investigates the spatiotemporal aridity changes in China using hydroclimate datasets (1950–2022) and examines associated hydrological responses via remote sensing (RS) since the early 2000s. The results reveal that: (1) a pronounced ~32-year oscillatory pattern governs both the expansion and contraction of drylands and non-drylands, with China currently in a wetting phase; (2) a distinct climatic transitional zone is identified, and a distinct boundary emerges separating drylands and non-drylands, here referred to as China’s Arid–Humid Divide, reflecting the climatic equilibrium shaped by multiple monsoon systems and local topography; and (3) the nationwide expansion of surface water bodies, following the increase of groundwater storage in partial areas, was detected via recent RS data. These findings provide new insights into the mechanisms driving long-term aridity transitions and support climate adaptation and sustainable land management in China.

Traffic network partitioning studies show that road networks can be divided into spatially connected subregions with relatively homogeneous traffic states, whose composition may evolve with congestion. However, many hierarchical traffic forecasting models rely on offline or globally shared node-to-region relationships that remain fixed across input windows. We propose DH-STGCN, an input-conditioned dynamic hierarchical spatiotemporal graph convolutional network for traffic flow prediction. The model generates a window-specific soft node-to-region assignment from current spatiotemporal node representations, constructs corresponding regional representations and a regional graph, performs spatiotemporal learning at both sensor and regional scales, and feeds regional information back to the sensor scale. Aggregation consistency and region balancing are used as auxiliary structural regularizers. Experiments on PeMSD3, PeMSD4, PeMSD7, and PeMSD8 show that DH-STGCN reduces average MAE by 3.5–8.2% relative to STGCN and by 2.3–8.2% relative to HGCN. Relative to the strongest competing models, performance is dataset-dependent: Graph WaveNet achieves lower mean MAE on PeMSD3, PeMSD4, and PeMSD7, whereas DH-STGCN performs better on PeMSD8. Controlled hierarchy comparisons favor the window-conditioned assignment over fixed-uniform, static-hard, globally shared, and alternative differentiable assignments. Diagnostic analyses further show that the learned memberships are diffuse yet measurably nonuniform, change across consecutive input windows, and produce distinguishable regional representations. Overall, DH-STGCN provides a flexible input-conditioned hierarchical representation for multistep traffic flow prediction.