Urbanization impacts ecosystem functions and services by fundamentally altering the balances between precipitation, water yield (Q), and evapotranspiration (ET) in watersheds. Accurate quantification of future hydrologic impacts is essential for national urban planning and watershed management decision making. We hypothesize that “hydrologic impacts of urbanization are not created equal” as a result of the large spatial variability in climate and land use/land cover change (LULCC). A monthly water balance model was validated and applied to quantify the hydrologic responses of 81,900 12‐digit Hydrologic Unit Code (HUC) watersheds to historical and projected LULC in 2000, 2010, 2050, and 2100 in the conterminous United States (CONUS). Stepwise regression and Geographically Weighted Regression models were used to identify key factors controlling the spatially varied hydrologic impacts across CONUS. Although the simulated impact of future urbanization on mean change in water yield (ΔQ) was small at the national level, significant changes (ΔQ > 50 mm/year) were found in 1,046 and 3,747 watersheds by 2050 and 2100, respectively. Hydrologic responses varied spatially and were more pronounced in the eastern United States. Overall, the impacts of urbanization on water yield were influenced by local climate, previous LULC characteristics, and the magnitude of changes in land use and impervious surfaces. The continued increase in impervious surface, especially in previously urbanized watersheds, and background precipitation contributed most to future ΔQ through both increase in direct runoff and reduction in ET. Effective national‐scale integrated watershed management strategies must consider local climatic and LULC conditions to minimize negative hydrologic impacts of urbanization.

The use of very-high-resolution images to extract urban, suburban and rural roads has important application value. However, it is still a problem to effectively extract the road area occluded by roadside tree canopy or high-rise buildings to maintain the integrity of the extracted road area, the smoothness of the sideline and the connectivity of the road network. This paper proposes an innovative Cascaded Attention DenseUNet (CADUNet) semantic segmentation model by embedding two attention modules, such as global attention and core attention modules, in the DenseUNet framework. First, a set of cascaded global attention modules are introduced to obtain the contextual information of the road; secondly, a set of cascaded core attention modules are embedded to ensure that the road information is transmitted to the greatest extent among the dense blocks in the network, and further assist the global attention module in acquiring multi-scale road information, thereby improving the connectivity of the road network while restoring the integrity of the road area shaded by the tree canopy and high-rise buildings. Based on binary cross entropy, an adaptive loss function is proposed for network parameter tuning. Experiments on the Massachusetts road dataset and the DeepGlobe-CVPR 2018 road dataset show that this semantic segmentation model can effectively extract the road area shaded by tree canopy and improve the connectivity of the road network.