Introduction: The construction of digital governance of national land space depends greatly on the development of a digital model for robust control of water and ecological space. However, how changes to the urban-water coupling relationships affect the resilience control of water ecological space is rarely reported.Methods: The evolution characteristics of urban and water space in the study area from 2000 to 2020 and the correlation between them are analyzed based on the grid analysis using InVEST and Moran’I methods. Based on the theory of human-environment interaction territorial system to provide a theoretical framework to explain the urban and water space. We used digital to construct an resilience control framework in the Dongting Lake area based on the correlation between the urban and water space.Results: The results show that: 1) From 2000 to 2020, the geographical evolution of towns and cities in the research area displayed obvious spatial variation in intensity, indicating a process of expansion and change. The regional and temporal fluctuations of the water conservation function are significant. The mountainous areas in the east, south, and northwest are where the high values of the water conservation function are primarily found. These regions have more vegetation, which increases the water conservation function. 2) According to the results of local binary spatial autocorrelation analysis, it can be seen that from 2000 to 2020, the high-high agglomeration of town space and water-related is mainly distributed in Linxiang City, Yueyang County, Miluo City, Li County, and Yiyang City, and the low-low agglomeration is mainly distributed in Dongting Lake, Datong Lake, and along the Yangtze River. 3) Based on how urban spatial evolution affects water ecological space, we construct a theoretical framework of urban-water coupling and establish a digital model of water ecological space resilience control in the Dongting Lake area from four perspectives: threshold, visualization, dynamics, and intelligence.

The factors influencing urban pluvial flooding in cities with complex topography, such as hill–basin systems, are highly nonlinear and spatially heterogeneous due to the interplay between rugged terrain and intensive human activities. However, previous research has predominantly focused on plain, mountainous, and coastal cities. As a result, the waterlogging mechanisms in hill–basin areas remain notably understudied. In this study, we developed a geographically explainable artificial intelligence (GeoXAI) framework integrating Geographical Machine Learning Regression (GeoMLR) and Geographical Shapley (GeoShapley) values to analyze nonlinear impacts of flooding factors in Changsha, a typical hill–basin city. The XGBoost model was employed to predict flooding risk (validation AUC = 0.8597, R² = 0.8973), while the GeoMLR model verified stable nonlinear driving relationships between factors and flooding susceptibility (test set R² = 0.7546)—both supporting the proposal of targeted zonal regulation strategies. Results indicated that impervious surface density (ISD), normalized difference vegetation index (NDVI), and slope are the dominant drivers of flooding, with each exhibiting distinct nonlinear threshold effects (ISD > 0.35, NDVI < 0.70, Slope < 5°) that differ significantly from those identified in plain, mountainous, or coastal regions. Spatial analysis further revealed that topography regulates flooding by controlling convergence pathways and flow velocity, while vegetation mitigates flooding through enhanced interception and infiltration, showing complementary effects across zones. Based on these findings, we proposed tailored zonal management strategies. This study not only advances the mechanistic understanding of urban waterlogging in hill–basin regions but also provides a transferable GeoXAI framework offering a robust methodological foundation for flood resilience planning in topographically complex cities.

The microclimate of traditional blocks, a key component of urban fabric, directly affects the overall urban thermal environment. Creating a suitable microclimate is crucial for improving urban living quality. Field measurements, ENVI-met simulations, and the PET index were used to analyze the spatiotemporal variations and core drivers of thermal comfort. Temporally, five open space types showed a unimodal “rise–stabilization–fall” PET curve, with peak heat stress occurring at 11:00–14:00. Courtyards heated fastest, but green spaces had the most stable thermal environment because trees provided shading and transpiration for gentle cooling. Spatially, thermal comfort varied significantly. For example, green spaces rich in trees performed best (PET 5–8 °C lower than pure grassland), while squares and courtyards faced severe midday heat stress (PET mostly moderate or above). Alley comfort depended on aspect ratio and orientation—north–south alleys with an aspect ratio > 2 were 2–3 °C cooler than open spaces, but east–west or narrower alleys (aspect ratio < 1.5) and low-enclosed courtyard control apply to southern Hunan’s hot-humid zone. However, the synergistic principles can be extended to similar southern regions, providing technical reference for traditional block livability and climate-resilient cities.

Urbanization-induced land use transition results in a decline in ecosystem services, which has implications for regional ecological security. In order to explore the relationship between ecosystem services and land use transition, this paper utilizes the InVEST model, geographically weighted regression model to examine the impact of land use transition on ecosystem services in the Dongting Lake area (DLA). The results showed that (1) During the period 2000-2020, the intensity and motivation of land-use transition showed obvious spatial and temporal heterogeneity with the variation of urbanization development. (2) Habitat quality and Carbon sequestrations showed a downward trend. In contrast, food supply followed an upward trend; soil conservation and water yield services initially increased and dropped later. The overall spatial changes in habitat quality and Carbon sequestration appear to be insignificant. Food supply shows significant differences in the plains compared to other areas; while soil conservation and water yield service shows significant changes in places other than the DLA. (3) From 2000 to 2020, land use transition dynamics, population density, GDP density, night lighting and transition intensity had mainly negative effects on ecosystem services. Only the Normalized Vegetation Index (NDVI) showed a positive effect on ecosystem services. The results of the research will provide valuable references for the development and implementation of spatial ecological restoration planning and land use policies in the national territory.