Scientific site selection for urban parks is an important way to increase urban resilience and safeguard people’s well-being. Aiming at the lack of systematic consideration in the traditional park siting research, this study utilizes geographically weighted regression to explore the various characteristic factors affecting the spatial distribution of parks, and based on this, combines the random forest model and the interpretable model to accurately assess the potential of parks on urban land in Shenzhen and provide the basis for site selection. The study indicates that: ① Shenzhen’s parks exhibit complex differentiation characteristics in terms of natural landscape elements and the intensity of economic activities; ② The geographically weighted random forest (GWRF) model has better learning and generalization capabilities compared to the random forest (RF) model, and the average accuracy of the GWRF model is improved by 0.04 compared to the traditional RF model; ③ The park’s development potential is divided according to the results of the GWRF model, with 52.01% denoted as the potential incubation zone, 21.15% the potential accumulation zone, 8.25% the potential growth zone, and 18.59% the potential core zone; ④ Through interpretability analysis, it is identified that vegetation coverage, the density of tourist attractions or points of interest (POI), slope, elevation, and nighttime light intensity are the most significant factors affecting park development potential, while the distance to roads and the distance to bodies of water are the least influential factors. The research systematically explores a quantitative evaluation framework for the development potential of Shenzhen’s parks, opening new theoretical pathways and practical paradigms for the sustainable development planning of Shenzhen under the “Park City” concept.

Land-use allocation models can effectively support sustainable land use. A large number of studies solve the problems of land-use planning by constructing models, such as mathematical models and spatial analysis models. However, these models fail to fully and comprehensively consider three uncertain factors of land-use systems: randomness, interval and fuzziness. 33Therefore, through the study of the watershed land-use system, this paper develops a land-use allocation model considering the regional land–society–economy–environment system under uncertain conditions. On the basis of this model, an interval fuzzy two-stage random land-use allocation model (IFTSP-LUAM) combining social, economic and ecological factors is proposed to provide sustainable development strategies at the basin level. In addition, the proposed IFTSP-LUAM takes into account the above three uncertainties and multistage, multiobjective, dynamic, systematic and complex characteristics of typical land-use planning systems. The results showed that the model considers more socioeconomic and ecological factors and can effectively reflect the quantitative relationship between the increase in economic benefits and the decrease in environmental costs of a land-use system. The model was applied to land-use planning of Nansihu River Basin in Shandong Province. The results provided a series of suitable land-use patterns and environmental emission scenarios under uncertain conditions, which can help the watershed environmental protection bureau and watershed land-use decision-makers to formulate appropriate land-use policies, so as to balance social and economic development and ecological protection. The simulation results can provide support for an in-depth analysis of land-use patterns and the trade-off between economic development and ecological environment protection.