Design of a Hierarchical Planning System for Plant Landscape Space under the Background of Big Data

With the increasing demand for refined urban landscape construction, traditional plant landscape planning methods have problems such as reliance on experience-based judgment, difficulty in identifying hierarchical conflicts, and insufficient stability of planning results in terms of spatial hierarchy expression, structural synergy, and quantitative decision-making. To address this, this paper constructs a hierarchical spatial planning system for plant landscapes under big data conditions. By standardizing and vectorizing multi-source plant landscape data, a hierarchical decision-making model integrating spatial hierarchy identification, conflict detection, and planning optimization is established. Based on indicators such as spatial density, hierarchical continuity, and shading relationships, the system automatically identifies the vertical and planar hierarchies of plant landscapes and drives iterative optimization of planning schemes through objective functions and constraints. The experimental results show that under different planning scenarios, the average hierarchical continuity of the system generated scheme remains between 0.79-0.85 (Case-2 to Case-3), the spatial conflict rate is controlled within the range of 0.078-0.114, the functional partition balance is higher than 0.91, and the comprehensive objective function value J shows a stable convergence trend with the change of scene complexity (18.5-25.3). The results indicate that this method can effectively improve the continuity and coordination of the spatial hierarchy of plant landscapes, providing a feasible systematic technical path for data-driven fine planning of plant landscapes.