Answers are grounded in this paper and cite their sources.
Achieving sustainability and environmental quality, public safety and economic development are complex trade-offs in urban land-use planning. These goals are typically planned separately, which reduces their ability to put together solutions that are both balanced and sustainable. This study suggests a framework for multi-objective optimisation, which combines data-driven predictive modelling, feature sensitivity analysis and evolutionary optimization, for sustainable urban land use. A surrogate model called A Histogram Based Gradient Boosting (HistGB) is created to explore the nonlinear relationships between 15 sustainability indicators, and the hyper parameters of HistGB are optimized by Novel Hybrid Kepler Optimization Algorithm (NOHKOA). The Dynamic Trade-off Coefficient Selection Multi-Objective (DTCSMO) algorithm is then used to optimize conflicting sustainability, environmental burden and urban risk goals while integrating continuous and discrete planning variables. The coefficient of determination for the test data reaches 0.9877 and the mean absolute error (MAE) is 0.0152 and the root mean squared error (RMSE) is 0.0193 for the HistGB model. For feature sensitivity analysis, the most sensitive features are green cover (mean change in coefficient of determination: 0.8196) and renewable energy use (mean change in coefficient of determination: 0.3584). The results of the ablation experiment also show the significance of the environmental indicator, and the test coefficient of determination drops to 0.1542 when the environmental indicator is removed. The DTCSMO algorithm can produce 120 Pareto-optimal solutions, allowing decision makers to consider different trade-offs between the planning goals. For the evaluation of the characteristics of the solutions a comparison with the multi-objective particle swarm optimization algorithm is additionally provided. In summary, the proposed framework provides a data-driven method for urban land-use planning that is accurate, interprets the data through sensitivity analysis and incorporates multiple objectives in decision making.
No takes yet. Share an insight, caveat, or question.
崔 et al. (2026) studied this question.
Synapse has enriched 8 closely related papers on similar clinical questions. Consider them for comparative context: