An improved knowledge-informed NSGA-II for multi-objective land allocation (MOLA)

Abstract

Multi-objective land allocation (MOLA) can be regarded as a spatial optimization problem that allocates appropriate use to certain land units subjecting to multiple objectives and constraints. This article develops an improved knowledge-informed non-dominated sorting genetic algorithm II (NSGA-II) for solving the MOLA problem by integrating the patch-based, edge growing/decreasing, neighborhood, and constraint steering rules. By applying both the classical and the knowledge-informed NSGA-II to a simulated planning area of 30 × 30 grid, we find that: when compared to the classical NSGA-II, the knowledge-informed NSGA-II consistently produces solutions much closer to the true Pareto front within shorter computation time without sacrificing the solution diversity; the knowledge-informed NSGA-II is more effective and more efficient in encouraging compact land allocation; the solutions produced by the knowledge-informed have less scattered/isolated land units and provide a good compromise between construction sprawl and conservation land protection. The better performance proves that knowledge-informed NSGA-II is a more reasonable and desirable approach in the planning context.