Combining system dynamics and hybrid particle swarm optimization for land use allocation

• Land use allocation problem has been encountered in many fields of applications.
• Most of land use allocation models ignore macro-level socio-economic variables.
• The combination of system dynamics (SD) and hybrid particle swarm optimization for land use allocation in this work is new.

Urban land use spatial allocation is crucial to lots of countries that are usually under severe environmental and demographic pressures, because it can be used to alleviate some land use problems. A number of models have been proposed for the optimal allocation of land use. However, most of these models only address the suitability of individual land use types and spatial competition between different land uses at micro-scales, but ignore macro-level socio-economic variables and driving forces. This article proposes a novel model (SDHPSO-LA) that integrates system dynamics (SD) and hybrid particle swarm optimization (HPSO) for solving land use allocation problems in a large area. The SD module is used to project land use demands influenced by economy, technology, population, policy, and their interactions at macro-scales. Furthermore, particle swarm optimization (PSO) is modified by incorporating genetic operators to allocate land use in discrete geographic space. The SDHPSO-LA model was then applied to a case study in Panyu, Guangdong, China. The experiments demonstrated the proposed model had the ability to reflect the complex behavior of land use system at different scales, and can be used to generate alternative land use patterns based on various scenarios.