Multi-objective land use optimization coupling spatialized shuffled frog leaping algorithm with multi-level agent

Land use optimization is a crucial method to reduce carbon emission and promote sustainable development, calling for advanced fine-grained modeling to address complex human-land conflicts. However, existing models still exhibit limitations in internalizing geographical rules, constructing multi-level interaction mechanisms, and bridging the spatial-scale mismatch between global and local optimization. Therefore, this study constructs a multi-objective optimization scenario under low-carbon development, proposing a novel coupling model (SSFLA-MLAS), which integrates a spatialized shuffled frog leaping algorithm (SSFLA) with a multi-level agent system (MLAS). The integration resolves cross-scale spatial coordination through a nested coupling architecture, while simultaneously accounting for multi-level interactive decision simulation and multi-objective heuristic search. The case study in Huangpi District demonstrates that: (1) SSFLA-MLAS outperforms single algorithms in effectiveness and efficiency, achieving overall objective 3.4%, 32.5% and 26.5% greater than SSFLA, MLAS and multi-agent system (MAS). (2) MLAS improves the comprehensive landscape pattern index by 26.4% over MAS while aligning spatial layouts with development strategies. (3) SSFLA-MLAS demonstrates remarkable optimization results, improving economic, social and ecological objectives by 5.01%, 2.87% and 0.74%, while enhancing net carbon sink by 1.38%. The model not only offers intelligent support for sustainable land-use planning, but also advances the methodological integration of spatial optimization modeling through coupling global search with local simulation.