A HYBRID GA-PSO AND COUPLING COORDINATION FRAMEWORK FOR MULTI-OBJECTIVE OPTIMIZATION IN SUSTAINABLE TOURISM SYSTEMS

Rapid tourism growth has boosted local economies but also posed environmental and social challenges, highlighting the need for sustainable management. This study presents a hybrid optimization framework that integrates Genetic Algorithm with Particle Swarm Optimization (GA-PSO) with a Coupling Coordination Degree (CCD) mechanism to balance social, economic, and environmental subsystems. The model targets maximization of employment, tourism revenue, and glacier stability under statistical and coordination constraints. Regression analysis and the entropy weight–TOPSIS method were applied to quantify subsystem interactions. Results show that GA-PSO outperforms single GA and PSO, achieving an optimal coordination degree of 0.6254. Employment, tourism revenue (USD 147 million), and environmental sustainability all showed notable improvements. This research extends the use of hybrid evolutionary algorithms in sustainable tourism and provides quantitative support for policymakers seeking to balance economic growth, social well-being, and ecological resilience.