Optimization of air quality monitoring station layout using a multi-objective optimization algorithm: a case study of...

A scientific and rational optimization optimizing the layout of air quality monitoring networks (AQMN) is of great significance for accurately understanding the spatial distribution of pollution and enhancing the effectiveness of environmental governance. To improve the scientific basis and operational efficiency of regional AQMN, this study proposes a multi-objective hybrid optimization method (GA-ACO) integrating genetic algorithm (GA) and ant colony optimization (ACO) for optimizing the spatial layout of monitoring stations. The framework is designed to achieve three primary objectives: minimizing Kriging variance, reducing optimization cost, and decreasing the monitoring area coverage redundancy rate. The model was subsequently deployed and its efficacy was demonstrated through a case study involving PM_2.5 monitoring stations in Henan Province, the third most populous region in China. The results show that the algorithm successfully generated a Pareto optimal solution set, with clear trade-off relationships among the objectives. Based on the proposed GA-ACO model and a simplified TOPSIS-based ideal-point evaluation of the Pareto candidate solutions, an optimal adjustment scheme was derived. This scheme recommends adding 3 new stations, decommissioning 1 existing station, and relocating 2 stations. With a total cost of 3.3 million CNY, the plan reduces the Kriging variance by 14.9% and lowers the coverage redundancy rate to 6.78%, achieving a good balance among monitoring precision, economic efficiency, and resource utilization. This study provides a quantifiable and generalizable decision-making framework for optimizing regional AQMN, offering reference value for future monitoring station layout optimization.