Research on the Optimal Water Level Evaluation of the Great Lakes Based on Entropy Weight Method and Particle Swarm Algorithm

The hydrological conditions of the Great Lakes have undergone significant changes due to climate variation and human activities, impacting the ecological environment and multiple stakeholders. Therefore, scientific assessment and management of lake water levels are crucial. This study employs the entropy weight method and Particle Swarm Optimization (PSO) algorithm to optimize the water levels. By integrating multiple data sources that affect water level changes, an indicator system encompassing water level - related factors is constructed. The entropy weight method is utilized to determine the weights of natural factors, the Analytic Hierarchy Process is applied to quantify the weights of stakeholders, and a comprehensive scoring model is established. The PSO algorithm is adopted to solve for the optimal water level. The results indicate that the weights of each factor are clearly defined, and the monthly optimal water levels from 2011 to 2020 show an upward trend, and the scoring coefficients of stakeholders can be maximized. This study provides a scientific basis for the water level management of the Great Lakes, and the constructed method framework is helpful for dealing with complex water resource challenges, which has important practical significance for water resource management.