A study of Great Lakes dam regulation based on water level and flow prediction models: application of particle swarm algorithm and LSTM neural network

Abstract

This study aims to solve the problem of maintaining optimal water levels in the Great Lakes by proposing a dam regulation method based on a water level and flow prediction model. First, a river flow was derived using Manning's formula, and a water level and flow prediction model was developed by combining the effects of rainfall and evaporation on lake inflows and outflows. Secondly, the local optimal solution of the dam was determined using particle swarm algorithm to realize the reasonable regulation of water level. Finally, future rainfall and evaporation were predicted by LSTM neural network to further optimize the predictive ability of the model. The experimental results show that the method can accurately predict the water level changes of the Great Lakes and effectively regulate the dams to maintain the optimal level, which provides an important reference for lake management and protection.