A split-step PSO algorithm in prediction of water quality pollution

Abstract

In order to allow the key stakeholders to have more float time to take appropriate precautionary and preventive measures, an accurate prediction of water quality pollution is very significant. Since a variety of existing water quality models involve exogenous input and different assumptions, artificial neural networks have the potential to be a cost-effective solution. This paper presents the application of a split-step particle swarm optimization (PSO) model for training perceptrons to forecast real-time algal bloom dynamics in Tolo Harbour of Hong Kong. The advantages of global search capability of PSO algorithm in the first step and local fast convergence of Levenberg-Marquardt algorithm in the second step are combined together. The results demonstrate that, when compared with the benchmark backward propagation algorithm and the usual PSO algorithm, it attains a higher accuracy in a much shorter time.