The application of neural network optimized by genetic algorithm in water quality prediction

In order to overcome the BP neural network´s shortcomings, such as the slow convergence rate and easily fall into a local minimum value, the genetic algorithm is used to optimize the BP neural network. Firstly, the BP neural network´s structure, initial weight and threshold values are optimized by genetic algorithm, and then the optimized BP neural network is trained by the samples, to get the knowledge existing in the samples. At last, this method is used to predict the water quality of Taihu Lake. The experiment results show that this method has higher prediction accuracy and faster convergence than the standard BP network.