Using Radial Basis Function Neural Networks to identify river water data parameters

Abstract

The complex conditions of water dynamics create a challenge in selecting an appropriate neuron structure for artificial neural networks to simulate real river parameters. This study proposes an identification model based on Radial Basis Function (RBF) Neural Networks. We applied this identification model to river water quality parameters with different neuron node size scenarios to test network structure characters. Simulation results reveal that the RBF Neural Networks model achieves convergence through neuron iterations and the simulation error is well controlled within a small margin. The adjusting effect is closely related to structure design and the neuron updating strategy.