Water temperature prediction in sea cucumber aquaculture ponds by RBF neural network model

Water temperature is considered as one of the most important parameters which influence the growth rate and development of sea cucumbers as well as their distribution within the pond environment. As the change process of water temperature is dependent on the complicated meteorological and geophysical conditions, artificial neural network with specific features such as non-linearity, adaptivity, generalization, and model independence will be a proper method for solving this problem. This paper presents a Radial Basis Function (RBF) neural network model based on nearest neighbor clustering algorithm and puts forward some improved methods aiming at looking for the defects of original algorithm, then integrated them into an optimization model and verified it on matlab platform. Finally, a comparison between RBF model and 1-D vertical model was made to confirm the excellent predictive performance of optimized RBF neural network model.