Study of short-term water quality prediction model based on wavelet neural network

Improved water quality prediction accuracy and reduced computational complexity are vital for ensuring a precise control over the water quality in intensive pearl breeding. This paper combined the wavelet transform with the BP neural network to build the short-term wavelet neural network water quality prediction model. The proposed model was used to predict the water quality of intensive freshwater pearl breeding ponds in Duchang county, Jiangxi province, China. Compared with prediction results achieved by the BP neural network and the Elman neural network, the mean absolute percentage error dropped from 17.464% and 8.438%, respectively, to 3.822%. The results show that the wavelet neural network is superior to the BP neural network and the Elman neural network. Furthermore, the proposed model features a high learning speed, improved predict accuracy, and strong robustness. The model can predict water quality effectively and can meet the management requirements in intensive freshwater pearl breeding.

► The novel model which combined the wavelet transform with the BP neural network to build the short-term wavelet neural network is presented to predict water quality in intensive freshwater pearl breeding ponds.
► WNN is faster, more precise, and more robust than the BP neural network and the Elman neural network in water quality prediction of intensive freshwater pearl breeding.
► WNN can be used as a suitable and effective modeling tool for predicting water quality in intensive freshwater pearl breeding.