AUTHOR=Hao Zhenhui 

TITLE=A dissolved oxygen prediction model based on GRU–N-Beats

JOURNAL=Frontiers in Marine Science

VOLUME=Volume 11 - 2024

YEAR=2024

URL=https://www.frontiersin.org/journals/marine-science/articles/10.3389/fmars.2024.1365047

DOI=10.3389/fmars.2024.1365047

ISSN=2296-7745

ABSTRACT=Dissolved oxygen is one of the most important water quality parameters in aquaculture, and the level determines whether fish can grow healthily. Since there is a delay in equipment control in the aquaculture environment, dissolved oxygen prediction is needed to reduce the loss due to low dissolved oxygen. To solve the problem of insufficient accuracy and poor interpretability of traditional methods in predicting dissolved oxygen from multivariate water quality parameters, this paper proposes an improved Nbeats-based prediction network. Firstly, the maximum expectation algorithm (EM) was used to fill in the original data by fitting the missing values. Secondly, the discrete wavelet transform (DWT) was used to reduce the overall noise of the sample, and then the GRU feature extraction network was employed to extract the water quality information from the temporal dimension, and the N-beats was utilized to predict the pre-processed data, and the residual operation through Stack was performed to obtain the prediction results. The improved algorithm overcomes the challenge of insufficient prediction accuracy of the traditional algorithm. The GRU-NBeats network proposed in this paper can extract features from multivariate time dimensions for prediction. The values of RMSE, MAE, MAPE and R2 for the proposed algorithm are 0.171, 0.120, 0.015 and 0.97, respectively.