Title | ||
---|---|---|
MPA-RNN: A Novel Attention-Based Recurrent Neural Networks for Total Nitrogen Prediction |
Abstract | ||
---|---|---|
Accurately predicting the short- and long-term variations of total nitrogen (TN) is vital for operating the wastewater treatment plants (WWTPs), considering the critical role TN plays in reflecting the eutrophication of wastewater. However, only a few relevant water quality parameters with limited samples can be obtained in WWTPs, which tremendously increases the difficulty in precisely predicting TN concentration. In this study, a multiphase attention-based recurrent neural network (MPA-RNN) is proposed. Benefited from its unique decomposition-summary attention structure, MPA-RNN first learns the temporal correlations and effectively excavates the useful information hidden in the historical data. Then, by designing a two-channel structure to transmit attention information, summary attention can integrate the decomposed information and learn the spatial relationships without information loss. Experimental results demonstrate that MPA-RNN achieves the best performance on both the SML2010 and practical TN datasets with the smallest root-mean-squared error, mean absolute error, and mean absolute percentage error when compared with the other state-of-the-art methods. |
Year | DOI | Venue |
---|---|---|
2022 | 10.1109/TII.2022.3161990 | IEEE Transactions on Industrial Informatics |
Keywords | DocType | Volume |
Attention-based recurrent neural network,attention mechanism,multivariate time series prediction,spatial-temporal relationship,total nitrogen (TN) prediction | Journal | 18 |
Issue | ISSN | Citations |
10 | 1551-3203 | 0 |
PageRank | References | Authors |
0.34 | 23 | 5 |
Name | Order | Citations | PageRank |
---|---|---|---|
Jingxuan Geng | 1 | 0 | 0.34 |
Chunhua Yang | 2 | 435 | 71.63 |
Yonggang Li | 3 | 0 | 5.07 |
Lijuan Lan | 4 | 0 | 1.69 |
Qiwu Luo | 5 | 14 | 9.06 |