Chongxuan Xu, Ying Chen, Xueliang Zhao, Wenyang Song, Xiao Li. Prediction of seawater pH by bidirectional gated recurrent neural network with attention under phase space reconstruction: case study of the coastal waters of Beihai[J]. Acta Oceanologica Sinica.
Citation:
Chongxuan Xu, Ying Chen, Xueliang Zhao, Wenyang Song, Xiao Li. Prediction of seawater pH by bidirectional gated recurrent neural network with attention under phase space reconstruction: case study of the coastal waters of Beihai[J]. Acta Oceanologica Sinica.
Chongxuan Xu, Ying Chen, Xueliang Zhao, Wenyang Song, Xiao Li. Prediction of seawater pH by bidirectional gated recurrent neural network with attention under phase space reconstruction: case study of the coastal waters of Beihai[J]. Acta Oceanologica Sinica.
Citation:
Chongxuan Xu, Ying Chen, Xueliang Zhao, Wenyang Song, Xiao Li. Prediction of seawater pH by bidirectional gated recurrent neural network with attention under phase space reconstruction: case study of the coastal waters of Beihai[J]. Acta Oceanologica Sinica.
Prediction of seawater pH by bidirectional gated recurrent neural network with attention under phase space reconstruction: case study of the coastal waters of Beihai
Hebei Province Key Laboratory of Test/Measurement Technology and Instrument, School of Electrical Engineering, Yanshan University, Qinhuangdao, Hebei 066004, China
2.
Center for Hydrogeology and Environmental Geology, China Geological Survey, Geological Environment Monitoring Engineering Technology Innovation Center of the Ministry of Natural Resources, Baoding, Heibei 071051, China
Funds:
The National Natural Science Foundation of China under contract No. 62275228, the Key Research and Development Project of Hebei Province under contract Nos. 19273901D and 20373301D, the Natural Science Foundation of Hebei Province, China under contract No. F2020203066.
Marine life is very sensitive to changes in pH. Even slight changes can cause ecosystems to collapse. Therefore, understanding the future pH of seawater is of great significance for the protection of the marine environment. At present, the monitoring method of seawater pH has been matured. However, how to accurately predict future changes has been lacking effective solutions. Based on this, the model of bidirectional gated recurrent neural network with multi-headed self-attention based on improved complete ensemble empirical mode decomposition with adaptive noise combined with phase space reconstruction (ICPBGA) is proposed to achieve seawater pH prediction. To verify the validity of this model, pH data of two monitoring sites in the Beihai coastal sea area are selected to verify the effect. At the same time, the ICPBGA model is compared with other excellent models for predicting chaotic time series, and root mean square error (RMSE), mean absolute error (MAE), mean absolute percentage error (MAPE), and coefficient of determination (R2) are used as performance evaluation indicators. The R2 of the ICPBGA model at site 1 and site 2 are above 0.9, and the prediction errors are also the smallest. The results show that the ICPBGA model has a wide range of applicability and the most satisfactory prediction effect. The prediction method in this paper can be further expanded and used to predict other marine environmental indicators.
Figure 3. The structure diagram of the bidirectional GRU neural network
Figure 4. The structure diagram of multi-head self-attention
Figure 5. The framework of the ICPBGRA model
Figure 6. The decomposition result of CEEMDAN
Figure 7. The decomposition result of ICEEMDAN
Figure 8. Determine the time delay τ by the mutual information method. a, b, and c are the change trends of the delay mutual information of n-com1, n-com2, and n-com3 with time delay τ.
Figure 9. Determine embedding dimension m by the Cao. a, b, and c are the change trends of the E(d) of n-com1, n-com2, and n-com3 with embedding dimension d.
Figure 10. Ablation study results. a is the prediction result graph of each model. b is the relationship between the actual value and the predicted value.
Figure 11. the Taylor diagram of the ablation experiment
Figure 12. Comparison of prediction results of various models
Figure 13. The relationship between the actual value and the predicted value. a is the result of monitoring site 1. b is the result of monitoring site 2.
Figure 14. The prediction error violin plot. a is the result of monitoring site 1. b is the result of monitoring site 2.
DownLoad:
