Laser & Optoelectronics Progress, Volume. 58, Issue 24, 2415005(2021)
Sea Surface Temperature Prediction Method Based on Empirical Mode Decomposition-Gated Recurrent Unit Model
Figures & Tables(11)
Fig. 5. Comparison between complexity of original sequence and multi-scale complexity after decomposition
Fig. 6. Comparison of prediction results of five experimental data in 3 neural networks
Fig. 7. Comparison of experimental results between EMD based on machine learning model and direct machine learning models
Fig. 8. Comparison between predicted value and real value under 4 different prediction models
Table 1. Comparison between prediction results of EMD based on machine learning model and those of direct machine learning models
View tableTable 1. Comparison between prediction results of EMD based on machine learning model and those of direct machine learning models
SST Parameter LSTM EMD-LSTM GRU EMD-GRU SST1 MSE 0.1963 0.1077 0.1721 0.0706 MAE 0.3269 0.2040 0.3203 0.1965 SST2 MSE 0.2355 0.1463 0.2092 0.0692 MAE 0.3666 0.2804 0.3583 0.1978 SST3 MSE 0.4896 0.3040 0.2924 0.0964 MAE 0.3733 0.2371 0.3898 0.2333 SST4 MSE 0.3896 0.2656 0.4537 0.2609 MAE 0.4759 0.3967 0.5067 0.3891 SST5 MSE 0.8724 0.3810 0.8744 0.2366 MAE 0.6507 0.4419 0.6911 0.3710
Table 2. Supplementary experimental results
View tableTable 2. Supplementary experimental results
In-out Parameter GRU EMD-GRU 7--1 MSE 0.2569 0.1748 MAE 0.3753 0.3282 10--5 MSE 0.8744 0.2366 MAE 0.6911 0.3710 15--7 MSE 1.0459 0.6309 MAE 0.7767 0.6062
Tools
Get Citation
Copy Citation Text
Qi He, Zeyu Hu, Huifang Xu, Wei Song, YanLin Du. Sea Surface Temperature Prediction Method Based on Empirical Mode Decomposition-Gated Recurrent Unit Model[J]. Laser & Optoelectronics Progress, 2021, 58(24): 2415005
Paper Information
Category: Machine Vision
Received: Jan. 18, 2021
Accepted: Mar. 8, 2021
Published Online: Dec. 1, 2021
The Author Email: Huifang Xu (17069@gench.edu.cn)
© Copyright 2018-2021 | Chinese Laser Press.
All Rights Reserved 沪ICP备15018463号-20