School of Artificial Intelligence (School of Future Technology), Nanjing University of Information Science and Technology, Nanjing 210044, China
2.
Southern Marine Science and Engineering Guangdong Laboratory (Zhuhai), Zhuhai 519080, China
3.
School of Marine Sciences, Nanjing University of Information Science and Technology, Nanjing 210044, China
Funds:
The Southern Marine Science and Engineering Guangdong Laboratory (Zhuhai) under contract No.SML2020SP007; the National Natural Science Foundation of China under contract Nos 42192562 and 62072249
As wave height is an important parameter in marine climate measurement, its accurate prediction is crucial in ocean engineering. It also plays an important role in marine disaster early warning and ship design, etc. However, challenges in the large demand for computing resources and the improvement of accuracy are currently encountered. To resolve the above mentioned problems, sequence-to-sequence deep learning model (Seq-to-Seq) is applied to intelligently explore the internal law between the continuous wave height data output by the model, so as to realize fast and accurate predictions on wave height data. Simultaneously, ensemble empirical mode decomposition (EEMD) is adopted to reduce the non-stationarity of wave height data and solve the problem of modal aliasing caused by empirical mode decomposition (EMD), and then improves the prediction accuracy. A significant wave height forecast method integrating EEMD with the Seq-to-Seq model (EEMD-Seq-to-Seq) is proposed in this paper, and the prediction models under different time spans are established. Compared with the long short-term memory model, the novel method demonstrates increased continuity for long-term prediction and reduces prediction errors. The experiments of wave height prediction on four buoys show that the EEMD-Seq-to-Seq algorithm effectively improves the prediction accuracy in short-term (3-, 6-, 12-, and 24-h forecast horizon) and long-term (48-, and 72-h forecast horizon) predictions.
Figure 1. Location of National Data Buoy Center buoys41040, 41044, 41046 and 41047
Figure 2. The flow chart of the EEMD algorithm
Figure 3. The structure of the Seq-to-Seq prediction model with attention mechanism
Figure 4. The structure of LSTM neuron
Figure 5. The structure of the EEMD-Seq-to-Seq prediction model
Figure 6. The flowchart of the EEMD-Seq-to-Seq prediction model
Figure 7. Comparison of SWH forecasts of different models for buoy 41040 at the (a) 3-, (b) 6-, (c) 12- and (d) 24-hwindows.
Figure 8. Comparison of SWH forecasts of different models for buoy 41044 at the (a) 3-, (b) 6-, (c) 12- and (d) 24-h windows
Figure 9. Comparison of SWH forecasts of different models for buoy 41046 at the (a) 3-, (b) 6-, (c) 12- and (d) 24-h windows
Figure 10. Comparison of SWH forecasts of different models for buoy 41047 at the (a) 3-, (b) 6-, (c) 12- and (d) 24-h windows
Figure 11. Comparison of EMD-LSTM(blue) and EMD-Seq-to-Seq (orange) SWH forecast errors at the (a) 3-, (b) 6-, (c) 12- and (d) 24-h forecast windows for buoy 41047
Figure 12. Comparison of SWHs of the second, third, fourth and fifth intrinsic mode functions through EMD model (a)–(d) and EEMD model (e)–(h)
Figure 13. Scatter diagram of the observed and predicted SWHs obtained by different algorithms at buoy 41040. (a)–(d) for 3-h forecast window, (e)–(h) for 6-h forecast window, (I)–(l) of 12-h forecast window, (m)–(p) for 24-h forecast window
DownLoad:
