Table 5 Comparison of drifter trajectory data combining different environmental features. RMSE is the root mean square error of latitude and longitude(°), and the distance is the mean absolute distance error (km).
From: Prediction of surface drifter trajectories in the South China sea using deep learning
6 h | 12 h | 18 h | 24 h | |||||
|---|---|---|---|---|---|---|---|---|
RMSE | MAE | RMSE | MAE | RMSE | MAE | RMSE | MAE | |
Informer-CNN: SSTe | 0.0537 | 5.0510 | 0.0653 | 5.5941 | 0.1119 | 9.2901 | 0.1683 | 13.4595 |
Informer-CNN: SSSe | 0.0636 | 5.3668 | 0.0702 | 5.7558 | 0.1099 | 9.0002 | 0.1777 | 13.8609 |
Informer-CNN: SSTe+SSSe | 0.0587 | 4.9943 | 0.0611 | 4.9640 | 0.1132 | 9.2180 | 0.1707 | 13.3803 |
Informer-CNN: U + V | 0.0494 | 4.3279 | 0.0577 | 4.7287 | 0.1116 | 9.0450 | 0.1718 | 13.3481 |
