Real-time in situ prediction of ocean currents
Last updated
Last updated
Journal: Ocean Engineering (Q1)
Deep autoregressive networks (LSTM and Transformer) can predict ocean currents in real-time at any location in the world.
Ocean current data at 831 sites (222 stations have data length greater than 2 months) from . Sampling interval: 6 or 10 min
LSTM and Transformer can predict ocean currents in real-time at any location in the world and even better than traditional Harmonic Method.
e.g., Comparison of speed Normalized Root Mean Squared Error (NRMSE) (lower is better)
hb0401
15.7
0.14
0.12
0.12
jx0302
29.5
0.1
0.09
0.33
jx0701
15
0.09
0.10
0.12
cb0701
13.9
0.18
0.19
0.2