Fig. 1

Calculation work flow of deep learning model"

Fig. 2

Diagram of how the model works. (a) The training process, time series of different lengths are randomly selected from the training set, and each time series is cropped with the random subregion, then trained in G and generated data, the authenticity of the data is evaluated in D; (b) The verification process is carried out synchronously with the training process. The complete research data in the verification set is input into the model for prediction; (c) The test process is carried out after the model training is completed. The test set data with removed the continental shelf is input into the model for prediction to obtain the final prediction data. SLA refers to sea level anomaly; G is the generator; D is the discriminator"

Fig. 3

Spatial distribution of the SLA daily MAE. (a) Daily average MAE on the 7th day of forecast. The rectangular box corresponds to each region in Figure 4. Red represents the southwest of Taiwan Island, blue represents the northwest of Luzon Island, green represents the southwest of Luzon Island, purple indicates the central and western waters of the South China Sea, and black represents the Northwest Pacific; (b) Daily average MAE on the 14th day of forecast; (c) Daily average MAE on the 21st day of forecast; (d) Daily average MAE on the 28th day of forecast"

Fig. 4

Difference between observed and predicted values of average SLA in different regions"

Fig. 5

Variation of MAE of eddy number with prediction time"

Fig. 6

Daily distribution of eddy number in each amplitude range of anticyclone. The column height is the real quantity, and the blue part is the predicted quantity"

Fig. 7

Daily distribution of eddy number in each amplitude range of cyclone. The column height is the real quantity, and the cyan part is the predicted quantity"

Fig. 8

Daily distribution of eddy number in each radius range of anticyclone. The column height is the real quantity, and the blue part is the predicted quantity"

Fig. 9

Daily distribution of eddy number in each radius range of cyclone. The column height is the real quantity, and the cyan part is the predicted quantity"

Fig. 10

Different statistics of the eddy position. (a) Average prediction accuracy; (b) The mean minimum eddy center distance between the real and predicted results in the accurately predicted eddies; (c) In the accurately predicted eddies, the number of eddies in different amplitude ranges, and the column height represents the number; (d) In the accurately predicted eddies, the number of eddies in different radius ranges, and the column height represents the number. The abscissa of all subgraphs stands for days"

Fig. 11

Spatial distribution of the difference between observation and the prediction field of the eddy kinetic energy. (a) Spatial distribution of the difference on the 7th day of prediction; (b) Spatial distribution of the difference on the 14th day of prediction; (c) Spatial distribution of the difference on the 21st day of prediction; (d) Spatial distribution of the difference on the 28th day of prediction"

Fig. 12

Distribution of real eddies and predicted eddies under normal weather conditions and typhoon weather conditions. (a~e) correspond to normal weather conditions from October 1, 2019 to October 5, 2019 respectively; (f~j) correspond to typhoon Nakri conditions from November 1, 2019 to November 5, 2019 respectively. The light red dotted line, red solid line, light blue dotted line and blue solid line in the figure represent the distribution of real anticyclone, predicted anticyclone, real cyclone and predicted cyclone respectively. The pink dotted line is the central position and moving path of Nakri"