Skip to main content

Table 5 RMSE of the LSTM model trained with and without the use of the AGW parameter

From: Equatorial spread-F forecasting model with local factors using the long short-term memory network

 

All nights

Post-sunset

Post-midnight

AGW

No AGW

AGW

No AGW

AGW

No AGW

Feb

15.9

10.6

19

9.6

12

11.5

Mar

14.3

13

19.4

16.5

5.7

8

Apr

32.8

23.5

44.5

29.5

12.9

15.4

Aug

20.4

20.1

14

12.4

25.2

25.6

Sep

7.4

11.1

6.5

12.2

8.3

9.7

Oct

27.2

20.3

37.7

27.6

7.3

8.1

  1. Significant improvements of the ESF model are gained with the AGW index as shown in bold text