Skip to Main Content
Table 5

Performance of the XAJ-LSTM model for flood forecasting at lead times , , , and in the training and validation stages

PeriodIndexXAJ-LSTM model
Training NSE 0.983 0.967 0.950 0.941 
KGE 0.965 0.953 0.949 0.940 
0.992 0.984 0.976 0.971 
RE (%) 2.472 −4.389 1.511 1.028 
RMSE (m3/s) 32.641 45.928 56.104 61.299 
Validation NSE 0.983 0.959 0.944 0.932 
KGE 0.941 0.958 0.941 0.939 
0.992 0.980 0.972 0.966 
RE (%) 3.615 −1.734 0.266 −0.114 
RMSE (m3/s) 35.266 55.162 64.670 71.343 
PeriodIndexXAJ-LSTM model
Training NSE 0.983 0.967 0.950 0.941 
KGE 0.965 0.953 0.949 0.940 
0.992 0.984 0.976 0.971 
RE (%) 2.472 −4.389 1.511 1.028 
RMSE (m3/s) 32.641 45.928 56.104 61.299 
Validation NSE 0.983 0.959 0.944 0.932 
KGE 0.941 0.958 0.941 0.939 
0.992 0.980 0.972 0.966 
RE (%) 3.615 −1.734 0.266 −0.114 
RMSE (m3/s) 35.266 55.162 64.670 71.343 
Close Modal

or Create an Account

Close Modal
Close Modal