Table 5 The statistical results of models developed under the ideal meta-parameters in forecasting CCRSFm.

From: Developing a novel hybrid model based on GRU deep neural network and Whale optimization algorithm for precise forecasting of river’s streamflow

Model

RMSE (m3/s)

R2

NSE

MBE (m3/s)

MAE (m3/s)

General single GRU model (1)

1.29

0.59

0.55

0.047

0.91

General single Bi-GRU model (2)

0.83

0.66

0.6

-0.06

0.53

2GRU× model (3)

0.49

0.74

0.71

-0.078

0.33

Hybrid 2GRU×–WOA model (4)

0.36

0.79

0.76

-0.01

0.21

  1. *Quantities that are shown in bold are the results of optimal model.
Back to article page