Table 8 One-step-ahead Forecasting for Kon Tum dataset.

From: Accurate discharge and water level forecasting using ensemble learning with genetic algorithm and singular spectrum analysis-based denoising

Metrics/models

Ensemble SSA GA

Ensemble SSA

Ensemble

LSTM

ANN

ARIMA

Q

NSE

0.871

0.795

0.690

0.671

0.611

0.639

MSE

1821.301

2238.117

3407.576

4334.260

5522.118

4669.353

MAE

16.585

22.033

22.620

22.568

24.302

22.603

MAPE

15.683

22.252

22.341

18.973

30.875

22.933

H

NSE

0.943

0.929

0.916

0.847

0.808

0.862

MSE

0.016

0.021

0.024

0.045

0.056

0.038

MAE

0.074

0.083

0.099

0.103

0.139

0.098

MAPE

0.014

0.016

0.019

0.020

0.027

0.019

  1. Best results are highlighted in bold text.
  2. Our proposed method (i.e., Ensemble SSA GA) outperforms the others.
Back to article page