Table 6 Performance evaluation of different models.
From: Enhancing groundwater level prediction with a hybrid deep learning model in Jinan City, China
Model | Stage | MAE | RMSE | R2 |
|---|---|---|---|---|
LSTM | Training | 0.188 ± 0.012 | 0.164 ± 0.015 | 0.889 ± 0.011 |
Testing | 0.154 ± 0.011 | 0.139 ± 0.013 | 0.891 ± 0.009 | |
GRU | Training | 0.161 ± 0.009 | 0.151 ± 0.010 | 0.912 ± 0.012 |
Testing | 0.139 ± 0.008 | 0.121 ± 0.009 | 0.928 ± 0.009 | |
STGCN | Training | 0.095 ± 0.006 | 0.125 ± 0.008 | 0.956 ± 0.008 |
Testing | 0.095 ± 0.007 | 0.103 ± 0.006 | 0.965 ± 0.008 | |
STGPM | Training | 0.062 ± 0.004 | 0.064 ± 0.003 | 0.980 ± 0.001 |
Testing | 0.039 ± 0.002 | 0.052 ± 0.002 | 0.988 ± 0.001 |
