Research Article
Complexity to Forecast Flood: Problem Definition and Spatiotemporal Attention LSTM Solution
Table 4
Comparisons on Lech dataset with several comparative methods. Note that bold texts indicate best performance among comparative methods.
| Models | RT+3 | RT+6 | RT+9 | RA | MT+3 (%) | MT+6 (%) | MT+9 (%) | MA | DT+3 | DT+6 | DT+9 | DA |
| FCN | 51.27 | 82.54 | 123.4 | 85.74 | 12.82 | 20.64 | 30.85 | 21.44 | 0.88 | 0.70 | 0.32 | 0.63 | SVM | 63.99 | 79.98 | 92.49 | 78.82 | 16.00 | 20.00 | 23.12 | 19.71 | 0.82 | 0.72 | 0.62 | 0.72 | LSTM | 68.92 | 75.12 | 80.85 | 74.96 | 17.23 | 18.78 | 20.21 | 18.74 | 0.79 | 0.75 | 0.71 | 0.75 | STA-LSTM | 60.94 | 65.56 | 71.56 | 66.02 | 15.24 | 16.39 | 17.89 | 16.51 | 0.84 | 0.81 | 0.77 | 0.81 |
|
|