Table 1 Comparison of evaluation metrics between the numerical model and P2M
From: A machine learning-based prediction-to-map framework for rapid and accurate spatial flood prediction
Numerical Model | P2M | |||||||
|---|---|---|---|---|---|---|---|---|
1-h | 2-h | 3-h | 4-h | 5-h | 6-h | |||
NSE | – | 0.98 | 0.99 | 0.99 | 0.98 | 0.99 | 0.98 | |
RMSE (m) | – | 0.28 | 0.26 | 0.26 | 0.28 | 0.26 | 0.29 | |
Averaged flood peak (m) | 2.00 | 2.19 | 2.19 | 2.17 | 2.15 | 2.19 | 2.24 | |
Flooded area for flood depths exceeding a threshold (106 m2) | >0.1 m | 170.2 | 140.1 | 140.7 | 140.4 | 140.8 | 141.9 | 136.5 |
>0.5 m | 81.8 | 79.7 | 79.2 | 76.8 | 77.3 | 77.8 | 76.4 | |
>1.0 m | 65.3 | 62.0 | 63.4 | 62.6 | 61.9 | 65.9 | 61.7 | |
>1.5 m | 55.7 | 54.5 | 53.6 | 52.6 | 53.5 | 55.2 | 54.7 | |
>2.0 m | 49.3 | 43.2 | 42.5 | 43.0 | 42.0 | 44.1 | 46.1 | |
>3.0 m | 31.8 | 28.3 | 28.6 | 28.4 | 27.9 | 29.0 | 29.0 | |
