PM2.5 Prediction on EEA ground monitoring stations T+1 Complex Stations 2022 (σz ≥ 50 m, N = 875)
16.67RMSECRAN-PM
Evaluation results
| Method | Links | ||||
|---|---|---|---|---|---|
| CRAN-PMModel Type=Neural model, Resolution=1 km, Number of Parameters=96M2026.03 | 16.67 | 4.78 | 75 | -1.13 | |
| EarthformerModel Type=Neural model, Resolution=25 km, Number of Parameters=61M2026.03 | 16.75 | 5 | 59 | -1.32 | |
| SimVPModel Type=Neural model, Resolution=25 km, Number of Parameters=4.9M2026.03 | 16.79 | 4.97 | 60 | -1.37 | |
| ClimaXModel Type=Neural model, Resolution=25 km, Number of Parameters=57M2026.03 | 16.79 | 5.04 | 57 | -1.44 | |
| ConvLSTMModel Type=Neural model, Resolution=25 km, Number of Parameters=8.2M2026.03 | 16.8 | 4.95 | 58 | -1.39 | |
| TopoFlowModel Type=Neural model, Resolution=25 km, Number of Parameters=61M2026.03 | 16.91 | 4.98 | 62 | -1.77 | |
| CAMSModel Type=Physical model2026.03 | 17.35 | 5.9 | 45 | -2.69 |