Weather Forecasting On Sd
Metriken
MSE (t+1)
MSE (t+6)
Ergebnisse
Leistungsergebnisse verschiedener Modelle zu diesem Benchmark
Modellname | MSE (t+1) | MSE (t+6) | Paper Title | Repository |
|---|---|---|---|---|
| GRU-GNN | 0.5705 ± 0.0057 | 0.7414 ± 0.0294 | Neural Dynamics on Complex Networks | - |
| NDE | 0.3561 ± 0.0055 | 0.7301 ± 0.0048 | Climate Modeling with Neural Diffusion Equations | |
| NADE | 0.1430 ± 0.0280 | 0.6516 ± 0.0657 | Climate modeling with neural advection–diffusion equation | |
| GN-skip | 0.6543 ± 0.1195 | 0.9872 ± 0.2425 | Graph networks as learnable physics engines for inference and control | |
| NDCN | 0.5296 ± 0.0274 | 0.7542 ± 0.0730 | Neural Dynamics on Complex Networks | - |
| RNN-GNN | 0.5291 ± 0.0578 | 0.7862 ± 0.0475 | Neural Dynamics on Complex Networks | - |
| GN-only | 0.7007 ± 0.0848 | 1.0422 ± 0.0673 | Graph networks as learnable physics engines for inference and control | |
| AGCRN | 0.2010 ± 0.0188 | 1.0181 ± 0.1275 | Adaptive Graph Convolutional Recurrent Network for Traffic Forecasting | |
| LSTM-GNN | 0.5754 ± 0.0180 | 0.7954 ± 0.0110 | Neural Dynamics on Complex Networks | - |
| DPGN | 0.5149 ± 0.0831 | 0.6714 ± 0.1106 | Differentiable Physics-informed Graph Networks |
0 of 10 row(s) selected.