Traffic Prediction On Pemsd3
Metrics
12 steps MAE
12 steps MAPE
12 steps RMSE
Results
Performance results of various models on this benchmark
Model Name | 12 steps MAE | 12 steps MAPE | 12 steps RMSE | Paper Title | Repository |
|---|---|---|---|---|---|
| STD-MAE | 13.80 | 13.96 | 24.43 | Spatial-Temporal-Decoupled Masked Pre-training for Spatiotemporal Forecasting | |
| STG-NRDE | 15.50 | 14.9 | 27.06 | Graph Neural Rough Differential Equations for Traffic Forecasting | |
| PDG2Seq | 14.62 | 14.88 | 25.47 | PDG2Seq: Periodic Dynamic Graph to Sequence Model for Traffic Flow Prediction | |
| STG-NCDE | 15.57 | 15.06 | 27.09 | Graph Neural Controlled Differential Equations for Traffic Forecasting | |
| DDGCRN | 14.63 | 14.22 | 25.07 | A Decomposition Dynamic graph convolutional recurrent network for traffic forecasting | |
| STWave | 14.93 | - | - | When Spatio-Temporal Meet Wavelets: Disentangled Traffic Forecasting via Efficient Spectral Graph Attention Networks |
0 of 6 row(s) selected.