PEMS

The 'PEMS' dataset is a benchmark that contains multivariate traffic series data used to evaluate traffic forecasting models, particularly in the context of extreme events and their complex spatio-temporal correlations.

Papers using PEMS (14)

STGAtt: A Spatial-Temporal Unified Graph Attention Network for Traffic Flow Forecasting2025 · 1 citesSDA-GRIN for Adaptive Spatial-Temporal Multivariate Time Series Imputation2024 · 1 citesGAMMA-Net: Adaptive Long-Horizon Traffic Spatio-Temporal Forecasting Model based on Interleaved Graph Attention and Multi-Axis Mamba2026Temporal Attention Evolutional Graph Convolutional Network for Multivariate Time Series Forecasting2025Temporal Graph MLP Mixer for Spatio-Temporal Forecasting2025Residual Correction in Real-Time Traffic Forecasting2022 · 14 citesSpatio-Temporal Meta-Graph Learning for Traffic Forecasting2022 · 11 citesCorrelated Time Series Self-Supervised Representation Learning via Spatiotemporal Bootstrapping2023 · 7 citesAdaptive Graph Spatial-Temporal Transformer Network for Traffic Flow Forecasting2022 · 6 citesSpatial-Temporal-Decoupled Masked Pre-training for Spatiotemporal Forecasting2023 · 3 citesMegaCRN: Meta-Graph Convolutional Recurrent Network for Spatio-Temporal Modeling2022 · 2 citesGT-CausIn: a novel causal-based insight for traffic prediction2022 · 1 citesFast Temporal Wavelet Graph Neural Networks2023Test-Time Compensated Representation Learning for Extreme Traffic Forecasting2023