PEMS-04

PEMS-04 is a benchmark dataset used for evaluating spatiotemporal forecasting techniques, containing traffic data that reflects the complex spatiotemporal dynamics of transportation systems.

Papers using PEMS-04 (7)

GAMMA-Net: Adaptive Long-Horizon Traffic Spatio-Temporal Forecasting Model based on Interleaved Graph Attention and Multi-Axis Mamba2026A Decomposition-based State Space Model for Multivariate Time-Series Forecasting2026Lightweight Spatio-Temporal Attention Network with Graph Embedding and Rotational Position Encoding for Traffic Forecasting2025SGRU: A High-Performance Structured Gated Recurrent Unit for Traffic Flow Prediction2024 · 9 citesSpatial-Temporal-Decoupled Masked Pre-training for Spatiotemporal Forecasting2023 · 3 citesESGCN: Edge Squeeze Attention Graph Convolutional Network for Traffic Flow Forecasting2023 · 2 citesHybrid Transformer and Spatial-Temporal Self-Supervised Learning for Long-term Traffic Prediction2024