AMGST: Traffic Speed and Flow Data for Forecasting Model Evaluation

5.5 KB of traffic data in XLS format, published by Pei Shi on figshare in June 2026. The dataset contains speed and flow measurements from four public traffic datasets and was used to evaluate the AMGST forecasting model.

Use Cases

• Benchmarking traffic forecasting models based on speed and flow measurements.
• Training spatiotemporal graph neural networks based on the described spatial and temporal correlations.
• Evaluating adaptive graph construction methods for traffic data based on the described multi-graph diffusion convolution.
• Studying long-term dynamic temporal dependencies in urban traffic patterns.

Strengths

• Data is licensed under CC-BY-4.0, allowing for broad reuse.
• The description provides a detailed methodological context for the data's intended use.

Limitations

• The dataset is very small at 5.5 KB, indicating extremely limited scope.
• Column-level documentation is absent; field semantics must be inferred after download.
• Row count is unknown, which may limit suitability assessment.

Provenance

Source

figshare

Collection Method

Likely aggregated from four public traffic datasets, as mentioned in the description.

Freshness

Last updated 2026-06-04 17:36:32; freshness should be verified.