996 impact-verified traffic incidents paired with speed data from 325 sensor nodes in the PEMS-BAY network. The dataset is hosted on Kaggle and is tagged for applications in Graph Neural Networks and Time Series Analysis. Its author, organization, and last update date are unspecified.
Use Cases
- Predicting traffic speed anomalies based on verified incident reports
- Training graph neural networks for spatio-temporal forecasting using the 325-node sensor network
- Analyzing the causal impact of verified incidents on traffic flow patterns
- Developing out-of-distribution detection models for transportation systems
Strengths
- Includes 996 traffic incidents verified for impact
- Covers a network of 325 traffic sensor nodes
Limitations
- Column-level documentation is absent; field semantics must be inferred after download
- Row count is unknown, which may limit suitability assessment
- Last update date is unknown; freshness unverified
Provenance
- Source
- Kaggle
- Collection Method
- Likely aggregated from the PEMS-BAY traffic monitoring system
- Time Range
- null
- Freshness
- Last update date is unknown; freshness unverified
- Geography
- Likely the San Francisco Bay Area (inferred from PEMS-BAY codename)