Hailfinder: Bayesian Network for Severe Weather Forecasting with 56 Nodes

56-node Bayesian network designed for forecasting severe weather, specifically hail. Hailfinder was authored by B. Abramson, J. Brown, W. Edwards, A. Murphy, and R. L. Winkler and published in the International Journal of Forecasting in 1996. The network structure contains 66 arcs and 2656 parameters, modeling probabilistic relationships between meteorological variables.

Use Cases

• Benchmarking Bayesian network inference algorithms based on the described 56-node, 66-arc structure.
• Studying probabilistic reasoning for weather event prediction based on the network's focus on severe weather forecasting.
• Teaching concepts of graphical models and parameter estimation using a documented, real-world network example.
• Developing decision-support tools for meteorology based on the probabilistic relationships encoded in the network.

Strengths

• Well-documented academic provenance with a clear citation to a 1996 peer-reviewed publication.
• Specific structural metrics are provided, including 56 nodes, 66 arcs, and 2656 parameters.
• Network complexity is quantified with metrics like an average Markov blanket size of 3.54 and a maximum in-degree of 4.

Limitations

• Column-level documentation and sample data are unavailable, making field semantics and data format unclear.
• Row count, file formats, and data size are unknown, which may limit suitability assessment.
• Last update date is unknown; freshness unverified.

Provenance

Source

B. Abramson, J. Brown, W. Edwards, A. Murphy, and R. L. Winkler, via the bnlearn Bayesian Network Repository.

Collection Method

Likely constructed from expert meteorological knowledge for forecasting purposes.

Time Range

null

Freshness

unknown

Geography

null