Hailfinder: A Bayesian Network for Severe Weather Forecasting

A Bayesian network model for forecasting severe weather, specifically hail. The model contains 56 nodes and 66 arcs, with 2656 parameters. It 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.

Use Cases

• Benchmarking Bayesian network inference algorithms based on the model's 56-node structure.
• Studying probabilistic reasoning for weather forecasting based on the network's 2656 parameters.
• Developing decision support tools for meteorologists based on the hail prediction model.
• Teaching concepts of graphical models and conditional probability tables using a documented real-world network.

Strengths

• Well-documented academic provenance with a clear citation to the 1996 publication.
• Specific structural metrics provided: 56 nodes, 66 arcs, and a maximum in-degree of 4.
• Clear licensing as public domain (us-pd), facilitating reuse.

Limitations

• Column-level documentation is absent; field semantics must be inferred after download.
• Last update date is unknown; freshness unverified.
• Row count is unknown, which may limit suitability assessment for some empirical tasks.

Provenance

Source

bnlearn Bayesian Network Repository, based on work by Abramson et al.

Collection Method

Likely a hand-crafted or expert-defined probabilistic graphical model.

Time Range

Model developed circa 1996.

Freshness

Last updated date is unknown.

Geography

Geographic coverage is not specified in the provided metadata.