Hailfinder: Bayesian Network for Severe Weather Forecasting

Hailfinder_1 is a Bayesian network model for forecasting severe weather, containing 56 nodes and 66 arcs. The model 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. It has 2656 parameters and an average Markov blanket size of 3.54.

Use Cases

• Benchmarking probabilistic inference algorithms based on the network's 56-node structure.
• Studying causal relationships in meteorological systems based on the 66 defined arcs.
• Developing decision support tools for severe weather forecasting based on the Bayesian system described.
• Teaching Bayesian network concepts using a real-world, domain-specific model.

Strengths

• Well-defined network structure with 56 nodes and 66 arcs, providing a clear probabilistic framework.
• Model complexity is quantified with 2656 parameters and an average Markov blanket size of 3.54.
• Academic provenance with a published reference in a peer-reviewed journal.

Limitations

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

Provenance

Source

B. Abramson, J. Brown, W. Edwards, A. Murphy, and R. L. Winkler.

Collection Method

null

Time Range

null

Freshness

null

Geography

null