Fire Risk Factors for 55 Suburban Towns in Beijing

An AI-driven fire risk forecasting framework based on real incident data from 55 urban villages in Beijing. The proposed IGWO-LSTM-IL model achieved a 92.57% reduction in mean squared error compared to a baseline LSTM. The dataset, shared by Jiangxue Tian, was last updated in June 2026.

Use Cases

• Training AI models for fire risk forecasting based on the described IGWO-LSTM-IL framework.
• Analyzing factors contributing to fire hazards in high-density suburban towns.
• Implementing incremental learning strategies for real-time risk model updates.
• Benchmarking predictive accuracy and stability of fire risk models.

Strengths

• Model performance is quantified with a 92.57% reduction in mean squared error.
• Dataset is based on real fire incident data from a specific geographic area (Beijing).
• The accompanying study describes a specific methodological framework (IGWO-LSTM-IL).

Limitations

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

Provenance

Source

Jiangxue Tian via figshare.

Collection Method

Likely collected from municipal or fire department records, as referenced by 'real fire incident data'.

Freshness

Last updated 2026-06-02 17:31:43; freshness should be verified.

Geography

55 urban villages in Beijing, China.