Abstract:

A Poisson regression model and a negative binomial regression model (NB model) are often used in areas such as medicine and economy, but rarely in the domestic forestry sector, especially in the forest fire forecasting. Based on data of forest fire occurrences in Daxing’anling region in 1980—2005, this paper profoundly analyzes the application conditions and test methods of the two models. The AIC method was used to check the fitting level of the models and the capability of the models for forecasting forest fires was discussed. This study provided necessary theoretical basis and data support for the application of the two models in the field of forestry in China.

Key words: forest fire, Poisson model, negative binomial model, weather factor