Arima, S., Calculli, C., & Pollice, A. (2024). A zero-inflated Poisson spatial model with misreporting for wildfire occurrences in southern Italian municipalities. Environmetrics, e2853. https://doi.org/10.1002/env.2853

 

 

In this study, a new method for assessing and predicting the number of wildfires is introduced. Building upon previous research, the proposed approach is designed to accurately model error-contaminated count data by incorporating spatial relationships between areas. Through simulation studies, it was found that this approach outperforms existing models by effectively capturing spatial heterogeneity and error effects. Furthermore, researchers apply this model to real-world data, specifically examining wildfire occurrences in the municipal areas of two neighboring Italian regions during the summer of 2021. They utilize data obtained from MODIS satellite imagery to quantify wildfire counts and incorporate additional socio-economic and environmental factors into their analysis. The findings reveal significant effects of environmental and social factors on wildfire occurrences, while also considering spatial dependencies among neighboring areas. This information can help in developing strategies for better wildfire prevention and control.