The urban forest at risk: unveiling windstorm-induced tree fall patterns through spatial and machine learning analyses in a medium-large city in Southern Brazil

Key message

Our study reveals spatial patterns and meteorological drivers of urban tree falls, enabling enhanced urban tree risk management.

Abstract

Urban forestry plays a crucial role in maintaining the safety and resilience of urban environments yet understanding the spatial dynamics and underlying factors of tree fall incidents remains a complex challenge. In this study, we conducted a comprehensive analysis of tree fall incidents in Maringá, Paraná, Brazil, from 2015 to 2021, using kernel density estimation, inhomogeneous L function analysis, and regression tree modeling. Our findings reveal intriguing spatial patterns, with higher concentrations of incidents in the northern and northeastern regions of the city. Moreover, we identified dynamic changes in spatial distributions over time, emphasizing the need for proactive urban planning and risk management strategies. Regression tree analysis highlighted meteorological factors as significant contributors to tree falls, providing actionable insights for risk mitigation efforts. Overall, our study contributes to a better understanding of the spatial dynamics of tree fall incidents and advocates for standardized data collection methods and the development of tools to enhance urban forestry management and promote safer urban environments.