摘要：The context in which trees and forests grow in cities is highly variable and influences the provision of ecological, social, and economic benefits. Understanding the spatial extent, structure, and composition of forests is necessary to guide urban forest policy and management, yet current forest assessment methodologies vary widely in scale, sampling intensity, and focus. Current definitions of the urban forest include all trees growing in the urban environment, and have been translated to the design of urban forest assessments. However, such broad assessments may aggregate types of urban forest that differ significantly in usage and management needs. For example, street trees occur in highly developed environments, and are planted and cared for on an individual basis, whereas forested natural areas often occur in parkland, are managed at the stand level, and are primarily sustained by natural processes such as regeneration. We use multiple datasets for New York City to compare the outcomes from assessments of the entire urban forest, street trees, and forested natural areas. We find that non-stratified assessments of the entire urban forest are biased towards abundant canopy types in cities (e.g. street trees) and underestimate the condition of forested natural areas due to their uneven spatial arrangement. These natural areas account for one quarter of the city's tree canopy, but represent the majority of trees both numerically and in terms of biomass. Non-stratified assessments of urban forest canopy must be modified to accurately represent the true composition of different urban forest types to inform effective policy and management.
