Daniel C. Buckler

Potential impacts from climate change and other disturbances expedite the need to address vulnerabilities of urban forests. Low species diversity is a contributor to high urban forest vulnerability, and this study examined 40 public and private tree inventories in the metropolitan area of Milwaukee, Wisconsin, USA. Applying an established vulnerability framework, this study helps to identify the current and future resilience of the urban forest in the face of climate change and other urban forest threats. A Milwaukee metropolitan area tree inventory was compiled and includes 439,974 trees. This inventory then was assessed under 2 climate change models through the end of the century (2070 to 2099). It also was assessed for species diversity under multiple diameter classes, and the Shannon Diversity Index was used to determine correlations between tree size and diversity. The resulting data analysis revealed a poorly diversified urban tree canopy in the Milwaukee metropolitan area. However, when looking at tree size and diversity, diversity increased as tree diameters decreased. Additional analysis revealed that under a low climate change scenario (RCP 4.5), only 9.5% of the overall inventory was within the moderate, moderate-high, or high vulnerability categories through the end of the century. Under a high climate change scenario (RCP 8.5), 55.52% of the inventory fell within those same vulnerability categories. Diameter class did not have a significant impact on vulnerability under either climate change scenario. This data can help inform urban forestry practitioners during species selection for planting trees in their communities.

Urban tree canopy (UTC) is commonly used to assess urban forest extent and has traditionally been estimated using photointerpretation and human intelligence (HI). Artificial intelligence (AI) models may provide a less labor-intensive method to estimate urban tree canopy. However, studies on how human intelligence and artificial intelligence estimation methods compare are limited. We investigated how human intelligence and artificial intelligence compare with estimates of urban tree canopy and other landcovers. Change in urban tree canopy between two time periods and an assessment agreement accuracy also occurred. We found a statistically significant (p < 0.001) difference between the two interpretations for a statewide urban tree canopy estimate (n = 397). Overall, urban tree canopy estimates were higher for human intelligence (31.5%, 0.72 SE) than artificial intelligence (26.0%, 0.51 SE). Artificial intelligence approaches commonly rely on a training data set that is compared against a human decision maker. Within the artificial intelligence training region (n = 21) used for this study, no difference (p = 0.72) was found between the two methods, suggesting other regional factors are important for training the AI system. Urban tree canopy also increased (p < 0.001) between two time periods (2013 to 2018) and two assessors could detect the same sample point over 90 % of the time.