Determination of the optimum number of sample points to classify land cover types and estimate the contribution of trees on ecosystem services using the I‐Tree Canopy tool.

This article focuses on determining the optimum number of random sampling points required when using the I-Tree Canopy tool for land cover classification and assessing tree contributions to ecosystem services. I-Tree Canopy, developed by the US Department of Agriculture Forest Service, is a free, user-friendly software that estimates tree cover and its ecological benefits through sampling points interpreted from aerial imagery. By comparing 31 reports with sample sizes ranging from 100 to 3100 points against high-precision reference data for a 1-hectare urban area in Antalya, Turkey, the study found that approximately 760 ± 32 sampling points optimize accuracy for land cover classification, while about 714 ± 16 points suffice for estimating carbon sequestration and air pollution reduction. The findings suggest that increasing sample points beyond 800 does not significantly improve statistical accuracy, providing guidance for balancing precision and resource expenditure in ecological assessments using I-Tree Canopy.