UTCSA: A 0.5-meter resolution urban tree canopy dataset for 888 cities in South America and its pilot applications

Urban development in South America has undergone substantial growth and transformation in recent decades. The development of South American cities is intricately connected with its tree cover, and the presence of trees within urban areas plays a crucial role in shaping sustainable and resilient urban landscapes. Despite this, a comprehensive Urban Tree Canopy (UTC) dataset covering the entire South American continent is currently unavailable. In this study, we used high-resolution remote sensing images and a semi-supervised deep learning method to create UTC data for 888 South American cities. The proposed semi-supervised method can leverage both labeled and unlabeled data during training. By incorporating labeled data for guidance and utilizing unlabeled data to explore underlying patterns, the algorithm enhances model robustness and generalization for urban tree canopy detection across South America, with an average Kappa coefficient of 77.51% and an average overall accuracy of 95% for the tested cities. Based on the created UTC dataset, we conducted several pilot applications, including tree coverage estimation, driving factor exploration, tree-covered space provision assessment, and relationship analysis between UTC coverage and precipitation and urban heat islands. Evidence shows that 1) cities in South America have spatially heterogeneous UTC coverage and inequality in urban tree-covered space provision across South America; 2) natural factors (climatic and geographical) play a very important role in determining UTC coverage, followed by human activity factors; 3) precipitation and seasonal variations in rainfall have a strong impact on tree cover; and 4) tree coverage has the potential to mitigate the effects of urban heat islands. We expect that the created UTC dataset and the findings of this study will help formulate policies and strategies to promote sustainable urban forestry, thus further improving the quality of life of residents in South America.