Urban Tree Canopy Data for Deep Learning Applications in Boyle Heights and City Terrace, Los Angeles, California, USA

This dataset was prepared and processed as part of the research publication titled “A Practical, Open, and Transferable Deep Learning Framework for Mapping Urban Tree Canopy Using NAIP Imagery.” The zipped dataset includes geospatial data covering the Boyle Heights and City Terrace neighborhoods of Los Angeles, California, USA. It contains: Manually delineated polygon shapefiles representing urban tree canopy cover; Polygon shapefiles defining the spatial sampling schema used for analysis within the study area; NAIP imagery for the same area, originally provided by the U.S. Department of Agriculture (USDA) through the National Agriculture Imagery Program (NAIP) GeoHub (https://naip-usdaonline.hub.arcgis.com/, last accessed October 28, 2025); and Datasets specifically prepared for U-Net and YOLO deep learning model development for urban tree canopy mapping, intended for coordinated use with the corresponding Python repository (https://github.com/uscssi/urban-tree-canopy). This dataset supports research and education in urban forestry, remote sensing, geospatial analysis, and deep learning applications for environmental monitoring. It can be used to validate automated canopy mapping models, assess urban vegetation change, or serve as training data for AI-based land cover classification. Citation: Yoo, J., Qi, Y., Ashe-McNally, I., MacDonald, B., & Wilson, J. P. (2025). Urban Tree Canopy Data for Deep Learning Applications in Boyle Heights and City Terrace, Los Angeles, California, USA [Data set]. Zenodo. https://doi.org/10.5281/zenodo.17459767 Funding:This research was supported by the Bezos Earth Fund (Grant G-2022-34351), the Climate-related Exposures, Adaptation, and Health Equity (CLIMA) Center funded by the National Heart, Lung, and Blood Institute (Grant P20HL176204), and the Southern California Environmental Health Science Center funded by the National Institute of Environmental Health Sciences (Grant P30ES007048).