A 0.6-meter resolution canopy height and structure model for the contiguous United States

Abstract

Above-ground vertical structure is a critical variable for ecosystem monitoring, carbon accounting, and land management. However, the high cost and limited coverage of airborne lidar hinder its widespread application. To address this, we developed NAIP-CHM, a 0.6-meter resolution canopy height and structure model (CHM) covering the contiguous United States, derived from National Agriculture Imagery Program (NAIP) aerial imagery. Unlike forestry-specific models that exclude human-made features, NAIP-CHM characterizes the full vertical structure of the landscape including vegetation, buildings, and infrastructure. We utilized a U-Net convolutional neural network with attention mechanisms and environmental conditioning, training and validating the model with a peer-reviewed, publicly available dataset of 22.8 million co-registered NAIP imagery and lidar-derived CHM pairs, with stratified sampling to ensure robustness in open-canopy ecosystems. The model achieved a pixel-wise root mean square error (RMSE) of 2.28 meters and an r2 of 0.87. Forested sites alone produced an r2 of 0.82 and RMSE of 3.82 meters. We provide the dataset, source code, and cloud-based tools to enable broad application without requiring specialized computational resources.

Code and data availability

The paper's NAIP-CHM canopy height model, its CONUS 0.6 m dataset, trained weights, and full training/inference code are all publicly released with explicit availability statements and author-hosted URLs (Rangeland Analysis Platform server, GitHub, Zenodo, Colab notebook, Earth Engine app).