A 0.6-meter resolution canopy height and structure model for the contiguous United States
Morford, S. L.; Allred, B. W.; Coons, S. P.; Marcozzi, A. A.; McCord, S. E.; Smith, J. T.; Naugle, D. E.
Show 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 the model on 18 million lidar-derived training pairs with stratified sampling to ensure robustness in open-canopy ecosystems. Assessing performance against 2.3 million independent samples, the model achieved a root mean square error of 1.57 meters and coefficient of determination (r2) of 0.87. We release the dataset, source code, and cloud-based tools to enable broad application without requiring specialized computational resources.
Matching journals
The top 4 journals account for 50% of the predicted probability mass.
Similar papers in this journal
- Individual tree-crown detection in RGB imagery using semi-supervised deep learning neural networks 94%
- Classification of daily crop phenology in PhenoCams using deep learning and hidden markov models 94%
- Continuous land cover change detection in a critically endangered shrubland ecosystem using neural networks 93%
Similar papers in this journal
- Mapping Tree Cover Expansion in Montana, U.S.A. Rangelands using High-Resolution Historical Aerial Imagery 95%
- Accurate delineation of individual tree crowns in tropical forests from aerial RGB imagery using Mask R-CNN 93%
- Being confident in confidence scores : calibration in deep learning models for camera trap image sequences 91%
Similar papers in this journal
"Similar papers" are the closest papers from that journal in the model's embedding space. They show what the match is built on, but the ranking comes mostly from a classifier over the whole training set, not from these examples alone.