Articles | Volume 22, issue 21
https://doi.org/10.5194/bg-22-6509-2025
https://doi.org/10.5194/bg-22-6509-2025
Research article
 | 
06 Nov 2025
Research article |  | 06 Nov 2025

Identifying alpine treeline species using high-resolution WorldView-3 multispectral imagery and convolutional neural networks

Laurel A. Sindewald, Ryan Lagerquist, Matthew D. Cross, Theodore A. Scambos, Peter J. Anthamatten, and Diana F. Tomback

Data sets

Sindewald et al - Identifying alpine treeline species using high-resolution WorldView-3 multispectral imagery and convolutional neural networks dataset L. Sindewald https://zenodo.org/records/14942410

Model code and software

thunderhoser/wv3_species_classification: Release for 2025 journal paper (v1.0.0) R. Lagerquist https://doi.org/10.5281/zenodo.14946216

Download
Short summary
We used high-resolution satellite imagery and artificial intelligence models to identify six tree and shrub species commonly found at alpine treeline in the Rocky Mountains with accuracies from 44.1% to 86.2%. We are the first to attempt species identification using satellite imagery in treeline systems, where trees are small and difficult to identify remotely. Our work provides a method to identify species with satellite imagery over a broader geographic range than can be achieved with drones.
Share
Altmetrics
Final-revised paper
Preprint