Saved in:
| Main Author: | |
|---|---|
| Format: | Recurso digital |
| Language: | |
| Published: |
Zenodo
2025
|
| Online Access: | https://doi.org/10.5281/zenodo.17656503 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
Table of Contents:
- <p>This dataset is released under an open-access policy and is freely available for unrestricted use, redistribution, and analysis. Users are kindly requested to cite the Zenodo DOI associated with this dataset in any derivative work to ensure proper attribution and to facilitate tracking of data reuse.</p> <p>This dataset contains forest structural parameters estimated for natural Schrenk spruce (<em>Picea schrenkiana</em>) stands in the western Tianshan Mountains. The data were derived from an integrated modeling framework that combined UAV-LiDAR measurements with multi-source remote sensing data. Forest canopy height, mean tree height, stand density, and aboveground biomass (AGB) were predicted using a Bayesian-optimized Random Forest model. UAV-LiDAR provided high-precision structural reference data for model training, while SRTM DEM, Sentinel-1 SAR, and Sentinel-2 optical products served as predictor variables.</p> <p>This represents the first large-scale application of UAV-LiDAR to characterize forest structure in this region. The Bayesian optimization procedure efficiently identified the optimal hyperparameters for the Random Forest model, enabling robust and accurate prediction of forest structural attributes across the study area. </p>