Journal
IEEE JOURNAL OF SELECTED TOPICS IN APPLIED EARTH OBSERVATIONS AND REMOTE SENSING
Volume 8, Issue 11, Pages 5246-5261Publisher
IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
DOI: 10.1109/JSTARS.2015.2478478
Keywords
Forest volume; Lorey's height; maximum height; geoscience laser altimeter system (GLAS)/Ice; Cloud and land Elevation Satellite (ICESat); Iran; light detection and ranging; (LiDAR)
Categories
Funding
- Iran National Science Foundation (INSF)
- Cotutelle
Ask authors/readers for more resources
The importance of measuring forest biophysical properties for ecosystem health monitoring and forest management encourages researchers to find precise, yet low-cost methods especially in mountainous and large areas. In the present study, geoscience laser altimeter system (GLAS) on board Ice, Cloud, and land Elevation Satellite (ICESat) was used to estimate three biophysical characteristics of forests located in the north of Iran: 1) maximum canopy height (H-max); 2) Lorey's height (H-Lorey); and 3) forest volume (V). A large number of multiple linear regressions (MLR) and also random forest (RF) regressions were developed using different sets of variables including waveform metrics, principal components (PCs) produced from principal component analysis (PCA) and wavelet coefficients (WCs) generated from wavelet transformation (WT). To validate and compare models, statistical criteria were calculated based on a fivefold cross validation. Best model concerning the maximum height was an MLR (RMSE = 5.0 m) which combined two metrics extracted from waveforms (waveform extent W-ext and height at 50% of waveform energy H-50), and one from digital elevation model (terrain index, TI). The mean absolute percentage error (MAPE) of maximum height estimates was 16.4%. For Lorey's height, a simple MLR (including W-ext and TI) represented the highest performance (RMSE = 5.1 m, MAPE = 24.0%). Generally, MLR models had a better performance when compared to the RF models. In addition, the accuracy of height estimations using waveform metrics was greater than those based on PCs or WCs. Concerning forest volume, regression models estimating volume directly from GLAS data led to a better result (RMSE = 128.8 m(3)/ha) rather than volume-HLorey relationship (RMSE = 167.8 m(3)/ha).
Authors
I am an author on this paper
Click your name to claim this paper and add it to your profile.
Reviews
Recommended
No Data Available