Abstract
Hyperspectral remote sensing research was conducted to document the biophysical and biochemical characteristics of controlled forest plots subjected to various nutrient and irrigation treatments. The experimental plots were located on the Savannah River Site near Aiken, SC. AISA hyperspectral imagery were analysed using three approaches, including: (1) normalized difference vegetation index based simple linear regression (NSLR), (2) partial least squares regression (PLSR) and (3) machine-learning regression trees (MLRT) to predict the biophysical and biochemical characteristics of the crops (leaf area index, stem biomass and five leaf nutrients concentrations). The calibration and cross-validation results were compared between the three techniques. The PLSR approach generally resulted in good predictive performance. The MLRT approach appeared to be a useful method to predict characteristics in a complex environment (i.e. many tree species and numerous fertilization and/or irrigation treatments) due to its powerful adaptability.
Keywords
remote sensing,
hyperspectral analysis,
partial least squares regression,
machine learning,
regression trees,
NDVI,
leaf nutrients,
leaf are index,
biomass
Citation
Im, Jungho; Jensen, John R.; Coleman, Mark; Nelson, Eric. 2009. Hyperspectral remote sensing analysis of short rotation woody crops grown with controlled nutrient and irrigation treatments. Geocarto International 24(4):293-312.
