摘要：Warming in the Arctic has resulted in a lengthening of the growing season and changes to the distribution and composition of tundra vegetation including increased biomass quantities in the Low Arctic. Biomass has commonly been estimated using broad-band greenness indices such as NDVI; however, vegetation changes in the Arctic are occurring at spatial scales within a few meters. The aim of this paper is to assess the ability of hyperspectral remote sensing data to estimate biomass quantities among different plant tissue type categories at the North Slope site of Ivotuk, Alaska. Hand-held hyperspectral data and harvested biomass measurements were collected during the 1999 growing season. A subset of the data was used as a training set, and was regressed against the hyperspectral bands using LASSO. LASSO is a modification of SPLS and is a variable selection technique that is useful in studies with high collinearity among predictor variables such as hyperspectral remote sensing. The resulting equations were then used to predict biomass quantities for the remaining Ivotuk data. The majority of significant biomass-spectra relationships (65%) were for shrubs categories during all times of the growing season and bands in the blue, green, and red edge wavelength regions of the spectrum. The ability to identify unique biomass-spectra relationships per community is decreased at the height of the growing season when shrubs obscure lower-lying vegetation such as mosses. The results of this study support previous research arguing that shrubs are dominant controls over spectral reflectance in Low Arctic communities and that this dominance results in an increased ability to estimate shrub component biomass over other plant functional types.
