Basic research toward the application use of hyperspectral remote sensing for assessing pasture quality status

点击翻译按钮获取中文摘要

The results indicated that herbage biomass, concentrations of nitrogen (N), crude protein (CP), neutral detergent fiber (NDF), acid detergent fiber (ADF), and legume content in white clover-grass mixtures can be estimated from field hyperspectral measurements. Furthermore, the important wavebands to predict pasture parameters were obtained from waveband selection based on genetic algorithm (GA) using partial least squares (PLS) regression, and GA-PLS refined the predictive ability.