Rapid Assessment of Nitrogen Concentration of Two Bioenergy Feedstock Grasses Using Hyperspectral Reflectance Spectroscopy

Abstract

Rapidly and accurately monitoring crop nitrate concentration is critical for both plant nutrient management and animal health, but can be difficult. Traditional methods are laborious and require destructive plant samplings followed by chemical analyses, thus, alternative methods are warranted. The objective of this research was to design a rapid nitrate assessment method using two native warm-season grass (NWSG) species, including ‘Alamo’ switchgrass (Panicum virgatum L.) and ‘Cheyenne’ indiangrass [Sorghastrum nutans (L.) Nash]. Both grass species were planted in a greenhouse and fertilized with urea at control (0 kg N ha-1), low (65 kg N ha-1), medium (130 kg N ha-1), and high (260 kg N ha-1) rates. Plant height and leaf chlorophyll data were recorded weekly. Hyperspectral spectroscopy analysis and machine learning-based simulation approaches were used for building prediction models. The models accurately estimated botanical nitrate concentration even at its low level using data acquired from both years (R2 = 0.88 and RMSE = 0.358).