Skip to main content

Advertisement

Table 3 Model performance over different wavelength ranges

From: Predicting the quality of ryegrass using hyperspectral imaging

Variable HSI data Wavelength range # LV PLSR R2 calibration RMSE calibration R2 validation RMSE validation Validation intercept Validation slope Validation prediction bias
Sugars (mg/g) BL + PS 550–1700 nm 12 0.70 28.9 0.58 34.4 10.1 ± 9.6 mg/g 0.93 ± 0.10 − 3.8 mg/g
Sugars (mg/g) BL + PS 550–900 nm 5 0.18 47.6 0.20 47.7 − 15.3 ± 27.6 mg/g 1.20 ± 0.30 − 2.54 mg/g
Sugars (mg/g) BL + PS 900–1700 nm 8 0.53 36.0 0.43 40.1 18.8 ± 11.6 mg/g 0.85 ± 0.12 − 4.9 mg/g
Nitrogen (%) BL + PS 550–1700 nm 20 0.86 0.25 0.70 0.35 0.69 ± 0.22% 0.80 ± 0.067 − 0.05%
Nitrogen (%) BL + PS 550–900 nm 13 0.71 0.36 0.41 0.48 1.19 ± 0.31% 0.64 ± 0.10 − 0.06%
Nitrogen (%) BL + PS 900–1700 nm 7 0.62 0.41 0.44 0.47 0.64 ± 0.37% 0.79 ± 0.11 0.04%
  1. HSI data, mean reflectance spectra analysed by PLSR model (Blades (BL) + pseudostems (PS) using Standard Normal Variate (SNV) preprocessing. Models are based on 550–1700 nm (original model based on full spectral range) and restricted wavelength ranges of 550–900 nm and 900–1700 nm