Estimating canopy nitrogen concentration of sugarcane crop using in situ spectroscopy

Abstract

Estimating nitrogen (N) concentration in situ is fundamental for managing the fertilization of the sugarcane crop. The purpose of this work was to develop estimation models that explain how N varies over time as a function of three spectral data transformations in two stages (plant cane and first ratoon) under variable rates of N application. A randomized complete-block experimental design was applied, with four levels of N fertilization: 0, 80, 160, and 240 kg N ha −1 . Six sampling events were carried out during the rapid growth stage, where the canopy reflectance spectra with a hyperspectral sensor were measured, and tissue samples for N determination in plant cane and first ratoon were taken, from 60 days after emergence (DAE) and 60 days after harvest (DAH), respectively, until days 210 DAE and 210 DAH. To build the models, partial least squares regression analysis was used and was trained by three transformations of the spectral data: (i) average reflectance spectrum (R), (ii) multiple scatter correction and Savitzky-Golay filter MSC-SG) reflectance spectrum, and (iii) calculated vegetation indices (VIs).

Prediction of leaf nitrogen in sugarcane (Saccharum spp.) by Vis-NIR-SWIR spectroradiometry

“…According to the magnitudes, the regions of visible (450–680 nm) and red-edge (680–750 nm) were the most important spectral ranges. Therefore, the models generated with only the effective wavelengths (450–680 nm) presented the best performance (R 2 > 0.81, RMSE <1.24 g kg −1 , d index >0.94), which is in accordance with the literature [ 18 , 36 , 38 ]. Li et al (2016) selected, by the VIP values, the spectral wavelengths at 432, 467, 519, 614, 772, 912 and 1072 nm to generate nitrogen prediction models with greater precision for the canola crop ( Brassica napus L.); consequently, the new models achieved values of R 2 > 0.86, being considered acceptable.…”

“…The spectral region of blue (450–500 nm) recorded a high participation in the predictions, which is interesting, since the region of blue is not commonly associated to the nutritional stress of the plant, generating situations for greater investigations. Nonetheless, these findings have already been mentioned in other studies [ 36 , 38 ].…”

“…The prediction of the nitrogen contents by the leaf spectral behavior was performed using the technique PLSR with the algorithm NIPALS. This is a multivariate analysis technique which can treat correlated independent variables (wavelengths) and relatively few observations, reduce them to a set of components, avoiding multicollinearity for the estimation of a set of dependent variables (LNC) [ 36 ]. During the calibration step, PLSR uses the information of the independent variables (spectra) and dependent variables (N contents), to generate new variables called latent variables (or factors).…”

An Advanced Framework for Multi-Scale Forest Structural Parameter Estimations Based on UAS-LiDAR and Sentinel-2 Satellite Imagery in Forest Plantations of Northern China

“…Normalized Difference Vegetation Index (NDVI) (B7 − B4)/(B7 + B4) [47] MERIS Terrestrial Chlorophyll Index (MTCI) (B6 − B5)/(B5 − B4) [48] Water Index (WI) B8a/B9 [49] Corrected Transformed Vegetation Index (CTVI) (NDVI + 0.5)/abs(NDVI + 0.5) abs(NDVI + 0.5) [50] Enhanced Vegetation Index Red Edge 1(B5) (EVIRE1) 2.5 × (B5 − B4)/(1 + B5 + 6 × B4 − 7.5 × B2) [51] Enhanced Vegetation Index Red Edge 2(B6) (EVIRE2) 2.5 × (B6 − B4)/(1 + B6 + 6 × B4 − 7.5 × B2) [52] Nir infrared Enhanced Vegetation Index (EVINI)…”