Different Perspectives on the Same Target: Field and Laboratory Spectroscopy for Estimating Nitrogen Content in Sugarcane Leaves

Abstract

Proper nitrogen (N) management is essential for increasing the productivity of sugarcane (Saccharum spp.) and reducing the economic and environmental impacts associated with excessive fertilizer use. This study compared the performance of two portable spectroradiometers, FieldSpec 3 and HandHeld 2, in estimating foliar nitrogen content based on hyperspectral data in the visible and near-infrared regions, obtained throughout the crop cycle. The experiment was conducted in Piracicaba, São Paulo, Brazil, under four N rates: 0, 60, 120, and 180 kg ha−1. Spectral measurements were taken at the foliar and canopy levels at eight evaluation times, accompanied by laboratory determination of N content. Partial Least Squares Regression (PLSR) and Random Forest (RF) models were fitted using the spectral data and days after cutting (DAC), included as a categorical factor and evaluated using 10-fold internal cross-validation, based on the metrics R2, RMSE, MAE, and Willmott’s refined agreement index (dr). The foliar data performed better with PLSR (R2 = 0.727; RMSE = 1.381 g kg−1; MAE = 1.109; dr = 0.917) than canopy data (R2 = 0.591; RMSE = 1.489 g kg−1; MAE = 1.157; dr = 0.866). PLSR also outperformed RF at both acquisition levels. The green (~550 nm) and red edge (~740 nm) regions were the most relevant for N estimation. Under the evaluated conditions, model performance was associated with the spectral acquisition level and conditions, the instrumental configuration, and the modeling strategy employed.

Code and data availability

The supplied blocks describe hyperspectral leaf/canopy data collection and PLSR/RF modeling for sugarcane nitrogen estimation, but contain no data availability statement, no public repository deposit, and no author code/model release. The only software mentioned (ParLeS v3.1, R pls package) is a generic third-party or-

No evidence-backed public reproduction asset is currently recorded.