Retrieval of the canopy chlorophyll content from Sentinel-2 spectral bands to estimate nitrogen uptake in intensive winter wheat cropping systems

• Published in: Remote sensing of environment 2018-10, Vol.216, p.245-261
• Main Authors: Delloye, Cindy, Weiss, Marie, Defourny, Pierre
• Format: Article
• Language: English
• Subjects: Agriculture; Artificial neural network; Artificial neural networks; Biodiversity and Ecology; Canopies; Canopy chlorophyll content; Cereal crops; Chlorophyll; Chlorophyll content; Correlation analysis; Cropping systems; Crops; Cultivars; Dependence; Environmental impact; Environmental Sciences; Estimation accuracy; Fertilization; Heterogeneity; Intensive cropping systems; Neural networks; Nitrogen; Nitrogen content; Numerical controls; Nutrition; Nutrition assessment; Precision agriculture; Red-edge bands; Remote sensing; Satellite imagery; Scaling issue; Sentinel-2; Spectral bands; Wheat; Winter wheat
• ISSN: 0034-4257; 1879-0704
• DOI: 10.1016/j.rse.2018.06.037

One of the most common approaches to reducing the environmental impact of nitrogen (N) fertilisation in intensive agrosystems is to adjust the N input of the crop requirement. This adjustment is frequently related to the nitrogen nutrition index (NNI) based on the concepts of the critical and actual N absorbed (kg/ha) in the crop canopy (respectively, NC and CNC). Accurate estimation of the NC and CNC at the field scale over large areas based on freely available satellite imagery is thus a key issue to address. Relying on a large dataset of farmers' fields, this study highlights the high correlation (R2 = 0.90) between the wheat CNC and canopy chlorophyll content (CCC) retrieved from Sentinel-2 (S2) with an Artificial Neural Network (ANN). The estimation is related to errors of 4 and 21 kg/ha (depending on the growing stage), which is a promising result for evaluating the NNI. There are four major outcomes from this result: (i) the importance of working at the canopy level; (ii) the independence of the relationship to the considered cultivars; (iii) the dependence of the relationship on the growing stage; and (iv) the potential to use only the 10 m S2 bands, opening the way for precision agriculture. In parallel, estimation accuracies were investigated for the three biophysical variables (BV) related to the CNC and NC, i.e., the green area index (GAI), leaf chlorophyll content (Cab) and CCC. From this analysis, the added value of the red-edge bands for improving the estimation of the 3 BVs of interest was quantified as was the performance reduction related to the field heterogeneity. •The wheat nitrogen content can be estimated only with the 10 m bands of Sentinel-2.•The wheat nitrogen content is accurately estimated at the canopy level.•Within-pixel heterogeneity affects the GAI estimation accuracy.•The red-edge bands increase the GAI estimation accuracy along the growing season.