Deep-learning-based regression model and hyperspectral imaging for rapid detection of nitrogen concentration in oilseed rape (Brassica napus L.) leaf

• Published in: Chemometrics and intelligent laboratory systems Vol. 172; pp. 188 - 193
• Main Authors: Yu, Xinjie, Lu, Huanda, Liu, Qiyu
• Format: Journal Article
• Language: English
• Published: Elsevier B.V 15.01.2018
• Subjects: Deep learning; Fully-connected neural network; Nitrogen concentration; Nondestructive detection; Oilseed rape; Stacked auto-encoders; Deep learning; Oilseed rape; Nitrogen concentration; Nondestructive detection; Stacked auto-encoders; Fully-connected neural network
• ISSN: 0169-7439; 1873-3239
• DOI: 10.1016/j.chemolab.2017.12.010

Deep-learning-based regression model composed of stacked auto-encoders (SAE) and fully-connected neural network (FNN) was used for the detection and quantification of nitrogen (N) concentration in oilseed rape leaf. SAE was applied to extract deep spectral features from visible and near-infrared (380–1030 nm) hyperspectral image of oilseed rape leaf, and then these features were used as input data for FNN to predict N concentration. The SAE-FNN model achieved reasonable performance with R2P = 0.903, RMSEP =0 .307% and RPDP = 3.238 for N concentration. Results confirmed the possibility of rapid and nondestructive detecting N concentration in oilseed rape leaf by the combination of hyperspectral imaging technique and deep learning method. •Hyperspectral imaging could non-destructively detect N in oilseed rape leaf.•Deep spectral features were extracted by SAE.•SAE-FNN model was applied to fit the spectral features to N content.