Onsite nutritional diagnosis of tea plants using micro near-infrared spectrometer coupled with chemometrics

•Smartphone-based NIRS technique was used for onsite nutritional diagnosis.•Two tea plant varieties widely cultivated in China were analyzed and studied.•Two novel algorithms, VCPA and VCPA-GA, were introduced to simplify the models.•The simplified models for three photosynthetic pigments yielded go...

Full description

Saved in:
Bibliographic Details
Published in:Computers and electronics in agriculture 2020-08, Vol.175, p.105538, Article 105538
Main Authors: Wang, Yu-Jie, Jin, Shan-Shan, Li, Meng-Hui, Liu, Ying, Li, Lu-Qing, Ning, Jing-Ming, Zhang, Zheng-Zhu
Format: Article
Language:English
Subjects:
Bluetooth
Chemometrics
Chlorophyll
Correlation coefficients
Diagnosis
Genetic algorithms
Infrared spectra
Infrared spectrometers
Micro near-infrared spectrometer
Near infrared radiation
Nutrition
Pigment contents
Portable equipment
Regression analysis
Smartphones
Tea plants
Variable combination population analysis
VCPA-GA hybrid strategy
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:•Smartphone-based NIRS technique was used for onsite nutritional diagnosis.•Two tea plant varieties widely cultivated in China were analyzed and studied.•Two novel algorithms, VCPA and VCPA-GA, were introduced to simplify the models.•The simplified models for three photosynthetic pigments yielded good performance. A rapid and accurate diagnosis of nutritional status in field crops is crucial for site-specific fertilizer management. The micro near-infrared spectrometer (Micro-NIRS) is an extremely portable optical device that can be connected to a smartphone through a Bluetooth connection. In this study, a Micro-NIRS was used to evaluate pigment contents, namely chlorophyll a (Chl-a), chlorophyll b (Chl-b), and carotenoid (Car) in two varieties of field tea plants. A variable combination population analysis (VCPA), genetic algorithm (GA), and VCPA-GA hybrid strategy were used to select characteristic wavelengths; a partial least squares regression (PLSR) algorithm was employed for modeling. Results indicated that the simplified VCPA-GA-PLSR models provided the most favorable performance among all models for Chl-a, Chl-b, and Car content prediction; the correlation coefficients in prediction (Rps) were 0.9226, 0.9006, and 0.8313, respectively; the root mean square errors in prediction (RMSEPs) were 0.0952, 0.0771, and 0.0373 mg/g, respectively; the relative prediction deviations (RPDs) were 2.55, 1.92, and 1.79, respectively. Extracted characteristic variables occupied
ISSN:0168-1699
1872-7107
DOI:10.1016/j.compag.2020.105538