Discrimination of Genetically Very Close Accessions of Sweet Orange (Citrus sinensis L. Osbeck) by Laser-Induced Breakdown Spectroscopy (LIBS)

Abstract

The correct recognition of sweet orange (Citrus sinensis L. Osbeck) variety accessions at the nursery stage of growth is a challenge for the productive sector as they do not show any difference in phenotype traits. Furthermore, there is no DNA marker able to distinguish orange accessions within a variety due to their narrow genetic trace. As different combinations of canopy and rootstock affect the uptake of elements from soil, each accession features a typical elemental concentration in the leaves. Thus, the main aim of this work was to analyze two sets of ten different accessions of very close genetic characters of three varieties of fresh citrus leaves at the nursery stage of growth by measuring the differences in elemental concentration by laser-induced breakdown spectroscopy (LIBS). The accessions were discriminated by both principal component analysis (PCA) and a classifier based on the combination of classification via regression (CVR) and partial least square regression (PLSR) models, which used the elemental concentrations measured by LIBS as input data. A correct classification of 95.1% and 80.96% was achieved, respectively, for set 1 and set 2. These results showed that LIBS is a valuable technique to discriminate among citrus accessions, which can be applied in the productive sector as an excellent cost–benefit tool in citrus breeding programs.

Application and Research Progress of Laser-Induced Breakdown Spectroscopy in Agricultural Product Inspection

“…Olive oil, another extensively studied agricultural product, demonstrates a strong link between quality and geographical factors. The Stelios Couist team pioneered the application of machine learning-assisted LIBS technology for olive oil classification, yielding highly accurate classification outcomes. , Furthermore, in citrus breeding, Magalhaes et al effectively employed LIBS technology to distinguish different citrus varieties, introducing a novel research avenue for citrus breeding.…”

Laser-Induced Breakdown Spectroscopy Associated with the Design of Experiments and Machine Learning for Discrimination of Brachiaria brizantha Seed Vigor

“…Instrumental parameters of LIBS influence the interaction of the laser pulse with the sample and the acquisition of the analytical signal. Thus, a 2 3 factorial design with a central point (Table 2) was used to optimize the variables at three levels: (i) laser pulse energy (29.73, 42.29, and 54.86 mJ), (ii) delay time (0.5, 1.0, and 1.5 µs), and (iii) the analytical signal acquisition time (1,11, and 20 µs) to obtain the LIBS spectrum. A total of 11 experiments were carried out.…”

“…Photonic techniques and machine learning algorithms have been extensively used to improve agricultural management in the past few years, mainly due to their high accuracy associated with their fast response, low analytical cost, simplified sample preparation, and environmentally clean techniques [ 7 , 8 , 9 , 10 , 11 , 12 ]. Recently, our research group demonstrated the potential application of the Fourier-transform infrared (FTIR) and Laser-induced breakdown spectroscopy (LIBS) for seed vigor classification [ 5 , 8 , 13 ].…”

Laser-Induced Breakdown Spectroscopy: An Efficient Tool for Food Science and Technology (from the Analysis of Martian Rocks to the Analysis of Olive Oil, Honey, Milk, and Other Natural Earth Products)

“…Larios et al [ 42 ] discriminated low and high-vigor soybean seed lots, using LIBS along with machine learning techniques such as Principal Components Analysis (PCA), Support Vector Machines (SVMs), Linear Discriminant Analysis (LDA), Quadratic Discriminant Analysis (QDA), and k-Nearest Neighbors (k-NN). Furthermore, LIBS has been used for discrimination of both the cultivar [ 43 , 44 ] and geographical origin [ 45 ] of different kinds of foodstuffs. In that view, Perez-Rodriguez et al [ 43 ], after selecting the emission lines of carbon (C), calcium (Ca), iron (Fe), magnesium (Mg), and sodium (Na) and using the Extreme Gradient Boosting (XGBoost) algorithm, developed a k-NN model able to predict the cultivar of brown rice with accuracy up to 86%.…”

“…In that view, Perez-Rodriguez et al [ 43 ], after selecting the emission lines of carbon (C), calcium (Ca), iron (Fe), magnesium (Mg), and sodium (Na) and using the Extreme Gradient Boosting (XGBoost) algorithm, developed a k-NN model able to predict the cultivar of brown rice with accuracy up to 86%. Similarly, Megalhães et al [ 44 ] used LIBS combined with some machine learning algorithms (i.e., PCA, PLSR, etc.) and achieved the successful discrimination of some sweet oranges, with similar DNA, with high accuracy.…”