Comparison of prediction power of three multivariate calibrations for estimation of leaf anthocyanin content with visible spectroscopy in Prunus cerasifera.

Xiuying Liu,Qingrui Chang,Chenzhou Liu,Zhaoyong Shi

doi:10.7717/peerj.7997

Abstract

The anthocyanin content in leaves can reveal valuable information about a plant’s physiological status and its responses to stress. Therefore, it is of great value to accurately and efficiently determine anthocyanin content in leaves. The selection of calibration method is a major factor which can influence the accuracy of measurement with visible and near infrared (NIR) spectroscopy. Three multivariate calibrations including principal component regression (PCR), partial least squares regression (PLSR), and back-propagation neural network (BPNN) were adopted for the development of determination models of leaf anthocyanin content using reflectance spectra data (450–600 nm) in Prunus cerasifera and then the performance of these models was compared for three multivariate calibrations. Certain principal components (PCs) and latent variables (LVs) were used as input for the back-propagation neural network (BPNN) model. The results showed that the best PCR and PLSR models were obtained by standard normal variate (SNV), and BPNN models outperformed both the PCR and PLSR models. The coefficient of determination (R2), the root mean square error of prediction (RMSEp), and the residual prediction deviation (RPD) values for the validation set were 0.920, 0.274, and 3.439, respectively, for the BPNN-PCs model, and 0.922, 0.270, and 3.489, respectively, for the BPNN-LVs model. Visible spectroscopy combined with BPNN was successfully applied to determine leaf anthocyanin content in P. cerasifera and the performance of the BPNN-LVs model was the best. The use of the BPNN-LVs model and visible spectroscopy showed significant potential for the nondestructive determination of leaf anthocyanin content in plants.

Highlights

Anthocyanins are a large group of water soluble flavonoid pigments (Strack, 1997; Iwashina, 2000), the common pigment, that occur in all tissues of higher plants, including the leaves, How to cite this article Liu X, Liu C, Shi Z, Chang Q. 2019
In the principal component regression (PCR) and Partial least squares (PLS) models, spectra the preprocessed by standard normal variate (SNV) achieved the best performance for the prediction of anthocyanin content
Acceptable prediction accuracies were achieved by the PCR and PLS models, but this level of accuracy may be not satisfactory for practical applications

Summary

Introduction

Anthocyanins are a large group of water soluble flavonoid pigments (Strack, 1997; Iwashina, 2000), the common pigment, that occur in all tissues of higher plants, including the leaves, How to cite this article Liu X, Liu C, Shi Z, Chang Q. 2019. Anthocyanins serve many functions, including pollinator attraction, as protectants (Gould, Davies & Winefield, 2009), as antioxidants (Gould, McKelvie & Markham, 2002; Yang et al, 2017), and as osmoprotectants (Chalker-Scott, 1999). These compounds play a photo-protective role (Liakopoulos et al, 2006), and act as optical barriers (Close & Beadle, 2003; Solovchenko & Merzlyak, 2008). This measurement method does not allow the measurement of changes in pigments over time in a single leaf (Garriga et al, 2014)

Methods

Results

Discussion

Conclusion