Estimation of nutrient contents in wolfberry (Lycium barbarum L.) based on hyperspectral analysis

Jin-Long ZHAO; Xue-Yi ZHANG; Qi ZHANG; Xue-Jun NAN; Yun-Xia WANG; Yang LI

doi:10.15835/nbha50312945

Authors

Jin-Long ZHAO Key Laboratory for Meteorological Disaster Monitoring and Early Warning and Risk Management of Characteristic Agriculture in Arid Regions, CMA, Yinchuan 750002; Ningxia Key Lab of Meteorological Disaster Prevention and Reduction, Ningxia Institute of Meteorological Sciences, Yinchuan 750002 (CN) https://orcid.org/0000-0003-1701-6626
Xue-Yi ZHANG Key Laboratory for Meteorological Disaster Monitoring and Early Warning and Risk Management of Characteristic Agriculture in Arid Regions, CMA, Yinchuan 750002; Ningxia Key Lab of Meteorological Disaster Prevention and Reduction, Ningxia Institute of Meteorological Sciences, Yinchuan 750002 (CN)
Qi ZHANG Key Laboratory for Meteorological Disaster Monitoring and Early Warning and Risk Management of Characteristic Agriculture in Arid Regions, CMA, Yinchuan 750002; Ningxia Key Lab of Meteorological Disaster Prevention and Reduction, Ningxia Institute of Meteorological Sciences, Yinchuan 750002 (CN)
Xue-Jun NAN Key Laboratory for Meteorological Disaster Monitoring and Early Warning and Risk Management of Characteristic Agriculture in Arid Regions, CMA, Yinchuan 750002; Ningxia Key Lab of Meteorological Disaster Prevention and Reduction, Ningxia Institute of Meteorological Sciences, Yinchuan 750002 (CN)
Yun-Xia WANG Key Laboratory for Meteorological Disaster Monitoring and Early Warning and Risk Management of Characteristic Agriculture in Arid Regions, CMA, Yinchuan 750002; Ningxia Key Lab of Meteorological Disaster Prevention and Reduction, Ningxia Institute of Meteorological Sciences, Yinchuan 750002 (CN)
Yang LI Key Laboratory for Meteorological Disaster Monitoring and Early Warning and Risk Management of Characteristic Agriculture in Arid Regions, CMA, Yinchuan 750002; Ningxia Key Lab of Meteorological Disaster Prevention and Reduction, Ningxia Institute of Meteorological Sciences, Yinchuan 750002 (CN)

DOI:

https://doi.org/10.15835/nbha50312945

Keywords:

hyperspectral, nutrient content, PLSR, remote sensing, wolfberry

Abstract

Rapid and accurate determination of the nutrient contents in wolfberry (Lycium barbarum L.) is of great significance for identifying the quality and origin of the fruit. Compared to traditional chemical analysis methods, hyperspectral remote sensing has the advantages of high speed and low cost. In this study, the dried fruits of wolfberry (cultivar ‘Ningqi No. 7’) taken from the Huinong, Yinchuan, Zhongning, and Tongxin regions of Ningxia, China, in 2020 were selected as samples. Two methods, the variable importance measure (VIM) under random forest and the successive projection algorithm (SPA), were applied to select the hyperspectral characteristic variables. The test set coefficient of determination (R²p), root mean square error of prediction (RMSEP), and relative percent deviation (RPD) for different pre-treatments and characteristic variable selection methods were compared. Finally, the optimal estimation models of partial least squares regression (PLSR) for the contents of eight nutrients in wolfberry were established. The results were as follows: (1) The variation trends of the original hyperspectral reflectance curves of wolfberries from different yield areas and harvest dates were similar, and the spectral characteristic absorption bands were significantly enhanced after first-order differential transformation. (2) After extracting the characteristic bands using SPA, the RPD values were all above 2.0, and the estimation performance was significantly better than that of the full bands. (3) The optimal estimation model for total sugar (TS), crude protein (CP), and Ca was found to be SG-MSC-SPA-PLSR; the optimal estimation model for Lycium barbarum polysaccharide (LBP), Mn, and Zn was found to be SG-2^ndD-SPA-PLSR; and the optimal estimation model for Cu and Fe was found to be SG-1^stD-SPA-PLSR. The results have important reference value for the quality evaluation and origin traceability of wolfberry.

References

Aernouts B, Polshin E, Lammertyn J, Saeys W (2011). Visible and near-infrared spectroscopic analysis of raw milk for cow health monitoring: Reflectance or transmittance? Journal of Dairy Science 94(11):5315-5329. https://doi.org/10.3168/jds.2011-4354

Araújo MCU, Saldanha TCB, Galvão RKH, Yoneyama T, Chame HC, Visani V (2001). The successive projections algorithm for variable selection in spectroscopic multicomponent analysis. Chemometrics and Intelligent Laboratory Systems 57(2):65-73. https://doi.org/10.1016/S0169-7439(01)00119-8

Bai SH, Tahmasbian I, Zhou J, Nevenimo T, Hannet G, Walton D, Randall B, Gama T, Wallace HM (2018). A non-destructive determination of peroxide values, total nitrogen and mineral nutrients in an edible tree nut using hyperspectral imaging. Computers and Electronics in Agriculture 151:492-500. https://doi.org/10.1016/j.compag.2018.06.029

Bellon-Maurel V, Fernandez-Ahumada E, Palagos B, Roger JM, McBratney A (2010). Critical review of chemometric indicators commonly used for assessing the quality of the prediction of soil attributes by NIR spectroscopy. Trends in Analytical Chemistry 29(9):1073-1081. https://doi.org/10.1016/j.trac.2010.05.006

Caporaso N, Whitworth MB, Fisk ID (2022). Prediction of coffee aroma from single roasted coffee beans by hyperspectral imaging. Food Chemistry 371:131159. https://doi.org/10.1016/j.foodchem.2021.131159

Chen JJ, Liu XL, Zhu LY, Wang Y (2013). Nuclear genome size estimation and karyotype analysis of Lycium species (Solanaceae). Scientia Horticulturae 151:46-50. https://doi.org/10.1016/j.scienta.2012.12.004

Chinese Pharmacopoeia Commission of the People’s Republic of China (2020). Pharmacopoeia of the People’s Republic of China (Part I). Beijing: China Medical Science Press, pp 260-261.

Curran PJ (1989). Remote sensing of foliar chemistry. Remote Sensing of Environment 30(3):271-278. https://doi.org/10.1016/0034-4257(89)90069-2

Duranovich FN, Yule IJ, Lopez-Villalobos N, Shadbolt NM, Draganova I, Morris ST (2020). Using proximal hyperspectral sensing to predict herbage nutritive value for dairy farming. Agronomy 10(11):1826. https://doi.org/10.3390/agronomy10111826

El-Sebaii AA, Shalaby SM (2013). Experimental investigation of an indirect-mode forced convection solar dryer for drying thymus and mint. Energy Conversion and Management 74:109-116. https://doi.org/10.1016/j.enconman.2013.05.006

Fatchurrahman D, Nosrati M, Amodio ML, Chaudhry MMA, de Chiara MLV, Mastrandrea L, Colelli G (2021). Comparison performance of visible-NIR and near-infrared hyperspectral imaging for prediction of nutritional quality of Goji berry (Lycium barbarum L.). Foods 10(7):1676. https://doi.org/10.3390/foods10071676

Galvão RKH, Pimentel MF, Araujo MCU, Yoneyama T, Visani V (2001). Aspects of the successive projection’s algorithm for variable selection in multivariate calibration applied to plasma emission spectrometry. Analytica Chimica Acta 443(1):107-115. https://doi.org/10.1016/S0003-2670(01)01182-5

Grieco M, Schmidt M, Warnemünde S, Backhaus A, Klück HC, Garibay A, … Pillen K (2022). Dynamics and genetic regulation of leaf nutrient concentration in barley based on hyperspectral imaging and machine learning. Plant Science 315:111123. https://doi.org/10.1016/j.plantsci.2021.111123

Han H, Guo XL, Yu H (2016). Variable selection using mean decrease accuracy and mean decrease Gini based on random forest. In: Proceedings of the 7th IEEE International Conference on Software Engineering and Service Science (ICESS). IEEE, Beijing, China pp 219-224. https://doi.org/10.1109/ICSESS.2016.7883053

He J, Chen LD, Chu BQ, Zhang C (2018). Determination of total polysaccharides and total flavonoids in chrysanthemum morifolium using near-infrared hyperspectral imaging and multivariate analysis. Molecules 23(9):2395. https://doi.org/10.3390/molecules23092395

Huang JH, Zhou RR, He D, Chen L, Yang YY, Xie HL, … Huang LQ (2020). Rapid identification of Lilium species and polysaccharide contents based on near infrared spectroscopy and weighted partial least square method. International Journal of Biological Macromolecules 154:182-187. https://doi.org/10.1016/j.ijbiomac.2020.03.109

Hu NY, Li W, Du CH, Zhang Z, Gao YM, Sun ZC, … Wang ZM (2021). Predicting micronutrients of wheat using hyperspectral imaging. Food Chemistry 343:128473. https://doi.org/10.1016/j.foodchem.2020.128473

Kämper W, Trueman SJ, Tahmasbian I, Bai SH (2020). Rapid determination of nutrient concentrations in Hass Avocado fruit by VIS/NIR hyperspectral imaging of flesh or skin. Remote Sensing 12(20):3409. https://doi.org/10.3390/rs12203409

Khodabux K, L'Omelette MSS, Jhaumeer-Laulloo S, Ramasami P, Rondeau P (2007). Chemical and near-infrared determination of moisture, fat and protein in tuna fishes. Food Chemistry 102(3):669-675. https://doi.org/10.1016/j.foodchem.2006.05.057

Konieczynski P, Arceusz A, Wesolowski M (2016). Essential elements and their relations to phenolic compounds in infusions of medicinal plants acquired from different European regions. Biological Trace Element Research 170(2):466-475. https://doi.org/10.1007/s12011-015-0481-6

Lan WJ, Jaillais B, Renard CMGC, Leca A, Chen SC, Le Bourvellec C, Bureau S (2021). A method using near infrared hyperspectral imaging to highlight the internal quality of apple fruit slices. Postharvest Biology and Technology 175:111497. https://doi.org/10.1016/j.postharvbio.2021.111497

Li Q, Yu XZ, Gao JM (2017). A novel method to determine total sugar of Goji berry using FT-NIR spectroscopy with effective wavelength selection. International Journal of Food Properties 20:S478-S488. https://doi.org/10.1080/10942912.2017.1299759

Liu MB, Li XL, Liu Y, Huang JF, Tang YL (2014). Detection of crude protein, crude starch, and amylose for rice by hyperspectral reflectance. Spectroscopy Letters 47(2):101-106. https://doi.org/10.1080/00387010.2013.779283

Manley M (2014). Near-infrared spectroscopy and hyperspectral imaging: non-destructive analysis of biological materials. Chemical Society Reviews 43(24):8200-8214. https://doi.org/10.1039/c4cs00062e

Mao F, Xiao BX, Jiang Z, Zhao JW, Huang X, Guo JM (2011). Anticancer effect of Lycium barbarum polysaccharides on colon cancer cells involves G0/G1 phase arrest. Medical Oncology 28(1):121-126. https://doi.org/10.1007/s12032-009-9415-5

Mu QS, Kang ZL, Guo YJ, Chen L, Wang SY, Zhao YC (2021). Hyperspectral image classification of wolfberry with different geographical origins based on three-dimensional convolutional neural network. International Journal of Food Properties 24(1):1705-1721. https://doi.org/10.1080/10942912.2021.1987457

Osco LP, Marques Ramos AP, Faita Pinheiro MM, Saito Moriya ÉA, Imai NN, Estrabis N, … Creste JE (2020). A machine learning framework to predict nutrient content in Valencia-Orange leaf hyperspectral measurements. Remote Sensing 12(6):906. https://doi.org/10.3390/rs12060906

Ouyang Q, Wang L, Park B, Kang R, Chen QS (2021). Simultaneous quantification of chemical constituents in matcha with visible-near infrared hyperspectral imaging technology. Food Chemistry 350:129141. https://doi.org/10.1016/j.foodchem.2021.129141

Potterat O (2010). Goji (Lycium barbarum and L. chinense): phytochemistry, pharmacology and safety in the perspective of traditional uses and recent popularity. Planta Medica 76(1):7-19. https://doi.org/10.1055/s-0029-1186218

Pu RL, Gong P (2003). Hyperspectral Remote Sensing and Its Applications. Beijing: Higher Education Press, pp 82-83.

Rossel RAV, McGlynn RN, McBratney AB (2006). Determing the composition of mineral-organic mixes using UV-vis-NIR diffuse reflectance spectroscopy. Geoderma 137(1-2):70-82. https://doi.org/10.1016/j.geoderma.2006.07.004

Ruano-Ramos A, Garcı́a-Ciudad A, Garcı́a-Criado B (1999). Near infrared spectroscopy prediction of mineral content in botanical fractions from semi-arid grasslands. Animal Feed Science and Technology 77(3-4):331-343. https://doi.org/10.1016/S0377-8401(98)00245-4

Shenkin A (2004). The role of minerals and trace elements in relation to long-term health and chronic disease. Nestlé Nutrition Workshop Series Clinical and Performance Programme 9:169-185. https://doi.org/10.1159/000080662

Shorten PR, Leath SR, Schmidt J, Ghamkhar K (2019). Predicting the quality of ryegrass using hyperspectral imaging. Plant Methods 15:63. https://doi.org/10.1186/s13007-019-0448-2

Smith C, Karunaratne S, Badenhorst P, Cogan N, Spangenberg G, Smith K (2020). Machine learning algorithms to predict forage nutritive value of in situ perennial ryegrass plants using hyperspectral canopy reflectance data. Remote Sensing 12(6):928. https://doi.org/10.3390/rs12060928

Soares FLF, Marcelo MCA, Porte LMF, Pontes OFS, Kaiser S (2019). Inline simultaneous quantitation of tobacco chemical composition by infrared hyperspectral image associated with chemometrics. Microchemical Journal 151:104225. https://doi.org/10.1016/j.microc.2019.104225

Tian YL, Xia T, Qiang X, Zhao YX, Li SP, Wang YM, Zheng Y, Yu JW, Wang JX, Wang M (2022). Nutrition, bioactive components, and hepatoprotective activity of fruit vinegar produced from Ningxia wolfberry. Molecules 27(14):4422. https://doi.org/10.3390/molecules27144422

Wang YG, Gao Y, Yu XZ, Wang YY, Deng S, Gao JM (2016). Rapid determination of Lycium barbarum polysaccharide with effective wavelength selection using near-infrared diffuse reflectance spectroscopy. Food Analytical Methods 9:131-138. https://doi.org/10.1007/s12161-015-0178-7

Wang YM, Guo JP, Liu J, Yu F, Tian YM, Wu YJ, Liu LE (2021). Comparison and principal component analysis of main mineral elements in Lycium ruthenicum Murray from different habitats. Science and Technology of Food Industry 42(11):233-239 (in Chinese with English abstract). https://doi.org/10.13386/j.issn1002-0306.2020070308

Wold H (1966). Estimation of principal components and related models by iterative least squares. Multivariate Analysis 1:391-420.

Ye XJ, Abe S, Zhang SH (2020). Estimation and mapping of nitrogen content in apple trees at leaf and canopy levels using hyperspectral imaging. Precision Agriculture 21(1):198-225. https://doi.org/10.1007/s11119-019-09661-x

Yu HC, Wang RB, Yin Y, Liu YH (2017). Detection of polysaccharides and total sugar in Chinese wolfberry based on hyperspectral imaging in different wavebands. Food Science 38(8):191-197 (in Chinese with English abstract). https://doi.org/10.7506/spkx1002-6630-201708030

Yu L, Hong YS, Geng L, Zhou Y, Zhu Q, Cao JJ, Nie Y (2015). Hyperspectral estimation of soil organic matter content based on partial least squares regression. Transactions of the Chinese Society of Agricultural Engineering 31(14):103-109 (in Chinese with English abstract). https://doi.org/10.11975/j.issn.1002-6819.2015.14.015

Zhang CH, Yun YH, Fan W, Liang YZ, Yu Y, Tang WX (2015). Rapid analysis of polysaccharides contents in Glycyrrhiza by near infrared spectroscopy and chemometrics. International Journal of Biological Macromolecules 79:983-987. https://doi.org/10.1016/j.ijbiomac.2015.06.025

Zhang C, Wu WY, Zhou L, Cheng H, Ye XQ, He Y (2020). Developing deep learning based regression approaches for determination of chemical compositions in dry black goji berries (Lycium ruthenicum Murr.) using near-infrared hyperspectral imaging. Food Chemistry 319:126536. https://doi.org/10.1016/j.foodchem.2020.126536

Zou S, Zhang X, Yao WB, Niu YG, Gao XD (2010). Structure characterization and hypoglycemic activity of a polysaccharide isolated from the fruit of Lycium barbarum L. Carbohydrate Polymers 80(4):1161-1167. https://doi.org/10.1016/j.carbpol.2010.01.038