Estimating the nitrogen content in wheat leaves by near-infrared reflectance spectroscopy

doi:10.3724/SP.J.1258.2011.00844

Abstract

Abstract:

Aims Our objectives were to determine the feasibility of estimating nitrogen content in fresh and dry wheat leaves using near-infrared (NIR) spectroscopy and chemometrics and to establish the near-infrared model for estimating nitrogen content in wheat leaves in order to lay a foundation for wheat nitrogen management.

Methods We conducted three field experiments with different years, wheat varieties and nitrogen rates and determined time-course near-infrared absorbance spectroscopy and total nitrogen content from fresh and dry wheat leaves. The methods of partial least squares (PLS), back-propagation neural network (BPNN) and wavelet neural network (WNN) were used to establish the calibration models, and a dataset selected at random was used to evaluate the established models.

Important findings Near infrared calibration models based on PLS, BPNN and WNN could be used to estimate nitrogen content in wheat leaves with high precision and stable performance, especially WNN. The validation results showed that the root mean square errors of prediction (RMSEP) for the power model are 0.147, 0.101 and 0.094, respectively, while those for the fresh leaves model are 0.216, 0.175 and 0.169, respectively. The correlation coefficients (R²) for all models are >0.84. Therefore, near-infrared spectrometry can be an efficient method to estimate the nitrogen nutrition of crops.

Key words: leaf, near-infrared spectroscopy, neural network, partial least squares, total nitrogen content, wheat

YAO Xia, TANG Shou-Peng, CAO Wei-Xing, TIAN Yong-Chao, ZHU Yan. Estimating the nitrogen content in wheat leaves by near-infrared reflectance spectroscopy[J]. Chin J Plant Ecol, 2011, 35(8): 844-852.

Add to citation manager EndNote|Ris|BibTeX

URL: https://www.plant-ecology.com/EN/10.3724/SP.J.1258.2011.00844

https://www.plant-ecology.com/EN/Y2011/V35/I8/844

Figures/Tables 6

References 26

[1]	Blakeney AB, Batten GD, Welsh LA (1996). Leaf nitrogen determination using a portable near-infrared spectrometer. In: Davies AMC, Williams P eds. Near Infrared Spectroscopy: the Future Waves. The Proceedings of the 7th International Conference on Near Infrared Spectroscopy. NIR Publications, Chichester,149-152.
[2]	Christy CD (2008). Real-time measurement of soil attributes using on-the-go near infrared reflectance spectroscopy. Computers and Electronics in Agriculture, 61,10-19.
[3]	Cozzolino D, Fassio A, Fernández E, Restaino E,La Manna A (2006). Measurement of chemical composition in wet whole maize silage by visible and near infrared reﬂectance spectroscopy. Animal Feed Science and Technology, 129,329-336.
[4]	Cozzolino D, Morón A (2006). Potential of near-infrared reflectance spectroscopy and chemometrics to predict soil organic carbon fractions. Soil and Tillage Research, 85,78-85.
[5]	Curran PJ, Dungan JL, Peterson DL (2001). Estimating the foliar biochemical concentration of leaves with reflectance spectrometry: testing the Kokaly and Clark methodologies. Remote Sensing of Environment, 76,349-359.
[6]	Dou Y, Mi H, Zhao LZ, Ren YQ, Ren YL (2006). Determination of compound aminopyrine phenacetin tablets by using artiﬁcial neural networks combined with principal components analysis. Analytical Biochemistry, 351,174-180. URL PMID
[7]	Feng W (冯伟), Yao X (姚霞), Zhu Y (朱艳), Tian YC (田永超), Cao WX (曹卫星) (2008). Monitoring leaf nitrogen concentration by hyperspectral remote sensing in wheat. Journal of Triticeae Crops (麦类作物学报), 25,851-860. (in Chinese with English abstract)
[8]	Fernandez JE, Badiali M, Guidetti A, Scot V (2007). Multiple scattering corrections for density proﬁle unfolding from Compton scattering signals in reﬂection geometry. Nuclear Instruments and Methods in Physics Research Section A (Accelerators, Spectrometers, Detectors and Associated Equipment), 580,77-80.
[9]	Gislum R, Micklander E, Nielsen JP (2004). Quantification of nitrogen concentration in perennial ryegrass and red fescue using near-infrared reflectance spectroscopy (NIRS) and chemometrics. Field Crops Research, 88,269-277.
[10]	Halgerson JL, Sheaffer CC, Martin NP, Peterson PR, Weston SJ (2004). Near-infrared reflectance spectroscopy prediction of leaf and mineral concentrations in alfalfa. Agronomy Journal, 96,344-351.
[11]	Kokaly RF, Clark RN (1999). Spectroscopic determination of leaf biochemistry using band-depth analysis of absorption features and stepwise multiple linear regression. Remote Sensing of Environment, 67,267-287.
[12]	Li DY (李冬云), Li CY (李彩云) (2007). Optimization method of near infrared spectroscopy signal. Computers and Applied Chemistry (计算机与应用化学), 24,1418-1420. (in Chinese with English abstract)
[13]	Liu L (刘莉), Huang L (黄岚), Yan YL (严衍禄), Wang ZY (王忠义) (2008). Progress in the study of impact of scattering on stability of quantitative analysis model using near infrared spectroscopy technology and correction methods. Spectroscopy and Spectral Analysis (光谱学与光谱分析), 28,2290-2295. (in Chinese with English abstract)
[14]	Luo JW, Ying K, Bai J (2005). Savitzky-Golay smoothing and differentiation ﬁlter for even number data. Signal Processing, 85,1429-1434.
[15]	Morón A, García A, Sawchik J, Cozzolino D (2007). Preliminary study on the use of near-infrared reflectance spectroscopy to assess nitrogen content of undried wheat plants. Journal of the Science of Food and Agriculture, 87,147-152.
[16]	Moros J, Llorca I, Cervera ML, Pastor A, Garrigues S,de la Guardia M (2008). Chemometric determination of arsenic and lead in untreated powdered red paprika by diffuse reﬂectance near-infrared spectroscopy. Analytica Chimica Acta, 613,196-206. URL PMID
[17]	Mroczyk WB, Michalski KM (1995). Quantitative and qualitative analyses in near infrared analysis of basic compounds in sugar beet leaf. Computers & Chemistry, 19,299-301.
[18]	Norris KH, Williams PC (1984). Optimization of mathematical treatments of raw near-infrared signal in the measurement of protein in hard red spring wheat. I. Influence of particle size. Cereal Chemistry, 61,158-165.
[19]	Riley MR, Cánaves LC (2002). FT-NIR spectroscopic analysis of nitrogen in cotton leaves. Applied Spectroscopy, 56,1484-1489.
[20]	Smith BM, Gemperline PJ (2000). Wavelength selection and optimization of pattern recognition methods using the genetic algorithm. Analytica Chimica Acta, 423,167-177.
[21]	Subasi A, Alkan A, Koklukaya E, Kiymik MK (2005). Wavelet neural network classification of EEG signals by using AR model with MLE preprocessing. Neural Networks, 18,985-997. DOI URL PMID
[22]	Wen X (闻新), Zhou L (周露), Wang DL (王丹力), Xiong XY (熊晓英) (2001). MATLAB Design for Neural Networks Application (MATLAB神经网络应用设计). Science Press, Beijing.225-232. (in Chinese)
[23]	Yan YL (严衍禄) (2005). Theoretical Principle of Near Infrared Spectroscopy and Its Application (近红外光谱分析基础与应用). China Light Industry Press, Beijing.1-189. (in Chinese)
[24]	Zhang LD (张录达), Shen XN (沈晓南), Zhao LL (赵龙莲), Li JH (李军会), Zhang JP (张建平), Xie WY (谢雯燕), Shu RX (束茹欣) (2000). Application of principal component all possible regression in quantitative analysis of flue-cured tobacco and wheat using near-infrared spectroscopy. Chinese Journal of Analytical Chemistry (分析化学), 28,723-726.(in Chinese with English abstract)
[25]	Zhang Q, Benveniste A (1992). Wavelet networks. IEEE Transactions on Neural Networks, 3,889-898. DOI URL PMID
[26]	Zhang YS (张玉森), Yao X (姚霞), Tian YC (田永超), Cao WX (曹卫星), Zhu Y (朱艳) (2010). Estimating leaf nitrogen content with near infrared reflectance spectroscopy in rice. Chinese Journal of Plant Ecology (植物生态学报), 34,704-712. (in Chinese with English abstract)

统计参数 Statistical parameter	样品数 Number of samples	最小值 Minimum value (%)	最大值 Maximum value (%)	平均值 Mean value (%)	标准偏差 Standard deviation (%)	变异系数 Coefficient of variation (%)
校正集 Calibration set	136	0.57	4.42	2.50	1.01	40.40
检验集 Testing set	39	0.60	4.26	2.42	0.95	39.26

统计参数 Statistical parameter	样品数 Number of samples	最小值 Minimum value (%)	最大值 Maximum value (%)	平均值 Mean value (%)	标准偏差 Standard deviation (%)	变异系数 Coefficient of variation (%)
校正集 Calibration set	136	0.57	4.42	2.50	1.01	40.40
检验集 Testing set	39	0.60	4.26	2.42	0.95	39.26

回归类型 Regression type	样品 Sample	预处理方式 Preprocessing method	校正均方根误差 RMSEC(%)	R²
偏最小二乘法 PLS	鲜叶 Fresh leaf	MSC+SG	0.252	0.805
		MSC+SG+1D	0.243	0.824
		MSC+SG+2D	0.231	0.832
		MSC+N+1D	0.276	0.786
		MSC+N+2D	0.269	0.791
	粉末状干叶 Dry leaf powder	MSC+SG	0.247	0.829
		MSC+SG+1D	0.275	0.811
		MSC+SG+2D	0.264	0.821
		MSC+N+1D	0.153	0.904
		MSC+N+2D	0.161	0.900
反向传播神经网络 BPNN	鲜叶 Fresh leaf	MSC+SG	0.195	0.852
		MSC+SG+1D	0.186	0.873
		MSC+SG+2D	0.174	0.881
		MSC+N+1D	0.206	0.844
		MSC+N+2D	0.198	0.856
	粉末状干叶 Dry leaf powder	MSC+SG	0.111	0.956
		MSC+SG+1D	0.121	0.950
		MSC+SG+2D	0.118	0.951
		MSC+N+1D	0.108	0.962
		MSC+N+2D	0.129	0.946
小波神经网络 WNN	鲜叶 Fresh leaf	MSC+SG	0.199	0.872
		MSC+SG+1D	0.185	0.884
		MSC+SG+2D	0.173	0.899
		MSC+N+1D	0.201	0.847
		MSC+N+2D	0.196	0.875
	粉末状干叶 Dry leaf powder	MSC+SG	0.105	0.958
		MSC+SG+1D	0.113	0.954
		MSC+SG+2D	0.102	0.967
		MSC+N+1D	0.091	0.983
		MSC+N+2D	0.118	0.961

回归类型 Regression type	样品 Sample	预处理方式 Preprocessing method	校正均方根误差 RMSEC(%)	R²
偏最小二乘法 PLS	鲜叶 Fresh leaf	MSC+SG	0.252	0.805
		MSC+SG+1D	0.243	0.824
		MSC+SG+2D	0.231	0.832
		MSC+N+1D	0.276	0.786
		MSC+N+2D	0.269	0.791
	粉末状干叶 Dry leaf powder	MSC+SG	0.247	0.829
		MSC+SG+1D	0.275	0.811
		MSC+SG+2D	0.264	0.821
		MSC+N+1D	0.153	0.904
		MSC+N+2D	0.161	0.900
反向传播神经网络 BPNN	鲜叶 Fresh leaf	MSC+SG	0.195	0.852
		MSC+SG+1D	0.186	0.873
		MSC+SG+2D	0.174	0.881
		MSC+N+1D	0.206	0.844
		MSC+N+2D	0.198	0.856
	粉末状干叶 Dry leaf powder	MSC+SG	0.111	0.956
		MSC+SG+1D	0.121	0.950
		MSC+SG+2D	0.118	0.951
		MSC+N+1D	0.108	0.962
		MSC+N+2D	0.129	0.946
小波神经网络 WNN	鲜叶 Fresh leaf	MSC+SG	0.199	0.872
		MSC+SG+1D	0.185	0.884
		MSC+SG+2D	0.173	0.899
		MSC+N+1D	0.201	0.847
		MSC+N+2D	0.196	0.875
	粉末状干叶 Dry leaf powder	MSC+SG	0.105	0.958
		MSC+SG+1D	0.113	0.954
		MSC+SG+2D	0.102	0.967
		MSC+N+1D	0.091	0.983
		MSC+N+2D	0.118	0.961