Estimation of Leaf Nitrogen Content of Winter Wheat Based on Akaike’s Information Criterion

  • Haojie Pei
  • Haikuan FengEmail author
  • Fuqin Yang
  • Zhenhai Li
  • Guijun Yang
  • Qinglin Niu
Conference paper
Part of the IFIP Advances in Information and Communication Technology book series (IFIPAICT, volume 546)


Nitrogen is one of the important indices for evaluation of crop growth and output quality. At present, there are a lot of researches on the estimation of crop nitrogen content, but most of the studies do not consider whether the model established by vegetation index and crop nitrogen content is the best. The purpose of this study was to estimate the nitrogen content of wheat leaves and to establish a method and the optimal model for monitoring nitrogen content in wheat leaves. Spectral reflectance of leaves and concurrent leaf nitrogen content parameters of samples were acquired in during 2013 and 2014 wheat growth season, in Beijing Academy of Agriculture and Forestry Sciences. 17 vegetation indices related to nitrogen content were chosen, and the relationship between related vegetation indices and leaf nitrogen content were built for screening vegetation indices with variable importance projection (VIP). Choosing first 10 different vegetation indices after ranking with VIP value as the independent variable for estimating nitrogen content of leaf in wheat. And the number of vegetation indices was gradually increased from top 4 to 10. The leaf nitrogen content estimation model with different vegetation indices can be built using the integrated model of variable importance projection (VIP) - partial least squares (PLS). At the same time, Akaike’s Information Criterion (AIC) value was calculated in different estimation model, and the AIC value of 7 different estimation model was compared. Then the optimal model with 5 vegetation indices was selected, which AIC value is the lowest. The optimal model was validated by leave one out cross-validation method. The result, (1) the comprehensive interpretation ability of the first 10 spectral indices on the nitrogen content of winter wheat leaves was PSSRc, GMI-2, SR705, RI-half, ZM, GMI-1, PSSRb, RI-3 dB, VOGc and CIred edge. (2) The optimal model with 5 vegetation indices was selected from 7 models. (3) The decision coefficient (R2) and root-mean-square error (RMSE) of the optimal model respectively were 0.73 and 0.33. The R2 and RMSE of wheat by validating were 0.73 and 0.33, respectively. The study showed: (1) The VIP-PLS model has higher ability to estimate the nitrogen content of leaf in wheat, which laying an important foundation for improving the precision of forecasting winter wheat leaf nitrogen content with remote sensing. (2) The AIC method can be used to select the optimal model, and the selected model has the higher predictive ability. And the optimal estimation model of wheat LNC can be obtained based on AIC.


Leaf nitrogen content Akaike’s Information Criterion Variable importance for projection Partial least squares Vegetation index 



This work was supported in part by the National Key Research and Development Programs (2016YFD0300603-5), National Natural Science Foundation of China (No.41601346).


  1. 1.
    Wang, J.H., Zhao, C.J., Huang, W.J., et al.: Quantitative Remote Sensing of Agriculture. Science Press, Beijing (2008)Google Scholar
  2. 2.
    Pinter Jr., P.J., Hatfield, J.L., Schepers, J.S., et al.: Remote sensing for crop management. Photogram. Eng. Remote Sens. 69(6), 647–664 (2003)CrossRefGoogle Scholar
  3. 3.
    Hansen, P.M., Schjoerring, J.K.: Reflectance measurement of canopy biomass and nitrogen status in wheat crops using normalized difference vegetation indices and partial least squares regression. Remote Sens. Environ. 86(4), 542–553 (2003)CrossRefGoogle Scholar
  4. 4.
    Feng, W., Yao, X., Zhu, Y., et al.: Monitoring leaf nitrogen status with hyperspectral reflectance in wheat. Eur. J. Agron. 28(3), 394–404 (2008)CrossRefGoogle Scholar
  5. 5.
    Clevers, J., Kooistra, L.: Using hyperspectral remote sensing data for retrieving total canopy chlorophyll and nitrogen content. In: 2011 3rd Workshop on Hyperspectral Image and Signal Processing: Evolution in Remote Sensing, WHISPERS, pp. 1–4. IEEE (2011)Google Scholar
  6. 6.
    Cui, R., Liu, Y., Fu, J.: Estimation of winter leaf nitrogen accumulation using machine learning algorithm and visible spectral. Spectrosc. Spectral Anal. 36(6), 1837–1842 (2016)Google Scholar
  7. 7.
    Zhang, X., Liu, L., Zhao, C., et al.: Estimating wheat nitrogen concentration with high spectral resolution image. J. Remote Sens. 7(3), 176–181 (2003)Google Scholar
  8. 8.
    Li, F., Chang, Q., Shen, J., et al.: Remote sensing estimation of winter wheat leaf nitrogen content based on GF-1 satellite data. Trans. Chin. Soc. Agric. Eng. 32(9), 157–164 (2016)Google Scholar
  9. 9.
    Fei, W., Zhu, Y., Yao, X., et al.: Monitoring nitrogen accumulation in wheat leaf with red edge characteristics parameters. Trans. Chin. Soc. Agric. Eng. 25(11), 194–201 (2009)Google Scholar
  10. 10.
    Wang, R., Song, X., Li, Z., et al.: Estimation of winter wheat nitrogen nutrition index using hyperspectral remote sensing. Trans. Chin. Soc. Agric. Eng. 30(19), 191–198 (2014)Google Scholar
  11. 11.
    Li, Z.H., Xu, X.G., Jin, X.L., et al.: Remote sensing prediction of winter wheat protein content based on nitrogen translocation and GRA-PLS method. Sci. Agric. Sin. 47(19), 3780–3790 (2014)Google Scholar
  12. 12.
    Jin, X.L., Xu, X.G., Wang, J.H., et al.: Hyperspectral estimation of leaf water content for winter wheat based on relational analysis (GRA). Spectrosc. Spectral Anal. 32(11), 3103–3106 (2012)Google Scholar
  13. 13.
    Gautam, R., Panigrahi, S., Franzen, D.: Neural network optimisation of remotely sensed maize leaf nitrogen with a genetic algorithm and linear programming using five performance parameters. Biosys. Eng. 95(3), 359–370 (2006)CrossRefGoogle Scholar
  14. 14.
    Blackburn, G.A.: Spectral indices for estimating photosynthetic pigment concentrations: a test using senescent tree leaves. Int. J. Remote Sens. 19(4), 657–675 (1998)MathSciNetCrossRefGoogle Scholar
  15. 15.
    Gitelson, A.A., Merzlyak, M.N.: Remote sensing of chlorophyll concentration in higher plant leaves. Adv. Space Res. 22(5), 689–692 (1998)CrossRefGoogle Scholar
  16. 16.
    Vogelmann, J.E., Rock, B.N., Moss, D.M.: Red edge spectral measurements from sugar maple leaves. Remote Sens. 14(8), 1563–1575 (1993)CrossRefGoogle Scholar
  17. 17.
    Zarco-Tejada, P.J., Miller, J.R., Noland, T.L., et al.: Scaling-up and model inversion methods with narrowband optical indices for chlorophyll content estimation in closed forest canopies with hyperspectral data. IEEE Trans. Geosci. Remote Sens. 39(7), 1491–1507 (2001)CrossRefGoogle Scholar
  18. 18.
    Gupta, R.K., Vijayan, D., Prasad, T.S.: Comparative analysis of red-edge hyperspectralindices. Adv. Space Res. 32(11), 2217–2222 (2003)CrossRefGoogle Scholar
  19. 19.
    Tian, Y.C., Yao, X., Yang, J., et al.: Assessing newly developed and published vegetation indices for estimating rice leaf nitrogen concentration with ground-and space-based hyperspectral reflectance. Field Crops Res. 120(2), 299–310 (2011)CrossRefGoogle Scholar
  20. 20.
    Rodriguez, D., Fitzgerald, G.J., Belford, R., et al.: Detection of nitrogen deficiency in wheat from spectral reflectance indices and basic crop eco-physiological concepts. Crop Pasture Sci. 57(7), 781–789 (2006)CrossRefGoogle Scholar
  21. 21.
    Penuelas, J., Baret, F., Filella, I.: Semi-empirical indices to assess carotenoids/chlorophyll a ratio from leaf spectral reflectance. Photosynthetica 31, 221–230 (1995)Google Scholar
  22. 22.
    Dash, J., Curran, P.J.: Evaluation of the MERIS terrestrial chlorophyll index (MTCI). Adv. Space Res. 39(1), 100–104 (2007)CrossRefGoogle Scholar
  23. 23.
    Eitel, J.U.H., Long, D.S., Gessler, P.E., et al.: Using in-situ measurements to evaluate the new RapidEye™ satellite series for prediction of wheat nitrogen status. Int. J. Remote Sens. 28(18), 4183–4190 (2007)CrossRefGoogle Scholar
  24. 24.
    Guyot, G., Baret, F., Major, D.J.: High spectral resolution: determination of spectral shifts between the red and the near infrared. Int. Arch. Photogram. Remote Sens. 11, 740–760 (1988)Google Scholar
  25. 25.
    Zhu, Y., Li, Y., Feng, W., et al.: Monitoring leaf nitrogen in wheat using canopy reflectance spectra. Can. J. Plant Sci. 86(4), 1037–1046 (2006)CrossRefGoogle Scholar
  26. 26.
    Zeng, T., Ju, C.Y., Cai, T.J., et al.: Selection of parameters for estimating canopy closure density using variable importance of projection criterion. J. Beijing For. Univ. 32(6), 37–41 (2010)Google Scholar
  27. 27.
    Yang, F.Q., Feng, H.K., Li, Z.H., et al.: Estimation of leaf area index of winter wheat based on Akaike’s information criterion. Trans. Chin. Soc. Agric. Mach. 46(11), 112–120 (2015)Google Scholar
  28. 28.
    Akaike, H.: Information theory and an extension of the maximum likelihood principle[J]. In: Petrov, B.N., Csaki, F. (eds.) 2nd International Symposium of Information Theory, pp. 267–281. Akademiai Kiado, Budapest (1973)Google Scholar

Copyright information

© IFIP International Federation for Information Processing 2019

Authors and Affiliations

  • Haojie Pei
    • 1
    • 2
    • 3
    • 4
  • Haikuan Feng
    • 1
    • 2
    • 3
    Email author
  • Fuqin Yang
    • 1
    • 5
  • Zhenhai Li
    • 1
    • 2
    • 3
  • Guijun Yang
    • 1
    • 2
    • 3
  • Qinglin Niu
    • 1
    • 2
    • 3
    • 4
  1. 1.Key Laboratory of Quantitative Remote Sensing in Agriculture of Ministry of Agriculture P. R. ChinaBeijing Research Center for Information Technology in AgricultureBeijingChina
  2. 2.National Engineering Research Center for Information Technology in AgricultureBeijingChina
  3. 3.Beijing Engineering Research Center for Agriculture Internet of ThingsBeijingChina
  4. 4.School of Surveying and Land Information EngineeringHenan Polytechnic UniversityJiaozuoChina
  5. 5.College of Civil EngineeringHenan Institute of EngineeringZhengzhouChina

Personalised recommendations