Advertisement

Precision Agriculture

, Volume 21, Issue 1, pp 198–225 | Cite as

Estimation and mapping of nitrogen content in apple trees at leaf and canopy levels using hyperspectral imaging

  • Xujun YeEmail author
  • Shiori Abe
  • Shuhuai Zhang
Article
  • 246 Downloads

Abstract

Accurate and rapid diagnosis of nitrogen status in fruit trees on an individual tree basis is a prerequisite for precision orchard nutrient management. This study presents a rapid and non-destructive approach for estimation and mapping of nitrogen content in apple trees at both leaf and canopy levels. An ImSpector V10 system was used to collect hyperspectral images (400–1000 nm) for both apple leaves and canopies. Nitrogen content in apple leaves was measured by Vario EL cube. Raw reflectance and first derivative reflectance were used to relate to leaf nitrogen content. Partial least squares (PLS) regression and multiple linear regression (MLR) analyses were performed to estimate nitrogen content from reflectance. The results showed that both PLS and MLR models achieved reasonable predictive accuracy (PLS and MLR models based on raw reflectance: R2 = 0.7728 and 0.7843 (p < 0.001); PLS and MLR models based on first derivative reflectance: R2 = 0.7745 and 0.774 (p < 0.001)). However, the MLR model based on raw reflectance demonstrated its advantage over the PLS models as well as the MLR model based on first derivative reflectance, because it only used 4 key wavelengths (505, 560, 675 and 705 nm) while the other models were based on either the full wavelengths (132 wavelengths) or more narrowband wavelengths adjacent to the selected key wavelengths. Furthermore, nitrogen distribution maps at both leaf and canopy levels were generated based on the nitrogen contents estimated by the MLR model based on raw reflectance. This new approach may be potentially applied to precision apple orchard nutrient management.

Keywords

Apple tree Nitrogen Estimation Mapping Hyperspectral imaging Multiple linear regression Partial least squares 

Notes

Acknowledgements

This work was jointly supported by the Japan Society for the Promotion of Science (JSPS) under the Grants-in-Aid for Scientific Research (No. 16K07968) and the Strategy I Project of Hirosaki University. The authors would like to thank the editor and two anonymous reviewers for their helpful and constructive comments that greatly contributed to improving the quality of the paper.

Compliance with ethical standards

Conflict of interest

The authors declare that they have no conflict of interest.

References

  1. Abdi, H. (2003). Partial least squares (PLS) regression. In M. Lewis-Beck, A. Bryman, & T. Futing (Eds.), Encyclopedia of social sciences research methods (pp. 1–7). Thousand Oaks, California, USA: Sage Publishing.Google Scholar
  2. Alchanatis, V., & Cohen, Y. (2011). Spectral and spatial methods of hyperspectral image analysis for estimation of biophysical and biochemical properties of agricultural crops. In P. S. Thenkabail, P. J. G. Lyon, & A. Huete (Eds.), Hyperspectral remote sensing of vegetation. Boca Raton, USA: CRC Press, Taylor and Francis Group.Google Scholar
  3. APTINET. (2016). Aomori tops the apple production in Japan! Aomori, Japan: AOMORI Prefectural Government. In Aomori. Retrieved April 2019 from https://www.en-aomori.com/20161020_apple.html.
  4. Bajwa, S. G., Mishra, A. R., & Norman, R. J. (2010). Canopy reflectance response to plant nitrogen accumulation in rice. Precision Agriculture,11, 488–506.Google Scholar
  5. Boyer, J., & Liu, R. (2004). Apple phytochemicals and their health benefits. Nutrition Journal,3, 5.PubMedPubMedCentralGoogle Scholar
  6. Chen, P. (2015). A comparison of two approaches for estimating the wheat nitrogen nutrition index using remote sensing. Remote Sensing,7, 4527–4548.Google Scholar
  7. Cohen, Y., & Alchanatis, V. (2018). Spectral and spatial methods for hyperspectral and thermal image-analysis to estimate biophysical and biochemical properties of agricultural crops. In P. S. Thenkabail, G. J. Lyon, & A. Huete (Eds.), Hyperspectral remote sensing of vegetation: Biophysical and biochemical characterization and plant species studies (2nd ed., Vol. III). Boca Raton, USA: CRC Press, Taylor and Francis group.Google Scholar
  8. Cohen, Y., Alchanatis, V., Zusman, Y., Dar, Z., Bonfil, D. J., Karnieli, A., et al. (2010). Leaf nitrogen estimation in potato based on spectral data and on simulated bands of the VEN mu S satellite. Precision Agriculture,11(5), 520–537.Google Scholar
  9. El-Gazzar, A. A. M. (2000). Effect of fertilization with nitrogen, potassium and magnesium on Anna apples. Part 1. Effect of nitrogen fertilization. Annals of Agricultural Science,3, 1145–1152.Google Scholar
  10. Erel, R., Dag, A., Ben-Gal, A., Schwartz, A., & Yermiyahu, U. (2008). Flowering and fruit set of olive trees in response to nitrogen, phosphorus, and potassium. Journal of the American Society for Horticultural Science,133(5), 639–647.Google Scholar
  11. Evans, J. R. (1989). Photosynthesis and nitrogen relationships in leaves of C3 plants. Oecologia,78, 9–19.PubMedGoogle Scholar
  12. Fageria, N. K., & Baligar, V. C. (2005). Enhancing nitrogen use efficiency in crop plants. Advances in Agronomy,80, 97–198.Google Scholar
  13. Freedman, D. A. (2009). Statistical models: Theory and practice (p. 26). Cambridge, UK: Cambridge University Press.Google Scholar
  14. Gitelson, A. A., Viña, A., Ciganda, V., Rundquist, D. C., & Arkebauer, T. J. (2005). Remote estimation of canopy chlorophyll content in crops. Geophysical Research Letters,32, L084031–L084034.Google Scholar
  15. Gosh, S., Manna, S., & Mathew, B. (2004). Effect of nitrogen and potassium fertilization on custard apple grown under rain fed laterite soils. Environmental Ecology,22, 144–147.Google Scholar
  16. Hikosaka, K., & Terashima, I. (1995). A model of the acclimation of photosynthesis in the leaves of C3 plants to sun and shade with respect to nitrogen use. Plant, Cell and Environment,18, 605–618.Google Scholar
  17. Hirose, T., & Werger, M. J. (1987). Maximizing daily canopy photosynthesis with respect to the leaf nitrogen allocation pattern in the canopy. Oecologia,72(4), 520–526.PubMedGoogle Scholar
  18. Igarashi, M., Hatsuyama, Y., Harada, T., & Fukasawa-Akada, T. (2016). Biotechnology and apple breeding in Japan. Breed Science,66(1), 18–33.Google Scholar
  19. Ignatov, N. V., & Litvin, F. E. (1994). Photo induced formation of pheophytin/chlorophyll-containing complexes during the greening of plant leaves. Photosynthesis Research,42, 27–35.PubMedGoogle Scholar
  20. Jadczuk, E., Pietranek, A., & Dziuban, R. (2001). Irrigation and fertilization effects on the cropping and fruit quality of ‘Katja’ apple trees on four different rootstocks. Folia Horticulturae,13(2), 47–60.Google Scholar
  21. Kohavi, R. (1995). A study of cross-validation and bootstrap for accuracy estimation and model selection. Proceedings of the Fourteenth International Joint Conference on Artificial Intelligence,2(12), 1137–1143.Google Scholar
  22. Lee, W., Alchanatis, V., Yang, C., Hirafuji, M., Moshou, D., & Li, C. (2010). Sensing technologies for precision specialty crop production. Computers and Electronics in Agriculture,74(1), 18–19.Google Scholar
  23. Li, F., Miao, Y. X., Hennig, S. D., Gnyp, M. L., Chen, X. P., Jia, L. L., et al. (2010). Evaluating hyperspectral vegetation indices for estimating nitrogen concentration of winter wheat at different growth stages. Precision Agriculture,11(4), 335–357.Google Scholar
  24. Li, J., Ye, X., Wang, Q., Zhang, C., & Yong, H. (2014). Development of prediction models for determining N content in citrus leaves based on hyperspectral imaging technology. Spectroscopy and Spectral Analysis,34(1), 212–216.PubMedGoogle Scholar
  25. Li, C., Zhu, X., Wei, Y., Cao, S., Guo, X., Yu, X., et al. (2018). Estimating apple tree canopy chlorophyll content based on Sentinel-2A remote sensing imaging. Scientific Reports,8, 3756.PubMedPubMedCentralGoogle Scholar
  26. Marsh, K. B., Volz, R. K., & Reay, P. (1996). Fruit colour, leaf nitrogen level, and tree vigour in ‘Fuji’ apples. New Zealand Journal of Crop Horticultural Science,24, 393–399.Google Scholar
  27. Matlab Release. (2016). Expands capabilities and simplifies working with big data in MATLAB. Natick, MA, USA: The MathWorks Inc.Google Scholar
  28. Mevik, B. H., & Wehrens, R. (2007). The pls package: Principal component and partial least squares regress in R. Journal of Statistical Software,18(2), 1–24.Google Scholar
  29. Mishra, P., Asaari, M. S. M., Herrero-Langreo, A., Lohumi, S., Diezma, B., & Scheunders, P. (2017). Close range hyperspectral imaging of plants: A review. Biosystems Engineering,164, 49–67.Google Scholar
  30. Nachtigall, G. R., & Dechen, A. R. (2006). Seasonality of nutrients in leaves and fruits of apple trees. Scientia Agricola,63(5), 493–501.Google Scholar
  31. Neilsen, D., Hogue, E. J., Neilsen, G. H., & Parchomchuk, P. (1995). Using SPAD-502 values to assess the nitrogen status of apple trees. HortScience,30(3), 508–512.Google Scholar
  32. Neilsen, G. H., Neilsen, D., Forge, T., & Hannam, K. (2017). Advances in soil and nutrient management in apple cultivation. In K. Evans (Ed.), Achieving sustainable cultivation of apples. Sawston, Cambridge, UK: Burleigh Dodds Science Publishing.Google Scholar
  33. Nigon, T. J., Mulla, D. J., Rosen, C. J., Cohen, Y., Alchanatis, V., Knight, J., et al. (2015). Hyperspectral aerial imagery for detecting nitrogen stress in two potato cultivars. Computers and Electronics in Agriculture,112, 36–46.Google Scholar
  34. O’Rourke, D. (2003). World production, trade, consumption and economic outlook for apples. In D. C. Ferree & I. J. Warrington (Eds.), Apples: Botany, production and uses (pp. 15–29). Wallingford, Oxon, UK: CAB International.Google Scholar
  35. Palermo, G., Piraino, P., & Zucht, H. D. (2009). Performance of PLS regression coefficients in selecting variables for each response of a multivariate PLS for omics-type data. Advances and Applications in Bioinformatics and Chemistry,2, 57–70.PubMedPubMedCentralGoogle Scholar
  36. Pearson, K. (1895). Notes on regression and inheritance in the case of two parents. Proceedings of the Royal Society of London,58, 240–242.Google Scholar
  37. Perry, E. M., & Davenport, J. R. (2007). Spectral and spatial differences in response of vegetation indices to nitrogen treatments on apple. Computers and Electronics in Agriculture,59, 56–65.Google Scholar
  38. Porro, D., Dorigatti, C., Stefanini, M., & Ceschini, A. (2001). Use of SPAD meter in diagnosis of nutritional status in apple and grapvine. Acta Horticulturae,564, 243–252.Google Scholar
  39. Ramadan, Z., Hopke, P. K., Johnson, M. J., & Scow, K. M. (2004). Application of PLS and back-propagation neural networks for the estimation of soil properties. Chemometrics and intelligent laboratory systems,75, 23–30.Google Scholar
  40. Rapaport, T., Hochberg, U., Shoshany, M., Karnieli, A., & Rachmilevitch, S. (2015). Combining leaf physiology, hyperspectral imaging and partial least squares-regression (PLS-R) for grapevine water status assessment. ISPRS Journal of Photogrammetry and Remote Sensing,109, 88–97.Google Scholar
  41. Rhee, K. C. (2001). Determination of total nitrogen. In R. E. Wrolstad, T. E. Acree, H. An, E. A. Decker, M. H. Penner, D. S. Reid, S. J. Schwartz, C. F. Shoemaker, & P. Sporns (Eds.), Current protocols in food analytical chemistry. Hoboken, New Jersey, USA: Wiley.Google Scholar
  42. Roggatz, R., McDonalD, A. J. S., Stadenberg, I., & Schurr, U. (1999). Effects of nitrogen deprivation on cell division and expansion in leaves of Ricinus communis L. Plant, Cell and Environment,22(1), 81–89.Google Scholar
  43. Saberioon, M. M., Amin, M. S. M., & Gholizadeh, A. (2012). Estimation of nitrogen of rice in different growth stages using tetracam agriculture digital camera. In 11th International Conference on Precision Agriculture (11th ICPA). Retrieved April 2019 from https://www.ispag.org/abstract_papers/papers/abstract_1051.pdf.
  44. Sankaran, S., Mishra, A., Maja, J. M., & Ehsani, R. (2011). Visible-near infrared spectroscopy for detection of Huanglongbing in citrus orchards. Computers and Electronics in Agriculture,77(2), 127–134.Google Scholar
  45. Savitzky, A., & Golay, M. J. E. (1964). Smoothing and differentiation of data by simplified least squares procedures. Analytical Chemistry,36(8), 1627–1639.Google Scholar
  46. Schlemmer, M., Gitelson, A., Schepers, J., Ferguson, R., Peng, Y., Shanahan, J., et al. (2013). Remote estimation of nitrogen and chlorophyll contents in maize at leaf and canopy levels. International Journal of Applied Earth Observation and Geoinformation,25, 47–54.Google Scholar
  47. Shafri, H. Z., & Hamdan, N. (2009). Hyperspectral imagery for mapping disease infection in oil palm plantation using vegetation indices and red edge techniques. American Journal of Applied Sciences,6(6), 1031.Google Scholar
  48. Shuaibu, M., Lee, W. K., Schueller, J., Gader, P., Hong, Y. K., & Kim, S. (2018). Unsupervised hyperspectral band selection for apple Marssonina blotch detection. Computers and Electronics in Agriculture,148, 45–53.Google Scholar
  49. Soares, A. G., Trugo, L. C., Botrel, N., & da Silva Souza, L. F. (2005). Reduction of internal browning of pineapple fruit (Ananas Comusus L.) by Preharvest soil application of potassium. Postharvest Biology and Technology,35, 201–207.Google Scholar
  50. Stone, M., & Brooks, R. (1990). Continuum regression: Cross-validated sequentially constructed prediction embracing ordinary least squares, partial least squares, and principal components regression. Journal of the Royal Statistical Society: Series B (Statistical Methodology),52, 237–269.Google Scholar
  51. Stone, M. L., Raun, W. R., Johnson, G. V., Solie, J. B., Whitney, R. W., Sembiring, H., et al. (1997). Sensing nitrogen deficiencies in winter wheat and bermudagrass. Better Crops,81(4), 15–17.Google Scholar
  52. Tahir, I. I., Johansson, E., & Olsson, M. E. (2007). Improvement of quality and storability of apple cv. Aroma by adjustment of some pre-harvest conditions. Scientia Horticulturae,112, 164–171.Google Scholar
  53. Takebe, M. (2009). Recent development in the plant nutritional diagnosis by nondestructive methods. Japanese Society of Soil Science and Plant Nutrition,80(1), 63–65.Google Scholar
  54. Thorp, K. R., Wang, G., Bronson, K. F., Badaruddin, M., & Mon, J. (2017). Hyperspectral data mining to identify relevant canopy spectral features for estimating durum wheat growth, nitrogen status, and grain yield. Computers and Electronics in Agriculture,136, 1–12.Google Scholar
  55. Tremblay, N., Fallon, E., & Ziadi, N. (2011). Sensing of crop nitrogen status: Opportunities, tools, limitations, and supporting information requirements. HortTechnology,21, 274–281.Google Scholar
  56. Tromp, J., & Wertheim, S. J. (2005). Fruit growth and development. In J. Tromp, A. D. Webster, & S. J. Wertheim (Eds.), Fundamentals of temperate zone tree fruit production (pp. 240–266). Leiden, The Netherlands: Backhuys Publishers.Google Scholar
  57. van Maarschalkerweerd, M., & Husted, S. (2015). Recent developments in fast spectroscopy for plant mineral analysis. Frontiers in Plant Science,6, 169.PubMedPubMedCentralGoogle Scholar
  58. Webster, A. D. (2005). Shoot growth. In J. Tromp, A. D. Webster, & S. J. Wertheim (Eds.), Fundamentals of temperate zone tree fruit production (pp. 120–136). Leiden, The Netherlands: Backhuys Publishers.Google Scholar
  59. Wold, S., Johansson, E., & Cocchi, M. (1993). PLS—partial least squares projections to latent structures. In H. Kubinyi (Ed.), 3D-QSAR in drug design, theory, methods, and applications (pp. 523–550). Leiden, The Netherlands: ESCOM Science Publishers.Google Scholar
  60. Wold, S., Ruhe, A., Wold, H., & Dunn, W. J., III. (1984). The collinearity problem in linear-regression—the partial least-squares (PLS) approach to generalized inverses. SIAM Journal on Scientific and Statistical Computing,5(3), 735–743.Google Scholar
  61. Wu, D., & Sun, D.-W. (2013). Potential of time series-hyperspectral imaging (TS-HSI) for non-invasive determination of microbial spoilage of salmon flesh. Talanta,111, 39–46.PubMedGoogle Scholar
  62. Xiong, D., Chen, J., Yu, T., Gao, W., Ling, X., Li, Y., et al. (2015). SPAD-based leaf nitrogen estimation is impacted by environmental factors and crop leaf characteristic. Scientific Reports,5, 13389.PubMedPubMedCentralGoogle Scholar
  63. Ye, X., & Sakai, K. (2015). Application of hyperspectral imaging in agriculture. The Journal of the Institute of Image Information and Television Engineers,69(5), 464–469.Google Scholar
  64. Ye, X., Sakai, K., Sasao, A., & Asada, S. (2008). Potential of airborne hyperspectral imagery to estimate fruit yield in citrus. Chemometrics and intelligent laboratory systems,90(2), 132–144.Google Scholar
  65. Yoder, B. J., & Pettigrew-Crosby, R. E. (1995). Predicting nitrogen and chlorophyll content and concentrations from reflectance spectra (400–2500 nm) at leaf and canopy scales. Remote Sensing of Environment,53(3), 199–211.Google Scholar
  66. Yuan, L., Huang, Y., Loraamm, R. W., Nie, C., Wang, J., & Zhang, J. (2014). Spectral analysis of winter wheat leaves for detection and differentiation of diseases and insects. Field Crops Research,156, 199–207.Google Scholar
  67. Zhang, L., Zhou, Z., Zhang, G., Meng, Y., Chen, B., & Wang, Y. (2012). Monitoring the leaf water content and specific leaf weight of cotton (Gossypium hirsutum L.) in saline soil using leaf spectral reflectance. European Journal of Agronomy,41, 103–117.Google Scholar
  68. Zhu, X. C., Zhao, G. X., Wang, L., Dong, F., Lei, T., & Zhan, B. (2010). Hyperspectrum based prediction model for nitrogen content of apple flowers. Spectroscopy and Spectral Analysis,30(2), 416–420.PubMedGoogle Scholar

Copyright information

© Springer Science+Business Media, LLC, part of Springer Nature 2019

Authors and Affiliations

  1. 1.Faculty of Agriculture and Life ScienceHirosaki UniversityAomoriJapan
  2. 2.Graduate School of Agriculture and Life ScienceHirosaki UniversityAomoriJapan

Personalised recommendations