Research on Hyperspectral Imaging Detection Method of Nitrogen in Facility-Grown Lettuce

Authors

  • Yixue Zhang Basic Engineering Training Center, Jiangsu University, Zhenjiang, Jiangsu, China Author
  • Jingbo Zhi The University of Sydney, Sydney, NSW, Australia Author
  • Jialiang Zheng School of Agricultural Engineering, Jiangsu University, Zhenjiang, Jiangsu, China Author
  • Zhaowei Li School of Agricultural Engineering, Jiangsu University, Zhenjiang, Jiangsu, China Author
  • Tiezhu Li School of Agricultural Engineering, Jiangsu University, Zhenjiang, Jiangsu, China Author

DOI:

https://doi.org/10.70088/yzkchm20

Keywords:

Protected lettuce, Crop nutrition, Hyperspectral imaging, Feature extraction, Rapid detection

Abstract

Rapid non-destructive detection of crop nutrition serves as a crucial basis for water-fertilizer management and environmental regulation. This paper proposes a rapid nitrogen detection method for lettuce based on hyperspectral imaging technology. Hyperspectral image data of lettuce samples were acquired, processed using the SG smoothing algorithm, and analyzed with the RF algorithm to extract nitrogen-specific wavelengths. Finally, a KELM model under the RBF-Kernel function was established to predict lettuce nitrogen content. Results demonstrate that the KELM prediction model based on RF feature extraction achieves excellent performance, with an R² value exceeding 0.95 and RMSE below 0.27. This method provides scientific support for water and fertilizer irrigation decisions based on crop nitrogen requirements.

References

T. Wu, H. Zhang, Y. Xiao, Z. Tang, F. Yang, H. Qi, and C. Zhang, "Quantification of multiple elements in Anji white tea using hyperspectral imaging combined with machine learning regression," Journal of Food Composition and Analysis, vol. 142, p. 107520, 2025. doi: 10.1016/j.jfca.2025.107520

J. Hao, Y. Zhang, Y. Zhang, and L. Wu, "Prediction of antioxidant enzyme activity in tomato leaves based on microhyperspectral imaging technique," Optics & Laser Technology, vol. 179, p. 111292, 2024. doi: 10.1016/j.optlastec.2024.111292

M. Mahmoodi-Eshkaftaki, M. Mahbod, and H. R. Ghenaatian, "Non-destructive estimation of biomass characteristics: Combining hyperspectral imaging data with neural networks," Renewable Energy, vol. 224, p. 120137, 2024. doi: 10.1016/j.renene.2024.120137

G. A. O. Jingxia, P. E. I. Hongxia, Z. H. A. N. G. Qingyun, X. I. Weina, and X. I. E. Hua, "The effect of water and fertilizer coupling on the growth development and yield of day lily," Journal of Irrigation & Drainage, 2024.

H. Y. Gao, H. P. Mao, and X. D. Zhang, "Measurement of nitrogen content in lettuce canopy using spectroscopy combined with BiPLS-GA-SPA and elm," Guang pu xue yu Guang pu fen xi= Guang pu, vol. 36, no. 2, pp. 491-495, 2016.

I. Orrillo, J. P. Cruz-Tirado, A. Cardenas, M. Oruna, A. Carnero, D. F. Barbin, and R. Siche, "Hyperspectral imaging as a powerful tool for identification of papaya seeds in black pepper," Food Control, vol. 101, pp. 45-52, 2019.

H. Luo, X. Chai, and C. Chen, "Based on multi-scale hyperspectral near ground remote to sensing the quality of Southern Xinjiang jujube," In Fifth Symposium on Novel Optoelectronic Detection Technology and Application, March, 2019, pp. 612-618.

H. Feng, Y. Chen, J. Song, B. Lu, C. Shu, J. Qiao, and W. Yang, "Maturity classification of rapeseed using hyperspectral image combined with machine learning," Plant Phenomics, vol. 6, p. 0139, 2024. doi: 10.34133/plantphenomics.0139

S. Vignati, A. Tugnolo, V. Giovenzana, A. Pampuri, A. Casson, R. Guidetti, and R. Beghi, "Hyperspectral imaging for fresh-cut fruit and vegetable quality assessment: Basic concepts and applications," Applied Sciences, vol. 13, no. 17, p. 9740, 2023. doi: 10.3390/app13179740

A. Femenias, F. Gatius, A. J. Ramos, V. Sanchis, and S. Marín, "Standardisation of near infrared hyperspectral imaging for quantification and classification of DON contaminated wheat samples," Food Control, vol. 111, p. 107074, 2020. doi: 10.1016/j.foodcont.2019.107074

J. C. Yang, M. Everett, C. Buehler, and L. McMillan, "A real-time distributed light field camera," Rendering Techniques, vol. 2002, no. 77-86, p. 2, 2002.

G. Z. Gu ZhengMin, L. Z. Li ZhenFeng, S. F. Song FeiHu, Z. J. Zhang JunSheng, and Z. W. Zhuang Wei, "Investigation of measurement method of soybean canopy leaf area based on light field camera," 2018.

N. S. Gruda, J. Dong, and X. Li, "From salinity to nutrient-rich vegetables: Strategies for quality enhancement in protected cultivation," Critical Reviews in Plant Sciences, vol. 43, no. 5, pp. 327-347, 2024. doi: 10.1080/07352689.2024.2351678

M. A. Cho, A. Ramoelo, P. Debba, O. Mutanga, R. Mathieu, H. Van Deventer, and N. Ndlovu, "Assessing the effects of subtropical forest fragmentation on leaf nitrogen distribution using remote sensing data," Landscape ecology, vol. 28, no. 8, pp. 1479-1491, 2013.

L. I. Trejo-Téllez, and F. C. Gómez-Merino, "Nutrient solutions for hydroponic systems," Hydroponics-a standard methodology for plant biological researches, vol. 1, pp. 1-22, 2012.

Downloads

Published

31 December 2025

Issue

Vol. 2 No. 1 (2025)

Section

Article

License

Copyright (c) 2025 Yixue Zhang, Jingbo Zhi, Jialiang Zheng, Zhaowei Li, Tiezhu Li (Author)

Creative Commons License

This work is licensed under a Creative Commons Attribution 4.0 International License.

How to Cite

Zhang, Y., Zhi, J., Zheng, J., Li, Z., & Li, T. (2025). Research on Hyperspectral Imaging Detection Method of Nitrogen in Facility-Grown Lettuce. Artificial Intelligence and Digital Technology, 2(1), 178-185. https://doi.org/10.70088/yzkchm20