DOI QR코드

DOI QR Code

Development of Machine Learning Models Classifying Nitrogen Deficiency Based on Leaf Chemical Properties in Shiranuhi (Citrus unshiu × C. sinensis)

부지화 잎의 화학성분에 기반한 질소결핍 여부 구분 머신러닝 모델 개발

  • Park, Won Pyo (Department of Plant Resources and Environment, Jeju National University) ;
  • Heo, Seong (Department of Horticulture, Kongju National University)
  • 박원표 (제주대학교 식물자원환경전공) ;
  • 허성 (공주대학교 원예학과)
  • Received : 2022.02.23
  • Accepted : 2022.03.23
  • Published : 2022.04.01

Abstract

Nitrogen is the most essential macronutrient for the growth of fruit trees and is important factor determining the fruit yield. In order to produce high-quality fruits, it is necessary to supply the appropriate nitrogen fertilizer at the right time. For this, it is a prerequisite to accurately diagnose the nitrogen status of fruit trees. The fastest and most accurate way to determine the nitrogen deficiency of fruit trees is to measure the nitrogen concentration in leaves. However, it is not easy for citrus growers to measure nitrogen concentration through leaf analysis. In this study, several machine learning models were developed to classify the nitrogen deficiency based on the concentration measurement of mineral nutrients in the leaves of tangor Shiranuhi (Citrus unshiu × C. sinensis). The data analyzed from the leaves were increased to about 1,000 training dataset through the bootstrapping method and used to train the models. As a result of testing each model, gradient boosting model showed the best classification performance with an accuracy of 0.971.

본 연구에서는 부지화 잎의 무기양분 농도 측정 결과를 바탕으로 질소를 제외한 다른 무기양분의 함량을 통해서 잎의 질소 결핍 여부를 구분하는 머신러닝 모델을 개발하였다. 그러기 위해서 부지화의 질소결핍구와 대조구의 잎 샘플을 분석한 36개의 데이터를 부트스트랩핑 방법을 통해서 학습용 데이터셋 1,000 여 개로 증량시켰다. 이를 이용해 학습한 각 모델을 테스트한 결과, gradient boosting 모델이 가장 우수한 분류성능을 보여주었다. 본 모델을 이용해 질소함량을 직접적으로 분석할 수 없는 경우, 잎의 무기성분 함량에 기반하여 질소결핍 가능성 여부를 판단해 질소가 부족한 부지화 나무를 분별하고, 정확한 질소함량을 측정하게 유도하여 그에 기초한 적정 질소비료 시비를 가능케 하고자 하였다.

Keywords

References

  1. Bennett, W.F. 1993. Nutrient Deficiencies and Toxicities in Crop Plants. APS Press, St. Paul, MN (USA). p. 202.
  2. Chapman, H.D. 1967. The mineral nutrition of citrus (Chapter 3): In Reuther, W., L.D. Batchelor and H.J. Webber (eds.), The Citrus Industry Vol. III Anatomy, Physiology, Mineral Nutrient, Seed Propagation, Genentics, Growth Regulators, University of California Press, Berkeley, CA (USA). pp. 127-298.
  3. Eo, H.J., Y. Park, G.H. Park, J.A. Kim, D.S. Kim, Y. Kang, K. Kim, J.H. Jang and H.J. Kim. 2021. Study on the correlation between the soil properties and albiflorin, paeoniflorin contents of Paeonia lactiflora Pall. Korean J. Plant Res. 34:384-394 (in Korean). https://doi.org/10.7732/KJPR.2021.34.4.384
  4. Field, C. and H.A. Mooney. 1986. The photosynthesis-nitrogen relationship in wild plants: In Givnish, T.J. (ed.), On The Economy of Plant Form and Function, Cambridge University Press, Cambridge, UK. pp. 25-55.
  5. Guo, S., Y. Chen, X. Chen, Y. Chen, L. Yang, L. Wang, Y. Qin, M. Li, F. Chen, G. Mi, R. Gu and L. Yuan. 2020. Grain mineral accumulation changes in Chinese maize cultivars released in different decades and the responses to nitrogen fertilizer. Front. Plant Sci. 10:1662. https://doi.org/10.3389/fpls.2019.01662
  6. Huang, W.T., Y.Z. Xie, X.F. Chen, J. Zhang, H.H. Chen, X. Ye, J. Guo, L.T. Yang and L.S. Chen. 2021. Growth, mineral nutrients, photosynthesis and related physiological parameters of Citrus in response to nitrogen deficiency. Agronomy 11:1859. https://doi.org/10.3390/agronomy11091859
  7. Hwangbo, H.W. and J.H. Jeong. 2021. Python, Data Science, Statistical Learning. Infopub, Seoul, Korea. pp. 311-358 (in Korean).
  8. Jang, S.W., Y.H. Kim, C.I. Na and I.J. Lee. 2017. Changes in mineral uptake and hormone concentrations in rice plants treated with silicon, nitrogen and calcium independently or in combination. Korean J. Crop Sci. 31:293-303 (in Korean).
  9. Jang, W.J. and J.I. Lee. 2021. All about Data Analysis. ILIFO, Seoul, Korea. pp. 339-341 (in Korean).
  10. Kang, T.W. 2006. Mineral nutrient absorption and disorder of Shiranuhi mandarin [(C. unshiu Marc. × C. sinensis Osb.) × C. reticulata Bla.] in hydroponics culture. Department of Agricultural Chemistry, Ph.D. Thesis, Jeju National Univ., Korea. pp. 5-7 (in Korean).
  11. Kim, D., I.B. Lee, U.H. Yeo, S.Y. Lee, S. Park, D. Cristina, J.G. Kim, Y.B. Choi, J.H. Cho, H.H. Jeong and S. Kang. 2021. Estimation of duck house litter evaporation rate using machine learning. J. Korean Soc. Agric. Eng. 63:77-88 (in Korean). https://doi.org/10.5389/KSAE.2021.63.6.077
  12. Kim, Y.H. and S.Y. Hong. 2007. Estimation of nondestructive rice leaf nitrogen content using ground optical sensors. Korean J. Soil Sci. Fert. 40:435-441 (in Korean).
  13. Kwon, C.M. 2020. Python, Machine Learning, Perfect Guide. Wikibooks, Seoul, Korea. pp. 217-221 (in Korean).
  14. Laacouri, A., T. Nigon, D. Mulla and C. Yang. 2018. A case study comparing machine learning and vegetation indices for assessing corn nitrogen status in an agricultural field in Minnesota. Proceedings of the 14th International Conference on Precision Agriculture, International Society of Precision Agriculture. Monticello, IL (USA). pp. 1-8.
  15. Lee, D.H., Y. Park, S.S. Hong, G.H. Park and H.J. Kim. 2021. Study on the of the correlation between soil chemical properties and bioactive compounds of Acer tegmentosum Maxim. Korean J. Plant Res. 34:566-574.
  16. NIAST. 2000. Methods of Soil and Plant Analysis. National Institute of Agricultural Science and Technology, RDA, Suwon, Korea (in Korean).
  17. Park, W.P. 2003. Effects of nitrogen deficiency on growth and nutrient uptake of (C. unshiu Marc. × C. sinensis Osb.) × C. reticulata Bla. Department of Agricultural Chemistry, M.S. Thesis, Jeju National Univ., Korea. pp. 1-2 (in Korean).
  18. Rufat, J. and T.M. DeJong. 2001. Estimating seasonal nitrogen dynamics in peach trees in response to nitrogen availability. Tree Physiol. 21:1133-1140. https://doi.org/10.1093/treephys/21.15.1133
  19. Shin, B.K. 2019. Naive bayes classification. Available at: https://bkshin.tistory.com (accessed on 19 March 2022) (in Korean).
  20. Sun, Y., Y. Liu, H. Zhou and H. Hu. 2021. Plant disease identification through a discount momentum optimizer in deep learning. Appl. Sci. 11:9468. https://doi.org/10.3390/app11209468
  21. Tang, J., B. Sun, R. Cheng, Z. Shi, D. Luo, S. Liu and M. Centritto. 2019. Effects of soil nitrogen (N) deficiency on photosynthetic N-use efficiency in N-fixing and non-N-fixing tree seedlings in subtropical China. Sci. Rep. 9:4604. https://doi.org/10.1038/s41598-019-41035-1
  22. Thompson, T.L., S.A. White, J. Walworth and G. Sower. 2003. Development of best management practices for fertigation of young citrus trees, 2003 report. In Citrus Research Report 2003, University of Arizona, Tucson, AZ (USA). pp. 1-9.