Hyperspectral Estimation Methods for Chlorophyll Content of Apple Based on Random Forest

  • Haojie Pei
  • Changchun LiEmail author
  • Haikuan FengEmail author
  • Guijun Yang
  • Mingxing Liu
  • Zhichao Wu
Conference paper
Part of the IFIP Advances in Information and Communication Technology book series (IFIPAICT, volume 546)


Chlorophyll content is a good indicator of fruit tree nutrition stress, photosynthesis, and another physiological state. 10 vegetation indices were selected and used as input variables of RF model, the number of input variables was gradually increased from 1 to 10. The modeling accuracy of 10 RF models with vegetation indices was compared. Finally, the accuracy of 2 estimation models, the RF model with the original spectrum, and the RF optimal model with vegetation indices were established and compared. The result, For modeling accuracy of 2 models, the R2 of four models are 0.527 and 0.609, and the RMSE of 2 models are 8.728 and 7.930 μg/cm2, respectively. For validation accuracy of 2 models, R2 of 2models is 0.411 and 0.843, RMSE is 14.455 and 11.034 μg/cm2, respectively. The result showed, (1) the accuracy of RF model with vegetation indices is higher than the other model. (2) The RF model with vegetation indices can estimate the chlorophyll content of apple leaves more accurately and it had the potential for estimating chlorophyll content of apple leaf. And it provides a new method for the accurate estimation of chlorophyll of apple leaves.


Apple leaf Hyperspectral Chlorophyll RF 



This work was supported in part by the National Natural Science Foundation of China (41601346, 41601369, 41471285, 41301475), Beijing Academy of agricultural and Forestry Sciences Innovation Capacity Construction Specific Projects (Grant no. KJCX20170423).


  1. 1.
    Jiang, J., Chen, Y., Huang, W.: Using hyperspectral remote sensing to estimate canopy chlorophyll density of wheat under yellow rust stress. Spectrosc. Spectral Anal. 30(8), 2243–2247 (2010)Google Scholar
  2. 2.
    Xu, X., Zhao, C., Wang, J., Li, C., Liu, H.: Study on relationship between new characteristic parameters of spectral curve and chlorophyll content for rice. Spectros. Spectral Anal. 31(1), 188–191 (2011)Google Scholar
  3. 3.
    Zhang, Y., Zheng, L., Li, M., Deng, X., Wang, S., Ji, R.: Construction of apple tree leaves nutrients prediction model based on spectral analysis. Trans. Chin. Soc. Agric. Eng. 29(8), 171–178 (2013)Google Scholar
  4. 4.
    Li, M.: Correlation between apple leaf spectral reflectance and chlorophyll content and leaf total nitrogen. Northwest Agriculture and Forestry University (2009)Google Scholar
  5. 5.
    Li, P.: Study on modeling total and phosphorus content of Korla Fragrant Pear leaves based on Hyperspectrum by analysis. Xinjiang Agricultural University (2013)Google Scholar
  6. 6.
    Zhang, L.: Hyperspectral Estimation on Chlorophyll and Water Contents in Young Apple Leaves. Shandong Agricultural University (2013)Google Scholar
  7. 7.
    Wang, L., Zhou, X., Zhu, X., Guo, W.: Inverting wheat leaf area index based on HJ-CCD remote sensing data and random forest algorithm. Trans. Chin. Soc. Agric. Eng. 3, 149–154 (2016)Google Scholar
  8. 8.
    Li, F., Wang, L., Liu, J., Chang, Q.: Remote sensing estimation of SPAD value for wheat leaf based on GF-1 data. Trans. Chin. Soc. Agric. Mach. 46(9), 273–281 (2015)Google Scholar
  9. 9.
    Wang, L., Ma, C., Zhou, X., Zhu, X., Guo, W.: Estimation of wheat leaf SPAD value using RF algorithmic model and remote sensing data. Trans. Chin. Soc. Agric. Mach. 46(1), 259–265 (2015)Google Scholar
  10. 10.
    Han, Z., et al.: Hyperspectral estimation of apple tree canopy LAI based on SVM and RF regression. Spectros. Spectral Anal. 36(3), 800–805 (2016)Google Scholar
  11. 11.
    Yue, J., Yang, G., Feng, H.: Comparative of remote sensing estimation models of winter wheat biomass based on random forest algorithm. Trans. Chin. Soc. Agric. Eng. 18, 175–182 (2016)Google Scholar
  12. 12.
    Lichtenthaler, H.K.: Chlorophylls and carotenoids: pigments of photosynthetic biomembranes. Methods Enzymol. 148(34), 350–382 (1987)CrossRefGoogle Scholar
  13. 13.
    Periuelas, J., Gamon, J.A., Fredeen, A.L., Merion, J., Field, C.B.: Reflectance indices associated with physiological changes in nitrogen- and water-limited sunflower leaves. Rem. Sens. Environ. 48(2), 135–146 (1994)CrossRefGoogle Scholar
  14. 14.
    Peñuelas, J., Filella, I., Lloret, P., Muñoz, F., Vilajeliu, M.: Reflectance assessment of mite effects on apple trees. Int. J. Rem. Sens. 16(14), 2727–2733 (2010)CrossRefGoogle Scholar
  15. 15.
    Daughtry, C.S.T., Walthall, C.L., Kim, M.S., Colstoun, E.B.D., Lii, M.M.: Estimating corn leaf chlorophyll concentration from leaf and canopy reflectance. Rem. Sens. Environ. 74(2), 229–239 (2000)CrossRefGoogle Scholar
  16. 16.
    Haboudane, D., Miller, J.R., Pattey, E., Zarco-Tejada, P.J., Strachan, I.B.: Hyperspectral vegetation indices and novel algorithms for predicting green LAI of crop canopies: modeling and validation in the context of precision agriculture. Rem. Sens. Environ. 90(3), 337–352 (2004)CrossRefGoogle Scholar
  17. 17.
    Haboudane, D., Miller, J.R., Tremblay, N., Zarco-Tejada, P.J., Dextraze, L.: Integrated narrow-band vegetation indices for prediction of crop chlorophyll content for application to precision agriculture. Rem. Sens. Environ. 81(2), 416–426 (2002)CrossRefGoogle Scholar
  18. 18.
    Dash, J., Curran, P.J.: The MERIS terrestrial chlorophyll index. Int. J. Rem. Sens. 25(23), 5403–5413 (2004)CrossRefGoogle Scholar
  19. 19.
    Sims, D.A., Gamon, J.A.: Relationships between leaf pigment content and spectral reflectance across a wide range of species, leaf structures and developmental stages. Remote Sens. Environ. 81(2–3), 337–354 (2002)CrossRefGoogle Scholar
  20. 20.
    Tucker, C.J.: Red and photographic infrared linear combinations for monitoring vegetation. Rem. Sens. Environ. 8(2), 127–150 (1979)CrossRefGoogle Scholar
  21. 21.
    Gitelson, A.A., Merzlyak, M.N., Chivkunova, O.B.: Optical properties and nondestructive estimation of anthocyanin content in plant leaves. Photochem. Photobiol. 74(1), 38–45 (2001)CrossRefGoogle Scholar
  22. 22.
    Roujean, J.L., Breon, F.M.: Estimating PAR absorbed by vegetation from bidirectional reflectance measurements. Rem. Sens. Environ. 51(3), 375–384 (1995)CrossRefGoogle Scholar
  23. 23.
    Qi, J., Chehbouni, A., Huete, A.R., Kerr, Y.H., Sorooshian, S.: A modified soil adjusted vegetation index. Rem. Sens. Environ. 48(2), 119–126 (1994)CrossRefGoogle Scholar
  24. 24.
    Guyot, G., Baret, F., Major, D.J.: High spectral resolution: determination of spectral shifts between the red and near infrared. ISPRS Archives, XXVII Part B7, 750–760 (1988)Google Scholar
  25. 25.
    Vincini, M., Frazzi, E., Alessio, P.D.: Angular dependence of maize and sugar beet VIs from directional CHRIS/Proba data (2006)Google Scholar
  26. 26.
    Gitelson, A.A., Merzlyak, M.N.: Remote estimation of chlorophyll content in higher plant leaves. Int. J. Rem. Sens. 18(12), 2691–2697 (1997)CrossRefGoogle Scholar
  27. 27.
    Vogelmann, J.E., Rock, B.N., Moss, D.M.: Red edge spectral measurements from sugar maple leaves. Int. J. Rem. Sens. 14(8), 1563–1575 (1993)CrossRefGoogle Scholar
  28. 28.
    Zarcotejada, P.J., Miller, J.R., Noland, T.L., Mohammed, G.H.: Scaling-up and model inversion methods with narrowband optical indices for chlorophyll content estimation in closed forest canopies with hyperspectral data. IEEE Trans. Geosci. Rem. Sens. 39(7), 1491–1507 (2001)CrossRefGoogle Scholar
  29. 29.
    Oppelt, N., Mauser, W.: The chlorophyll content of maize (zea mays) derived with the Airborne Imaging Spectrometer AVIS (2001)Google Scholar
  30. 30.
    Zarco-Tejada, P.J., Pushnik, J.C., Dobrowski, S., Ustin, S.L.: Steady-state chlorophyll a, fluorescence detection from canopy derivative reflectance and double-peak, red-edge effects. Rem. Sens. Environ. 84(2), 283–294 (2003)CrossRefGoogle Scholar
  31. 31.
    Kim, M.S., Daughtry, C.S.T., Chapelle, E.W.: The use of high spectral resolution bands for estimating absorbed photosynthetically active radiation (Apar.). In: Proceedings of the Sixth Symposium on Physical Measurements and Signatures in Remote Sensing, Val D’ Isure, France, 17–21 January 1994, vol. 299 (1994)Google Scholar
  32. 32.
    Chen, P., Haboudane, D., Tremblay, N., Wang, J., Vigneault, P., Li, B.: New spectral indicator assessing the efficiency of crop nitrogen treatment in corn and wheat. Rem. Sens. Environ. 114(9), 1987–1997 (2010)CrossRefGoogle Scholar
  33. 33.
    Jin, X., Li, Z., Feng, H., Yang, G.: Newly combined spectral indices to improve estimation of total leaf chlorophyll content in cotton. IEEE J. Sel. Top. Appl. Earth Observations Rem. Sens. 1(1), 4589–4600 (2014)CrossRefGoogle Scholar
  34. 34.
    Breiman, L.: Random forests. Mach. Learn. 45(1), 5–32 (2001)CrossRefGoogle Scholar
  35. 35.
    Breiman, L.: Bagging predictors. Mach. Learn. 24(2), 123–140 (1996)zbMATHGoogle Scholar
  36. 36.
    Wolpert, D.H., Macready, W.G.: An efficient method to estimate bagging’s generalization error, pp. 41–55. Santa Fe Institute (1999)Google Scholar

Copyright information

© IFIP International Federation for Information Processing 2019

Authors and Affiliations

  • Haojie Pei
    • 1
    • 2
    • 3
    • 4
    • 5
  • Changchun Li
    • 5
    Email author
  • Haikuan Feng
    • 1
    • 2
    • 3
    • 4
    Email author
  • Guijun Yang
    • 1
    • 2
    • 3
    • 4
  • Mingxing Liu
    • 1
    • 2
    • 3
    • 4
    • 5
  • Zhichao Wu
    • 1
    • 2
    • 3
    • 4
    • 5
  1. 1.Key Laboratory of Quantitative Remote Sensing in Agriculture of Ministry of Agriculture People’s Republic of ChinaBeijing Research Center for Information Technology in AgricultureBeijingChina
  2. 2.National Engineering Research Center for Information Technology in AgricultureBeijingChina
  3. 3.Key Laboratory for Information Technologies in Agriculture, the Ministry of AgricultureBeijingChina
  4. 4.Beijing Engineering Research Center of Agricultural Internet of ThingsBeijingChina
  5. 5.School of Surveying and Land Information EngineeringHenan Polytechnic UniversityJiaozuoChina

Personalised recommendations