Abstract
Timely diagnosis of apple tree nutrition is very important for efficient utilization of nutrients and improvement of apple yield and quality. This study aims to establish an accurate prediction model of nitrogen (N), phosphorus (P), and potassium (K) contents in apple tree leaves based on canopy hyperspectral reflectance. Two-year field experiments with four levels of N application were conducted in 2018 and 2019. The data, including canopy scale hyperspectral reflectance and leaf N, P, and K contents, were collected from young fruit stage to fruit enlargement stage. The stacked ensemble model was applied to build prediction model. The extreme learning machine (ELM) optimized by differential evolution (DE) or self-adaptive differential evolution (SaDE) algorithm and the unoptimized ELM were used to build sub-models, and the weighting strategy based on RMSE or partial least squares (PLS) was applied to combine the sub-models. Results showed that, the stacked ensemble model based on optimized ELM had achieved better prediction results, but the results of model optimized by DE algorithm were prone to over fitting. In the sub-model combination process, PLS could provide the optimal weigh to combine sub-models and correct the over fitting problem. The stacked ensemble SaDE_ELM and PLS (SE-SaDE_ELM-PLS) method for predicting N, P, K contents in apple tree leaves had achieved the best results (N, R2P = 0.844, RMSEP = 1.709 g kg−1, RRMSE = 7.654%; P, R2P = 0.931, RMSEP = 0.137 g kg−1, RRMSE = 6.402%; K, R2P = 0.725, RMSEP = 1.071 g kg−1, RRMSE = 8.747%). The SE-SaDE_ELM-PLS method was reliable for in-situ prediction of N, P, and K contents in apple tree leaves.
This is a preview of subscription content, log in via an institution to check access.
Similar content being viewed by others
References
Abulaiti Y, Sawut M, Maimaitiaili B, Ma CY (2020) A possible fractional order derivative and optimized spectral indices for assessing total nitrogen content in cotton. Comput Electron Agric 171:105275. https://doi.org/10.1016/j.compag.2020.105275
Bao SD (2000) Soil Agro-chemistrical Analysis, 3rd ed., China Agricultural Press, Beijing, China, pp. 263–271. (in Chinese)
Basayigit L, Senol H (2009) Prediction of plant nutrient contents in deciduous orchards fruits using spectroradiometer. Int J Chemtech Res 1:212–224
Cao JW, Lin ZP, Huang GB (2012) Self-adaptive evolutionary extreme learning machine. Neural Process Lett 36:285–305. https://doi.org/10.1007/s11063-012-9236-y
Chen PF (2015) A comparison of two approaches for estimating the wheat nitrogen nutrition index using remote sensing. Remote Sens 7:4527–4548. https://doi.org/10.3390/rs70404527
Chen Y, Xu LW, Huang ZY, Jiang L (2014) A self-adaptive different evolution extreme learning algorithm for electrical capacitance tomography system. J Harbin Univ Sci Technol 19:32–37 (in Chinese)
Chen SM, Hu TT, Luo LH, He Q, Zhang SW, Li MY, Cui XL, Li HX (2020) Rapid estimation of leaf nitrogen content in apple-trees based on canopy hyperspectral reflectance using multivariate methods. Infrared Phys Technol 111:103542. https://doi.org/10.1016/j.infrared.2020.103542
Cho MA, Skidmore AK (2006) A new technique for extracting the red edge position from hyperspectral data: the linear extrapolation method. Remote Sens Environ 101:181–193. https://doi.org/10.1016/j.rse.2005.12.011
Comino F, Ayora-Cañada MJ, Aranda V, Díaz A, Domínguez-Vidal A (2018) Near-infrared spectroscopy and X-ray fluorescence data fusion for olive leaf analysis and crop nutritional status determination. Talanta 188:676–684. https://doi.org/10.1016/j.talanta.2018.06.058
Deepak M, Keski-saari S, Fauch L, Granlund L, Oksanen E, Keinanen M (2019) Leaf canopy layers affect spectral reflectance in silver birch. Remote Sens 11:2884. https://doi.org/10.3390/rs11242884
FAO (Food and Agriculture Organization) (2019) Online statistical database. [2020–02–18] http://www.fao.org/faostat/en/ #data.
Feng S, Xu TY, Yu FH, Chen CL, Yang X, Wang NY (2019) Research of method for inverting nitrogen content in canopy leaves of Japonica rice in northeastern China based on hyperspectral remote sensing of Unmanned Aerial Vehicle. Spectrosc Spect Anal 39:3281–3287 (in Chinese)
Galvão RKH, Araujo MCU, José GE, Pontes MJC, Silva EC, Saldanha TCB (2005) A method for calibration and validation subset partitioning. Talanta 67:736–740. https://doi.org/10.1016/j.talanta.2005.03.025
Gunes A, Alpaslan M, Inal A (1998) Critical nutrient concentrations and antagonistic and synergistic relationships among the nutrients of NFT-grown young tomato plants. J Plant Nutr 21:2035–2047. https://doi.org/10.1080/01904169809365542
Huang GB, Zhu QY, Siew CK (2006) Extreme learning machine: theory and applications. Neurocomputing 70:489–501. https://doi.org/10.1016/j.neucom.2005.12.126
Huang T, Liang L, Geng D, Li L, Wang LJ, Wang SG, Luo X, Yang MH (2020) Effects of band width on estimation of wheat LAI using vegetation index. Transactions of the CSAE 36:168–177 (in Chinese)
Ji JM, Cai HJ, He JQ, Wang HJ (2014) Performance evaluation of CERES-Wheat model in Guanzhong Plain of Northwest China. Agric Water Manag 144:1–10. https://doi.org/10.1016/j.agwat.2014.04.016
Kamruzzaman M, Elmasry G, Sun DW, Allen P (2012) Prediction of some quality attributes of lamb meat using near-infrared hyperspectral imaging and multivariate analysis. Anal Chim Acta 714:57–67. https://doi.org/10.1016/j.aca.2011.11.037
Lemaire G, Jeuffroy MH, Gastal F (2008) Diagnosis tool for plant and crop N status in vegetative stage: theory and practices for crop N management. Eur J Agron 28:614–624. https://doi.org/10.1016/j.eja.2008.01.005
Li F, Mistele B, Hu YC, Chen XP, Schmidhalter U (2014) Reflectance estimation of canopy nitrogen content in winter wheat using optimised hyperspectral spectral indices and partial least squares regression. Eur J Agron 52:198–209. https://doi.org/10.1016/j.eja.2013.09.006
Liu YD, Chen XM, Sun XD (2008) Nondestructive measurement of vitamin C in NanFeng tangerine by visible/near-infrared diffuse reflectance spectroscopy. Spectrosc Spect Anal 28:2318–2320 (in Chinese)
Liu L Y (2018) Theory and application of quantitative remote sensing for vegetation, 1 st ed.; Science press, Beijing, China, pp. 23–45.(in Chinese)
Loozen Y, Karssenberg D, De Jong SM, Wang SQ, Dijk JV, Wassen MJ, Rebel KT (2019) Exploring the use of vegetation indices to sense canopy nitrogen to phosphorous ratio in grasses. Int J Appl Earth Obs Geoinf 75:1–14. https://doi.org/10.1016/j.jag.2018.08.012
Maes WH, Steppe K (2019) Perspectives for remote sensing with unmanned aerial vehicles in precision agriculture. Trends Plant Sci 24:152–164. https://doi.org/10.1016/j.tplants.2018.11.007
Menesatti P, Antonucci F, Pallottino F, Roccuzzo G, Allegra M, Stagno F, Intrigliolo F (2010) Estimation of plant nutritional status by Vis–NIR spectrophotometric analysis on orange leaves [Citrus sinensis (L) Osbeck cv Tarocco]. Biosyst Eng 105:448–454. https://doi.org/10.1016/j.biosystemseng.2010.01.003
Ni WD, Brown SD, Man R (2009) Stacked partial least squares regression analysis for spectral calibration and prediction. J Chemom 23:505–517. https://doi.org/10.1002/cem.1246
Osco LP, Ramos APM, Pereira DR, Moriya EAS, Imai NN, Matsubara ET, Estrabis N, De Souza M, Junior JM, Goncalves WN, Li J, Liesenberg V, Create JE (2019) Predicting canopy nitrogen content in citrus-trees using random forest algorithm associated to spectral vegetation indices from UAV-imagery. Remote Sens 11:2925. https://doi.org/10.3390/rs11242925
Qian WW, Chai JR, Zhang ZY, Tan R (2018) Adaptive differential evolution algorithm based on reflective mutation strategy. Comput Eng Appl 54:161–168 (in Chinese)
Schlemmer M, Gitelson A, Schepers J, Ferguson R, Peng Y, Shanahan J, Rundquist D (2013) Remote estimation of nitrogen and chlorophyll contents in maize at leaf and canopy levels. Int J Appl Earth Obs Geoinf 25:47–54. https://doi.org/10.1016/j.jag.2013.04.003
Shan et al., 2019 Shan P, Zhao Y H, Wang Q Y, Sha X P, Lv X Y, Peng S L. Ying Y (2019) Stacked ensemble extreme learning machine coupled with partial least squares-based weighting strategy for nonlinear multivariate calibration. Spectrochim Acta A Mol Biomol Spectrosc 215:97-111. https://doi.org/10.1016/j.saa.2019.02.089
Singh SK, Bejagam KK, An YX, Deshmukh SA (2019) Machine-learning based stacked ensemble model for accurate analysis of molecular dynamics simulations. J Phys Chem A 123:5190–5198. https://doi.org/10.1021/acs.jpca.9b03420
Sreekala GB, Subodh S K (2012) Hyperspectral data mining. In hyperspectral remote sensing of vegetation; Thenkabail P S, Lyon J G, Huete A, Eds.; CRC Press, Boca Raton, FL, USA, pp. 94–116.
Tan KZ, Wang SW, Song YZ, Liu Y, Gong ZP (2018) Estimating nitrogen status of rice canopy using hyperspectral reflectance combined with BPSO-SVR in cold region. Chemometr Intell Lab 172:68–79. https://doi.org/10.1016/j.chemolab.2017.11.014
Wang N, Joost W, Zhang FS (2016) Towards sustainable intensification of apple production in China-Yield gaps and nutrient use efficiency in apple farming systems. J Integr Agric 15:716–725. https://doi.org/10.1016/S2095-3119(15)61099-1
Wei Y, Yue YK (2018) Research on fault diagnosis of a marine fuel system based on the SaDE-ELM algorithm. Algorithms 11:82. https://doi.org/10.3390/a11060082
Wei PF, Xu XG, Li ZY, Yang GJ, Li ZH, Feng HK, Chen G, Fan LL, Wang YL, Liu SB (2019) Remote sensing estimation of nitrogen content in summer maize leaves based on multispectral images of UAV. Transactions of the CSAE 35:126–133 (in Chinese)
Xu L, Jiang JH, Zhou YP, Wu HL, Shen GL, Yu RQ (2007) MCCV stacked regression for model combination and fast spectral interval selection in multivariate calibration. Chemometr Intell Lab 87:226–230. https://doi.org/10.1016/j.chemolab.2007.02.001
Xu R, Liang X, Qi JS, Li ZY, Zhang SS (2019) Advances and trends in extreme learning machine. Chinese Journal of Computers 42:1640–1670 (in Chinese)
Yang BH, Chen JL, Chen LH, Cao WX, Yao X, Zhu Y (2015) Estimation model of wheat canopy nitrogen content based on sensitive bands. Transactions of the CSAE 31:176–182 (in Chinese)
Yao FQ, Zhang ZH, Yang RY, Sun JW, Cui SF (2009) Hyperspectral models for estimating vegetation chlorophyll content based on red edge parameter. Transactions of the CSAE S2:123–129 (in Chinese)
Ye XJ, Abe S, Zhang SH (2020) Estimation and mapping of nitrogen content in apple trees at leaf and canopy levels using hyperspectral imaging. Precis Agric 21:198–225. https://doi.org/10.1007/s11119-019-09661-x
Yu KQ, Zhao YR, Li XL, Shao YN, Liu F, He Y (2014) Hyperspectral imaging for mapping of total nitrogen spatial distribution in pepper plant. PLoS ONE 9:e116205. https://doi.org/10.1371/journal.pone.0116205
Yu SW (2018) MATLAB optimization algorithm case analysis and application. 1 st ed.; Tsinghua University Press: Beijing, China, pp. 505–518. (in Chinese)
Yun YH, Li HD, Deng BC, Cao DS (2019) An overview of variable selection methods in multivariate analysis of near-infrared spectra. Trac-Trend Anal Chem 113:102–115. https://doi.org/10.1016/j.trac.2019.01.018
Zhai YF, Cui LJ, Zhou X, Gao Y, Fei T, Gao WX (2013) Estimation of nitrogen, phosphorus, and potassium contents in the leaves of different plants using laboratory-based visible and near-infrared reflectance spectroscopy: comparison of partial least-square regression and support vector machine regression methods. Int J Remote Sens 34:2502–2518. https://doi.org/10.1080/01431161.2012.746484
Zhang D, Wang C, Li XL, Yang XS, Zhao LB, Xia SJ (2019) Correlation of production constraints with the yield gap of apple cropping systems in Luochuan county, china. J Integr Agric 18:1714–1725. https://doi.org/10.1016/S2095-3119(18)62098-2
Zhou HM, Huang GB, Lin ZP, Wang H, Soh YC (2015) Stacked extreme learning machines. IEEE Trans Cybern 45:2013. https://doi.org/10.1109/TCYB.2014.2363492
Zhou ZJ, Plauborg F, Thomsen AG, Andersen MN (2017) A RVI/LAI-reference curve to detect N stress and guide N fertigation using combined information from spectral reflectance and leaf area measurements in potato. Eur J Agron 87:1–7. https://doi.org/10.1016/j.eja.2017.04.002
Zou XB, Zhao JW, Malcolm JWP, Holmes M, Mao HP (2010) Variables selection methods in near-infrared spectroscopy. Anal Chim Acta 667:14–32. https://doi.org/10.1016/j.aca.2010.03.048
Acknowledgements
This work was supported by the National Key Research and Development Program of China (No.2017YFD0201508).
Author information
Authors and Affiliations
Corresponding author
Ethics declarations
Competing Interests
The authors declare no competing interests.
Additional information
Publisher’s Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
About this article
Cite this article
Chen, S., Hu, T., Luo, L. et al. Prediction of Nitrogen, Phosphorus, and Potassium Contents in Apple Tree Leaves Based on In-Situ Canopy Hyperspectral Reflectance Using Stacked Ensemble Extreme Learning Machine Model. J Soil Sci Plant Nutr 22, 10–24 (2022). https://doi.org/10.1007/s42729-021-00629-3
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s42729-021-00629-3