Accurate identification of nitrogen fertilizer application of paddy rice using laser-induced fluorescence combined with support vector machine

To identify accurately the doses of nitrogen (N) fertilizer and improve the photosynthetic efficiency of paddy rice, laser induced fluorescence (LIF) technique combined with the support vector machine (SVM) and principal component analysis (PCA) is proposed in this paper. The LIF technology, in which the ultraviolet light (355 nm) is applied as an excitation light source, is employed to measure fluorescence spectra of paddy rice. These fluorescence spectra demonstrate that the fluorescence spectral characteristics of paddy rice leaves with different doses of N fertilizer have distinct differences from each other. Then, PCA and SVM are implemented to extract the features of fluorescence spectra and to recognize different doses of N fertilizer, respectively. The overall recognition accuracy can reach 95%. The results show that the LIF technology combined with PCA and SVM is a convenient, rapid, and sensitive diagnostic method for detecting N levels of paddy rice. Thus, it will also be convenient for farmers to manage accurately their fertilization strategies.

[1]  Xin Huang,et al.  Wavelength selection and spectral discrimination for paddy rice, with laboratory measurements of hyperspectral leaf reflectance , 2011 .

[2]  M. Brestič,et al.  Photosystem II thermostability in situ: environmentally induced acclimation and genotype-specific reactions in Triticum aestivum L. , 2012, Plant physiology and biochemistry : PPB.

[3]  John E. Erickson,et al.  Foliar morphology and canopy nitrogen as predictors of light-use efficiency in terrestrial vegetation , 2003 .

[4]  Moon S. Kim,et al.  Estimating Corn Leaf Chlorophyll Concentration from Leaf and Canopy Reflectance , 2000 .

[5]  Fei Li,et al.  Reflectance estimation of canopy nitrogen content in winter wheat using optimised hyperspectral spectral indices and partial least squares regression , 2014 .

[6]  G. A. Blackburn,et al.  Quantifying Chlorophylls and Caroteniods at Leaf and Canopy Scales: An Evaluation of Some Hyperspectral Approaches , 1998 .

[7]  Hartmut K. Lichtenthaler,et al.  The Chlorophyll Fluorescence Ratio F735/F700 as an Accurate Measure of the Chlorophyll Content in Plants , 1999 .

[8]  M. Brestič,et al.  Application of chlorophyll fluorescence performance indices to assess the wheat photosynthetic functions influenced by nitrogen deficiency. , 2018 .

[9]  Ernst H K Stelzer,et al.  Light-sheet fluorescence microscopy for quantitative biology , 2014, Nature Methods.

[10]  Immanuel Bloch,et al.  Single-atom-resolved fluorescence imaging of an atomic Mott insulator , 2010, Nature.

[11]  W. Lüdeker,et al.  Remote sensing vegetation status by laser-induced fluorescence , 1994 .

[12]  Wei Gong,et al.  Application of fluorescence spectrum to precisely inverse paddy rice nitrogen content , 2016 .

[13]  Gong Wei,et al.  Multi-wavelength canopy LiDAR for remote sensing of vegetation: Design and system performance , 2012 .

[14]  H. Lichtenthaler.  CHLOROPHYLL AND CAROTENOIDS: PIGMENTS OF PHOTOSYNTHETIC BIOMEMBRANES , 1987 .

[15]  M. Boschetti,et al.  Plant nitrogen concentration in paddy rice from field canopy hyperspectral radiometry , 2009 .

[16]  Y Saito,et al.  Investigation of laser-induced fluorescence of several natural leaves for application to lidar vegetation monitoring. , 1998, Applied optics.

[17]  Moon S. Kim,et al.  Distinguishing nitrogen fertilization levels in field corn (Zea mays L.) with actively induced fluorescence and passive reflectance measurements , 1994 .