Using Different Regression Methods to Estimate Leaf Nitrogen Content in Rice by Fusing Hyperspectral LiDAR Data and Laser-Induced Chlorophyll Fluorescence Data

Nitrogen is an essential nutrient element in crop photosynthesis and yield improvement. Thus, it is urgent and important to accurately estimate the leaf nitrogen contents (LNC) of crops for precision nitrogen management. Based on the correlation between LNC and reflectance spectra, the hyperspectral LiDAR (HSL) system can determine three-dimensional structural parameters and biochemical changes of crops. Thereby, HSL technology has been widely used to monitor the LNC of crops at leaf and canopy levels. In addition, the laser-induced fluorescence (LIF) of chlorophyll, related to the histological structure and physiological conditions of green plants, can also be utilized to detect nutrient stress in crops. In this study, four regression algorithms, support vector machines (SVMs), partial least squares (PLS) and two artificial neural networks (ANNs), back propagation NNs (BP-NNs) and radial basic function NNs (RBF-NNs), were selected to estimate rice LNC in booting and heading stages based on reflectance and LIF spectra. These four regression algorithms were used for 36 input variables, including the reflectance spectral variables on 32 wavelengths and four peaks of the LIF spectra. A feature weight algorithm was proposed to select different band combinations for the LNC retrieval models. The determination coefficient (R2) and the root mean square error (RMSE) of the retrieval models were utilized to compare their abilities of estimating the rice LNC. The experimental results demonstrate that (I) these four regression methods are useful for estimating rice LNC in the order of RBF-NNs > SVMs > BP-NNs > PLS; (II) The LIF data in two forms, including peaks and indices, display potential in rice LNC retrieval, especially when using the PLS regression (PLSR) model for the relationship of rice LNC with spectral variables. The feature weighting algorithm is an effective and necessary method to determine appropriate band combinations for rice LNC estimation.

[1]  A. Hamid.  Efficiency of N uptake by wheat, as affected by time and rate of application, using N15-labelled ammonium sulphate and sodium nitrate , 1972, Plant and Soil.

[2]  W. Gong,et al.  Vegetation identification based on characteristics of fluorescence spectral spatial distribution , 2015 .

[3]  Gustavo Camps-Valls,et al.  Retrieval of oceanic chlorophyll concentration with relevance vector machines , 2006 .

[4]  H. Lichtenthaler,et al.  Characterization of the laser-induced blue, green and red fluorescence signatures of leaves of wheat and soybean grown under different irradiance. , 1993, Physiologia plantarum.

[5]  Mingyi He,et al.  Band selection based on feature weighting for classification of hyperspectral data , 2005, IEEE Geoscience and Remote Sensing Letters.

[6]  W. Heine,et al.  [A century of Kjeldahl's nitrogen determination]. , 1985, Zeitschrift fur medizinische Laboratoriumsdiagnostik.

[7]  P. M. Hansena,et al.  Reflectance measurement of canopy biomass and nitrogen status in wheat crops using normalized difference vegetation indices and partial least squares regression , 2003 .

[8]  Bo Zhu,et al.  Estimation of rice leaf nitrogen contents based on hyperspectral LIDAR , 2016, Int. J. Appl. Earth Obs. Geoinformation.

[9]  Yu Huang,et al.  Evaluation of Six Algorithms to Monitor Wheat Leaf Nitrogen Concentration , 2015, Remote. Sens..

[10]  Paul M. Mather,et al.  An assessment of the effectiveness of decision tree methods for land cover classification , 2003 .

[11]  S. Wold,et al.  The Collinearity Problem in Linear Regression. The Partial Least Squares (PLS) Approach to Generalized Inverses , 1984 .

[12]  V. Alekseyev,et al.  Control and signal processing system of hyperspectral FLS LiDAR , 2008, 2008 11th International Biennial Baltic Electronics Conference.

[13]  A. Arneth,et al.  Nitrogen controls plant canopy light-use efficiency in temperate and boreal ecosystems , 2008 .

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

[15]  Nicolas Tremblay,et al.  A comparison of multiwavelength laser-induced fluorescence parameters for the remote sensing of nitrogen stress in field-cultivated corn , 2007 .

[16]  R. Loomis,et al.  Nitrogen and plant production , 1981, Plant and Soil.

[17]  Gabriele Moser,et al.  Partially Supervised classification of remote sensing images through SVM-based probability density estimation , 2005, IEEE Transactions on Geoscience and Remote Sensing.

[18]  J. Dungan,et al.  Estimating the foliar biochemical concentration of leaves with reflectance spectrometry: Testing the Kokaly and Clark methodologies , 2001 .

[19]  A. Huete,et al.  Estimating biophysical parameters of rice with remote sensing data using support vector machines , 2011, Science China Life Sciences.

[20]  Vladimir Vapnik,et al.  Statistical learning theory , 1998 .

[21]  John R. Miller,et al.  Assessing vineyard condition with hyperspectral indices: Leaf and canopy reflectance simulation in a row-structured discontinuous canopy , 2005 .

[22]  Hartmut K. Lichtenthaler,et al.  Fluorescence imaging as a diagnostic tool for plant stress , 1997 .

[23]  K Maxwell,et al.  Chlorophyll fluorescence--a practical guide. , 2000, Journal of experimental botany.

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

[25]  Ibrahim Esat,et al.  ARTIFICIAL NEURAL NETWORK BASED FAULT DIAGNOSTICS OF ROTATING MACHINERY USING WAVELET TRANSFORMS AS A PREPROCESSOR , 1997 .

[26]  Pablo J. Zarco-Tejada,et al.  Chlorophyll Fluorescence Effects on Vegetation Apparent Reflectance: I. Leaf-Level Measurements and Model Simulation , 2000 .

[27]  John R. Miller,et al.  Remote Estimation of Crop Chlorophyll Content Using Spectral Indices Derived From Hyperspectral Data , 2008, IEEE Transactions on Geoscience and Remote Sensing.

[28]  Narayanan Subhash,et al.  Laser-induced red chlorophyll fluorescence signatures as nutrient stress indicator in Rice Plants , 1994 .

[29]  B. Mistele,et al.  Comparison of active and passive spectral sensors in discriminating biomass parameters and nitrogen status in wheat cultivars , 2011 .

[30]  L. Plümer,et al.  Robust fitting of fluorescence spectra for pre-symptomatic wheat leaf rust detection with Support Vector Machines , 2011 .

[31]  Teemu Hakala,et al.  Fast and nondestructive method for leaf level chlorophyll estimation using hyperspectral LiDAR , 2014 .

[32]  J. Eitel,et al.  LiDAR based biomass and crop nitrogen estimates for rapid, non-destructive assessment of wheat nitrogen status , 2014 .

[33]  Jungho Im,et al.  Support vector machines in remote sensing: A review , 2011 .

[34]  S. Wold,et al.  PLS-regression: a basic tool of chemometrics , 2001 .

[35]  M. McKee,et al.  SOIL MOISTURE PREDICTION USING SUPPORT VECTOR MACHINES 1 , 2006 .

[36]  Li Wang,et al.  Design of a New Multispectral Waveform LiDAR Instrument to Monitor Vegetation , 2015, IEEE Geoscience and Remote Sensing Letters.

[37]  Lee F. Johnson,et al.  Nitrogen influence on fresh-leaf NIR spectra , 2001 .

[38]  K. Moffett,et al.  Remote Sens , 2015 .

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

[40]  K. Günther,et al.  Characterisation of Drought Stress of Maize and Wheat Canopies by Means of Spectral Resolved Laser induced Fluorescence , 1992 .

[41]  Xu Chu,et al.  Comparison of different hyperspectral vegetation indices for canopy leaf nitrogen concentration estimation in rice , 2014, Plant and Soil.

[42]  F. Meer,et al.  Quantitative analysis of salt-affected soil reflectance spectra: A comparison of two adaptive methods (PLSR and ANN) , 2007 .

[43]  Andrew M. Wallace,et al.  Recovery of Forest Canopy Parameters by Inversion of Multispectral LiDAR Data , 2012, Remote. Sens..

[44]  K. R. Al-Balushi,et al.  Artificial neural networks and support vector machines with genetic algorithm for bearing fault detection , 2003 .

[45]  Timothy J. Malthus,et al.  A Multispectral Canopy LiDAR Demonstrator Project , 2011, IEEE Geoscience and Remote Sensing Letters.

[46]  Georg Bareth,et al.  Remotely detecting canopy nitrogen concentration and uptake of paddy rice in the Northeast China Plain , 2013 .

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

[48]  J. McMurtrey,et al.  Laser-induced fluorescence of green plants. 1: A technique for the remote detection of plant stress and species differentiation. , 1984, Applied optics.

[49]  J. Houghton,et al.  Climate Change 2013 - The Physical Science Basis: Working Group I Contribution to the Fifth Assessment Report of the Intergovernmental Panel on Climate Change , 2014 .

[50]  Anatoly A. Gitelson,et al.  Remote estimation of nitrogen and chlorophyll contents in maize at leaf and canopy levels , 2013, Int. J. Appl. Earth Obs. Geoinformation.