Estimating biophysical parameters of rice with remote sensing data using support vector machines

Hyperspectral reflectance (350–2500 nm) measurements were made over two experimental rice fields containing two cultivars treated with three levels of nitrogen application. Four different transformations of the reflectance data were analyzed for their capability to predict rice biophysical parameters, comprising leaf area index (LAI; m2 green leaf area m−2 soil) and green leaf chlorophyll density (GLCD; mg chlorophyll m−2 soil), using stepwise multiple regression (SMR) models and support vector machines (SVMs). Four transformations of the rice canopy data were made, comprising reflectances (R), first-order derivative reflectances (D1), second-order derivative reflectances (D2), and logarithm transformation of reflectances (LOG). The polynomial kernel (POLY) of the SVM using R was the best model to predict rice LAI, with a root mean square error (RMSE) of 1.0496 LAI units. The analysis of variance kernel of SVM using LOG was the best model to predict rice GLCD, with an RMSE of 523.0741 mg m−2. The SVM approach was not only superior to SMR models for predicting the rice biophysical parameters, but also provided a useful exploratory and predictive tool for analyzing different transformations of reflectance data.

[1]  Warren L. Butler,et al.  HIGHER DERIVATIVE ANALYSIS OF COMPLEX ABSORPTION SPECTRA , 1970 .

[2]  L. D. Miller,et al.  Remote mapping of standing crop biomass for estimation of the productivity of the shortgrass prairie, Pawnee National Grasslands, Colorado , 1972 .

[3]  A. J. Richardsons,et al.  DISTINGUISHING VEGETATION FROM SOIL BACKGROUND INFORMATION , 1977 .

[4]  C. Tucker.  Red and photographic infrared linear combinations for monitoring vegetation , 1979 .

[5]  R. Jackson,et al.  Spectral response of a plant canopy with different soil backgrounds , 1985 .

[6]  Ronald J. P. Lyon,et al.  Influence of rock-soil spectral variation on the assessment of green biomass , 1985 .

[7]  R. Jackson,et al.  Spectral response of architecturally different wheat canopies , 1986 .

[8]  F. Baret,et al.  Monitoring wheat canopies with a high spectral resolution radiometer , 1987 .

[9]  A. Huete.  A soil-adjusted vegetation index (SAVI) , 1988 .

[10]  Michael D. Steven,et al.  High resolution derivative spectra in remote sensing , 1990 .

[11]  A. J. Richardson,et al.  Vegetation indices in crop assessments , 1991 .

[12]  Tsuyoshi Akiyama,et al.  Estimating grain yield of maturing rice canopies using high spectral resolution reflectance measurements , 1991 .

[13]  J. Dungan,et al.  Reflectance spectroscopy of fresh whole leaves for the estimation of chemical concentration , 1992 .

[14]  Tsuyoshi Akiyama,et al.  Canopy water deficit detection in paddy rice using a high resolution field spectroradiometer , 1993 .

[15]  Christopher B. Field,et al.  Reflectance indices associated with physiological changes in nitrogen- and water-limited sunflower leaves☆ , 1994 .

[16]  W. Ripple.  Determining coniferous forest cover and forest fragmentation with NOAA-9 advanced very high resolution radiometer data , 1994 .

[17]  J. Peñuelas,et al.  The red edge position and shape as indicators of plant chlorophyll content, biomass and hydric status. , 1994 .

[18]  Wolfram Mauser,et al.  Imaging Spectroscopy in Hydrology and Agriculture - Determination of Model Parameters , 1994 .

[19]  Prasad S. Thenkabail,et al.  Landsat-5 Thematic Mapper models of soybean and corn crop characteristics , 1994 .

[20]  J. Hill,et al.  Imaging spectrometry : a tool for environmental observations , 1994 .

[21]  B. Yoder,et al.  Predicting nitrogen and chlorophyll content and concentrations from reflectance spectra (400–2500 nm) at leaf and canopy scales , 1995 .

[22]  C. Elvidge,et al.  Comparison of broad-band and narrow-band red and near-infrared vegetation indices , 1995 .

[23]  L. Johnson,et al.  Spectrometric Estimation of Total Nitrogen Concentration in Douglas-Fir Foliage , 1996 .

[24]  S. Gandia,et al.  Analyses of spectral-biophysical relationships for a corn canopy , 1996 .

[25]  R. Lunetta,et al.  A change detection experiment using vegetation indices. , 1998 .

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

[27]  Bernhard Schölkopf,et al.  The connection between regularization operators and support vector kernels , 1998, Neural Networks.

[28]  Xiao‐Hai Yan,et al.  A Neural Network Model for Estimating Sea Surface Chlorophyll and Sediments from Thematic Mapper Imagery , 1998 .

[29]  G. Carter.  Reflectance Wavebands and Indices for Remote Estimation of Photosynthesis and Stomatal Conductance in Pine Canopies , 1998 .

[30]  Bisun Datt,et al.  A New Reflectance Index for Remote Sensing of Chlorophyll Content in Higher Plants: Tests using Eucalyptus Leaves , 1999 .

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

[32]  Nello Cristianini,et al.  An introduction to Support Vector Machines , 2000 .

[33]  Vladimir N. Vapnik,et al.  The Nature of Statistical Learning Theory , 2000, Statistics for Engineering and Information Science.

[34]  P. Thenkabail,et al.  Hyperspectral Vegetation Indices and Their Relationships with Agricultural Crop Characteristics , 2000 .

[35]  John R. Miller,et al.  Scaling-up and model inversion methods with narrowband optical indices for chlorophyll content estimation in closed forest canopies with hyperspectral data , 2001, IEEE Trans. Geosci. Remote. Sens..

[36]  J. Suykens.  Nonlinear modelling and support vector machines , 2001, IMTC 2001. Proceedings of the 18th IEEE Instrumentation and Measurement Technology Conference. Rediscovering Measurement in the Age of Informatics (Cat. No.01CH 37188).

[37]  John R. Miller,et al.  Integrated narrow-band vegetation indices for prediction of crop chlorophyll content for application to precision agriculture , 2002 .

[38]  N. Broge,et al.  Deriving green crop area index and canopy chlorophyll density of winter wheat from spectral reflectance data , 2002 .

[39]  Bernard A. Engel,et al.  AE—Automation and Emerging Technologies: Neural Network Prediction of Maize Yield using Alternative Data Coding Algorithms , 2002 .

[40]  Axisymmetric fundamental solutions for a finite layer with impeded boundaries , 2003, Journal of Zhejiang University. Science.

[41]  In situ hyperspectral data analysis for pigment content estimation of rice leaves , 2003 .

[42]  In situ hyperspectral data analysis for pigment content estimation of rice leaves. , 2003, Journal of Zhejiang University. Science.

[43]  A. Skidmore,et al.  Integrating imaging spectroscopy and neural networks to map grass quality in the Kruger National Park, South Africa , 2004 .

[44]  Y. Wang,et al.  A modified chlorophyll absorption continuum index for chlorophyll estimation , 2006 .