Introduction of Variable Correlation for the Improved Retrieval of Crop Traits Using Canopy Reflectance Model Inversion

Look-up table (LUT)-based canopy reflectance models are considered robust methods to estimate vegetation attributes from remotely sensed data. However, the LUT inversion approach is sensitive to measurements and model uncertainties, which raise the ill-posed inverse problem. Therefore, regularization options are needed to mitigate this problem and reduce the uncertainties of estimates. In this study, we introduce a new method to regularize the LUT inversion approach to improve the accuracy of biophysical parameters (leaf area index (LAI) and fractional vegetation cover (fCover)). This was achieved by incorporating known variable correlations that existed at the test site into the LUT approach to correlate the model variables of the Soil–Leaf–Canopy (SLC) model using the Cholesky decomposition algorithm. The retrievals of 27 potato plots obtained from the regularized LUT (LUTreg) were compared with the standard LUT (LUTstd), which did not consider variable correlations. Different solutions from both types of LUTs (LUTreg and LUTstd) were utilized to improve the quality of the model outputs. Results indicate that the present method improved the accuracy of LAI estimation, with the coefficient of determination R2 = 0.74 and normalized root-mean-square error NRMSE = 24.45% in LUTreg, compared with R2 = 0.71 and NRMSE = 25.57% in LUTstd. In addition, the variability of LAI decreased in LUTreg (5.10) compared with that in LUTstd (12.10). Hence, our results give new insight into the impact of adding the correlation between variables to the LUT inversion approach to improve the accuracy of estimations. In this study, only two correlated variables (LAI and fCover) were examined; in subsequent studies, the full correlation matrix based on the Cholesky algorithm should be explored.

[1]  Peter R. J. North,et al.  Retrieval of leaf area index from MODIS surface reflectance by model inversion using different minimization criteria , 2013 .

[2]  J. Hill,et al.  Use of coupled canopy structure dynamic and radiative transfer models to estimate biophysical canopy characteristics , 2005 .

[3]  Martha C. Anderson,et al.  A comparison of empirical and neural network approaches for estimating corn and soybean leaf area index from Landsat ETM+ imagery ☆ , 2004 .

[4]  Wolfram Mauser,et al.  Remote Sens , 2015 .

[5]  S. Liang,et al.  Retrieving leaf area index using a genetic algorithm with a canopy radiative transfer model , 2003 .

[6]  C. Atzberger.  Object-based retrieval of biophysical canopy variables using artificial neural nets and radiative transfer models , 2004 .

[7]  Y. Li,et al.  Fractional Vegetation Cover Estimation Based on an Improved Selective Endmember Spectral Mixture Model , 2015, PloS one.

[8]  R. Giering,et al.  Application to MISR land products of an RPV model inversion package using adjoint and Hessian codes , 2007 .

[9]  José F. Moreno,et al.  Multiple Cost Functions and Regularization Options for Improved Retrieval of Leaf Chlorophyll Content and LAI through Inversion of the PROSAIL Model , 2013, Remote. Sens..

[10]  Guangjian Yan,et al.  Fractional vegetation cover estimation by using multi-angle vegetation index , 2018, Remote Sensing of Environment.

[11]  Qiang Liu,et al.  The Design and Implementation of the Leaf Area Index Sensor , 2015, Sensors.

[12]  Emilio Chuvieco,et al.  Linking ecological information and radiative transfer models to estimate fuel moisture content in the Mediterranean region of Spain: Solving the ill-posed inverse problem , 2009 .

[13]  R. Casa,et al.  Retrieval of crop canopy properties: a comparison between model inversion from hyperspectral data and image classification , 2004 .

[14]  R. Houborg,et al.  Combining vegetation index and model inversion methods for the extraction of key vegetation biophysical parameters using Terra and Aqua MODIS reflectance data , 2007 .

[15]  W. Verhoef,et al.  A Bayesian object based approach for estimating vegetation biophysical and biochemical variables from APEX at sensor radiance data , 2013 .

[16]  Joseph W. H. Liu.  An adaptive general sparse out-of-core cholesky factorization scheme , 1987 .

[17]  Luis Gómez-Chova,et al.  Biophysical Parameter Estimation With a Semisupervised Support Vector Machine , 2009, IEEE Geoscience and Remote Sensing Letters.

[18]  F. Baret,et al.  Evaluation of Canopy Biophysical Variable Retrieval Performances from the Accumulation of Large Swath Satellite Data , 1999 .

[19]  Jindi Wang,et al.  Development of the Adjoint Model of a Canopy Radiative Transfer Model for Sensitivity Study and Inversion of Leaf Area Index , 2008, IEEE Transactions on Geoscience and Remote Sensing.

[20]  Peter R. J. North,et al.  Statistical Distances and Their Applications to Biophysical Parameter Estimation: Information Measures, M-Estimates, and Minimum Contrast Methods , 2013, Remote. Sens..

[21]  W. Verhoef,et al.  PROSPECT+SAIL models: A review of use for vegetation characterization , 2009 .

[22]  Bo-Hui Tang,et al.  Inversion of the PROSAIL model to estimate leaf area index of maize, potato, and sunflower fields from unmanned aerial vehicle hyperspectral data , 2014, Int. J. Appl. Earth Obs. Geoinformation.

[23]  A. Skidmore,et al.  Inversion of a radiative transfer model for estimating vegetation LAI and chlorophyll in a heterogeneous grassland , 2008 .

[24]  Weiya Shi,et al.  Incomplete Cholesky decomposition based kernel principal component analysis for large-scale data set , 2010, The 2010 International Joint Conference on Neural Networks (IJCNN).

[25]  Alexander Tong.  Estimating Grassland Chlorophyll Content for a Mixed Grassland: Exploring the Performance of the Empirical-statistical and the Physical Modeling Approach , 2014 .

[26]  Wei He,et al.  Exploring optimal design of look-up table for PROSAIL model inversion with multi-angle MODIS data , 2012, Asia-Pacific Environmental Remote Sensing.

[27]  Jan G. P. W. Clevers,et al.  Using Sentinel-2 Data for Retrieving LAI and Leaf and Canopy Chlorophyll Content of a Potato Crop , 2017, Remote. Sens..

[28]  Wolfram Mauser,et al.  Evaluation of the PROSAIL Model Capabilities for Future Hyperspectral Model Environments: A Review Study , 2018, Remote. Sens..

[29]  R. Myneni,et al.  Investigation of a model inversion technique to estimate canopy biophysical variables from spectral and directional reflectance data , 2000 .

[30]  Frédéric Baret,et al.  Fractional vegetation cover estimation algorithm for Chinese GF-1 wide field view data , 2016 .

[31]  J.H. Zhang,et al.  Probabilistic Load Flow Evaluation With Hybrid Latin Hypercube Sampling and Cholesky Decomposition , 2009, IEEE Transactions on Power Systems.

[32]  W. Verhoef,et al.  Multi-temporal, multi-sensor retrieval of terrestrial vegetation properties from spectral–directional radiometric data , 2015 .

[33]  B. Hapke.  Bidirectional reflectance spectroscopy: 1. Theory , 1981 .

[34]  Dmitry Lukyanenko,et al.  Application of a Three-Dimensional Radiative Transfer Model to Retrieve the Species Composition of a Mixed Forest Stand from Canopy Reflected Radiation , 2018, Remote. Sens..

[35]  Jan G. P. W. Clevers,et al.  Optical remote sensing and the retrieval of terrestrial vegetation bio-geophysical properties - A review , 2015 .

[36]  M. Schlerf,et al.  Inversion of a forest reflectance model to estimate structural canopy variables from hyperspectral remote sensing data , 2006 .

[37]  H. Pleijel,et al.  Evaluating the relationship between leaf chlorophyll concentration and SPAD-502 chlorophyll meter readings , 2007, Photosynthesis Research.

[38]  Guang Zheng,et al.  Retrieving Leaf Area Index (LAI) Using Remote Sensing: Theories, Methods and Sensors , 2009, Sensors.

[39]  F. Baret,et al.  PROSPECT: A model of leaf optical properties spectra , 1990 .

[40]  F. Baret,et al.  Quantification of plant stress using remote sensing observations and crop models: the case of nitrogen management. , 2006, Journal of experimental botany.

[41]  Francesco Vuolo,et al.  RETRIEVAL OF LEAF AREA INDEX BY INVERTING HYPER-SPECTRAL, MULTI-ANGULAR CHRIS/PROBA DATA FROM SPARC 2003 , 2004 .

[42]  S. Liang,et al.  A hybrid inversion method for mapping leaf area index from MODIS data: experiments and application to broadleaf and needleleaf canopies , 2005 .

[43]  Roshanak Darvishzadeh,et al.  Inversion of a Radiative Transfer Model for Estimation of Rice Canopy Chlorophyll Content Using a Lookup-Table Approach , 2012, IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing.

[44]  Brigitte Leblon,et al.  Non-destructive estimation of potato leaf chlorophyll from canopy hyperspectral reflectance using the inverted PROSAIL model , 2007, International Journal of Applied Earth Observation and Geoinformation.

[45]  Frédéric Baret,et al.  MODELING CANOPY SPECTRAL PROPERTIES TO RETRIEVE BIOPHYSICAL AND BIOCHEMICAL CHARACTERISTICS. , 1994 .

[46]  Shunlin Liang,et al.  Estimating the Fractional Vegetation Cover from GLASS Leaf Area Index Product , 2016, Remote. Sens..

[47]  J. Clevers,et al.  Estimating potato leaf chlorophyll content using ratio vegetation indices , 2016 .

[48]  Jan G. P. W. Clevers,et al.  Using Hyperspectral Remote Sensing Data for Retrieving Canopy Chlorophyll and Nitrogen Content , 2012, IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing.

[49]  Yuri Knyazikhin,et al.  Retrieval of canopy biophysical variables from bidirectional reflectance Using prior information to solve the ill-posed inverse problem , 2003 .

[50]  Hongyan Zhang,et al.  Comparison of fractional vegetation cover estimations using dimidiate pixel models and look-up table inversions of the PROSAIL model from Landsat 8 OLI data , 2016 .

[51]  Mu Xia,et al.  Global Fractional Vegetation Cover Estimation Algorithm for VIIRS Reflectance Data Based on Machine Learning Methods , 2018, Remote. Sens..

[52]  C. Bacour,et al.  OPTIMAL SAMPLING CONFIGURATIONS FOR THE ESTIMATION OF CANOPY PROPERTIES FROM BRDF DATA ACQUIRED WITH THE EGO / JRC , 2006 .

[53]  Andreas Hueni,et al.  Cause, Effect, and Correction of Field Spectroradiometer Interchannel Radiometric Steps , 2017, IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing.

[54]  J. Hadamard.  Sur les problemes aux derive espartielles et leur signification physique , 1902 .

[55]  Vinay Kumar Sehgal,et al.  Inversion of radiative transfer model for retrieval of wheat biophysical parameters from broadband reflectance measurements , 2016 .

[56]  Farid Melgani,et al.  Gaussian Process Regression for Estimating Chlorophyll Concentration in Subsurface Waters From Remote Sensing Data , 2010, IEEE Geoscience and Remote Sensing Letters.

[57]  W. Verhoef,et al.  Coupled soil–leaf-canopy and atmosphere radiative transfer modeling to simulate hyperspectral multi-angular surface reflectance and TOA radiance data , 2007 .

[58]  A. Skidmore,et al.  Mapping grassland leaf area index with airborne hyperspectral imagery : a comparison study of statistical approaches and inversion of radiative transfer models , 2011 .

[59]  W. J. Timmermans,et al.  Physically based retrieval of crop characteristics for improved water use estimates , 2009 .

[60]  Jan G. P. W. Clevers,et al.  Improved estimation of leaf area index and leaf chlorophyll content of a potato crop using multi-angle spectral data - potential of unmanned aerial vehicle imagery , 2018, Int. J. Appl. Earth Obs. Geoinformation.

[61]  C. Bacour,et al.  Comparison of four radiative transfer models to simulate plant canopies reflectance: direct and inverse mode. , 2000 .

[62]  P. Sabino.  Monte Carlo Methods and Path-Generation Techniques for Pricing Multi-Asset Path-Dependent Options , 2007, 0710.0850.

[63]  F. M. Danson,et al.  Extraction of vegetation biophysical parameters by inversion of the PROSPECT + SAIL models on sugar beet canopy reflectance data. Application to TM and AVIRIS sensors , 1995 .

[64]  Vuolo Francesco,et al.  Retrieval of biophysical vegetation products from RapidEye imagery , 2010 .

[65]  S. Durbha,et al.  Support vector machines regression for retrieval of leaf area index from multiangle imaging spectroradiometer , 2007 .

[66]  Jindi Wang,et al.  A Bayesian network algorithm for retrieving the characterization of land surface vegetation , 2008 .

[67]  Xing Li,et al.  A Bayesian Network-Based Method to Alleviate the Ill-Posed Inverse Problem: A Case Study on Leaf Area Index and Canopy Water Content Retrieval , 2015, IEEE Transactions on Geoscience and Remote Sensing.