Comparative analysis of different uni- and multi-variate methods for estimation of vegetation water content using hyper-spectral measurements

Abstract Assessment of vegetation water content is critical for monitoring vegetation condition, detecting plant water stress, assessing the risk of forest fires and evaluating water status for irrigation. The main objective of this study was to investigate the performance of various mono- and multi-variate statistical methods for estimating vegetation water content (VWC) from hyper-spectral data. Hyper-spectral data is influenced by multi-collinearity because of a large number of (independent) spectral bands being modeled by a small number of (dependent) biophysical variables. Therefore, some full spectrum methods that are known to be suitable for analyzing multi-collinear data set were chosen. Canopy spectral reflectance was obtained with a GER 3700 spectro-radiometer (400–2400 nm) in a laboratory setting and VWC was measured by calculating wet/dry weight difference per unit of ground area (g/m2) of each plant canopy (n = 95). Three multivariate statistical methods were applied to estimate VWC: (1) partial least square regression, (2) artificial neural network and (3) principal component regression. They were selected to minimize the problem related to multi-collinearity. For comparison, uni-variate techniques including narrow band ratio water index (RWI), normalized difference water index (NDWI), second soil adjusted vegetation index (SAVI2) and transferred soil adjusted vegetation index (TSAVI) were applied. For each type of vegetation index, all two-band combinations were evaluated to determine the best band combination. Validation of the methods was based on the cross validation procedure and using three statistical indicators: R2, RMSE and relative RMSE. The cross-validated results identified PLSR as the regression model providing the most accurate estimates of VWC among the various methods. The result revealed that this model is highly recommended for use with multi-collinear datasets ( R CV 2 = 0.94 , RRMSECV = 0.23). Principal component regression exhibited the lowest accuracy among the multivariate models ( R CV 2 = 0.78 , RRMSECV = 0.41).

[1]  S. Tarantola,et al.  Designing a spectral index to estimate vegetation water content from remote sensing data: Part 1 - Theoretical approach , 2002 .

[2]  Clement Atzberger,et al.  Comparative analysis of three chemometric techniques for the spectroradiometric assessment of canopy chlorophyll content in winter wheat , 2010 .

[3]  F. Baret,et al.  A ratio vegetation index adjusted for soil brightness , 1990 .

[4]  Fumin Wang,et al.  Comparison Between Radial Basis Function Neural Network and Regression Model for Estimation of Rice Biophysical Parameters Using Remote Sensing , 2009 .

[5]  H. Noh,et al.  A Neural Network Model of Maize Crop Nitrogen Stress Assessment for a Multi-spectral Imaging Sensor , 2006 .

[6]  A. Savitzky,et al.  Smoothing and Differentiation of Data by Simplified Least Squares Procedures. , 1964 .

[7]  F. M. Danson,et al.  Estimating live fuel moisture content from remotely sensed reflectance , 2004 .

[8]  Ruiliang Pu,et al.  Estimation of forest leaf area index using vegetation indices derived from Hyperion hyperspectral data , 2003, IEEE Trans. Geosci. Remote. Sens..

[9]  A. Müller,et al.  Predictions of soil surface and topsoil organic carbon content through the use of laboratory and field spectroscopy in the Albany Thicket Biome of Eastern Cape Province of South Africa , 2011 .

[10]  Byun-Woo Lee,et al.  Assessment of rice leaf growth and nitrogen status by hyperspectral canopy reflectance and partial least square regression , 2006 .

[11]  T. Jackson,et al.  Remote sensing of vegetation water content from equivalent water thickness using satellite imagery , 2008 .

[12]  F. Roli,et al.  Multisource Classification of Complex Rural Areas by Statistical and Neural-Network Approaches , 1997 .

[13]  S. Liang.  Quantitative Remote Sensing of Land Surfaces , 2003 .

[14]  W. Cohen,et al.  An improved strategy for regression of biophysical variables and Landsat ETM+ data. , 2003 .

[15]  Bo-Cai Gao,et al.  Vegetation Biochemistry: What Can Imaging Spectrometry Tell Us About Canopies? , 1991 .

[16]  John A. Gamon,et al.  Monitoring drought effects on vegetation water content and fluxes in chaparral with the 970 nm water band index , 2006 .

[17]  T. Jackson,et al.  Vegetation water content estimation for corn and soybeans using spectral indices derived from MODIS near- and short-wave infrared bands , 2005 .

[18]  S. Leblanc,et al.  A Shortwave Infrared Modification to the Simple Ratio for LAI Retrieval in Boreal Forests: An Image and Model Analysis , 2000 .

[19]  A. Skidmore,et al.  Leaf Area Index derivation from hyperspectral vegetation indicesand the red edge position , 2009 .

[20]  T. Jackson,et al.  III. Measuring surface soil moisture using passive microwave remote sensing , 1993 .

[21]  A. Kalra,et al.  Estimating soil moisture using remote sensing data: A machine learning approach , 2010 .

[22]  N. Broge,et al.  Comparing prediction power and stability of broadband and hyperspectral vegetation indices for estimation of green leaf area index and canopy chlorophyll density , 2001 .

[23]  S. Ustin,et al.  Detection of stress in tomatoes induced by late blight disease in California, USA, using hyperspectral remote sensing , 2003 .

[24]  W. Cohen,et al.  Landsat's Role in Ecological Applications of Remote Sensing , 2004 .

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

[26]  Da-Wen Sun,et al.  Hyperspectral imaging for food quality analysis and control , 2010 .

[27]  C. Tucker.  Remote sensing of leaf water content in the near infrared , 1980 .

[28]  Haiqing Yang,et al.  Remote Sensing Technique for Predicting Harvest Time of Tomatoes , 2011 .

[29]  S. Tarantola,et al.  Detecting vegetation leaf water content using reflectance in the optical domain , 2001 .

[30]  Andrew K. Skidmore,et al.  Estimation of green grass/herb biomass from airborne hyperspectral imagery using spectral indices and partial least squares regression , 2007, Int. J. Appl. Earth Obs. Geoinformation.

[31]  Martha C. Anderson,et al.  Vegetation water content mapping using Landsat data derived normalized difference water index for corn and soybeans , 2004 .

[32]  C. Giardino,et al.  Estimation of leaf and canopy water content in poplar plantations by means of hyperspectral indices and inverse modeling , 2008 .

[33]  Meiling Liu,et al.  Neural-network model for estimating leaf chlorophyll concentration in rice under stress from heavy metals using four spectral indices , 2010 .

[34]  Lorenzo Bruzzone,et al.  An experimental comparison of neural and statistical non-parametric algorithms for supervised classification of remote-sensing images , 1996, Pattern Recognit. Lett..

[35]  R. Fensholt,et al.  Derivation of a shortwave infrared water stress index from MODIS near- and shortwave infrared data in a semiarid environment , 2003 .

[36]  P. Curran.  Remote sensing of foliar chemistry , 1989 .

[37]  F. Baret,et al.  About the soil line concept in remote sensing , 1993 .

[38]  Philip K. Hopke,et al.  Application of PLS and Back-Propagation Neural Networks for the estimation of soil properties , 2005 .

[39]  B. Rock,et al.  Detection of changes in leaf water content using Near- and Middle-Infrared reflectances , 1989 .

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

[41]  J. Peñuelas,et al.  The reflectance at the 950–970 nm region as an indicator of plant water status , 1993 .

[42]  M. Vohland,et al.  Comparing different multivariate calibration methods for the determination of soil organic carbon pools with visible to near infrared spectroscopy , 2011 .

[43]  J. Schjoerring,et al.  Reflectance measurement of canopy biomass and nitrogen status in wheat crops using normalized difference vegetation indices and partial least squares regression , 2003 .

[44]  Clement Atzberger,et al.  Spectrometric estimation of leaf pigments in Norway spruce needles using band - depth analysis, partial least - square regression and inversion of a conifer leaf model , 2003 .

[45]  S. Ustin,et al.  Estimating Vegetation Water content with Hyperspectral data for different Canopy scenarios: Relationships between AVIRIS and MODIS Indexes , 2006 .

[46]  M. Tamura,et al.  Estimation of leaf water status to monitor the risk of forest fires by using remotely sensed data , 2004 .

[47]  Daniel Schläpfer,et al.  1st EARSEL Workshop on Imaging Spectroscopy , 1998 .

[48]  Qihao Weng,et al.  Remote sensing of impervious surfaces in the urban areas: Requirements, methods, and trends , 2012 .

[49]  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 .

[50]  S. Ustin,et al.  Critique of stepwise multiple linear regression for the extraction of leaf biochemistry information from leaf reflectance data , 1996 .

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

[52]  Josep Peñuelas,et al.  Cell wall elasticity and Water Index (R970 nm/R900 nm) in wheat under different nitrogen availabilities , 1996 .

[53]  Xiuping Jia,et al.  Collinearity and orthogonality of endmembers in linear spectral unmixing , 2012, Int. J. Appl. Earth Obs. Geoinformation.

[54]  P. Atkinson,et al.  Introduction Neural networks in remote sensing , 1997 .

[55]  F. Baret,et al.  TSAVI: A Vegetation Index Which Minimizes Soil Brightness Effects On LAI And APAR Estimation , 1989, 12th Canadian Symposium on Remote Sensing Geoscience and Remote Sensing Symposium,.

[56]  Kenshi Sakai,et al.  Potential of airborne hyperspectral imagery to estimate fruit yield in citrus , 2008 .

[57]  Clement Atzberger,et al.  Estimation of vegetation LAI from hyperspectral reflectance data: Effects of soil type and plant architecture , 2008, Int. J. Appl. Earth Obs. Geoinformation.

[58]  Clement Atzberger,et al.  LAI and chlorophyll estimation for a heterogeneous grassland using hyperspectral measurements , 2008 .

[59]  Michael E. Schaepman,et al.  Estimating canopy water content using hyperspectral remote sensing data , 2010, Int. J. Appl. Earth Obs. Geoinformation.

[60]  A. Sasao,et al.  Estimation of citrus yield from airborne hyperspectral images using a neural network model , 2006 .

[61]  C. Justice,et al.  Global land cover classification by remote sensing: present capabilities and future possibilities , 1991 .

[62]  Clement Atzberger,et al.  Derivation of biophysical variables from Earth observation data: validation and statistical measures , 2012 .

[63]  Lin Li,et al.  Retrieval of vegetation equivalent water thickness from reflectance using genetic algorithm (GA)-partial least squares (PLS) regression , 2008 .

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

[65]  B. Gao.  NDWI—A normalized difference water index for remote sensing of vegetation liquid water from space , 1996 .

[66]  Nilanchal Patel,et al.  Biomass estimation of Shorea robusta with principal component analysis of satellite data , 2010, Journal of Forestry Research.

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

[68]  M. Umeda,et al.  Multivariate analysis of nitrogen content for rice at the heading stage using reflectance of airborne hyperspectral remote sensing , 2011 .

[69]  D. Sims,et al.  Estimation of vegetation water content and photosynthetic tissue area from spectral reflectance: a comparison of indices based on liquid water and chlorophyll absorption features , 2003 .