Utilizing a PLSR-Based Band-Selection Procedure for Spectral Feature Characterization of Floristic Gradients

The study introduces a new approach for the characterization of floristic gradients by hyperspectral features in a partial least squares regression (PLSR) framework. As ecological factors influence the composition of vegetation, our study is aimed to reveal related effects on spectral signatures. For this purpose, the variation of plant species in an open dryland area was projected into a three-dimensional ordination space using nonmetric multidimensional scaling (NMDS). Subsequently, ordination axes score rotations were performed in 180° semicircles and the waveband-specific correlation to spectral field measurements of reflectance, continuum removed, and first-derivative spectra were extracted. A bootstrapped PLSR modeling was applied over the entire rotation space using varying numbers of correlated spectral variables as input samples. On that basis, a new PLSR model suitability term was defined by isosurfaces that are spanned over ordination regions where PLSR latent vector (LV) number and PLSR R2 variance is minimized. It incorporates model performance evaluation with feature characterization using weighted frequencies of spectral variable input in suitable ordination areas. Final PLSR suitability surfaces were transferred to image spectra to prove feature stability and model performance. Our investigation supports the assumption that spectral features are separable to distinct ordination space regions that can be related to individual species gradients. Thereby, the selection of an optimal PLSR model crucially depends on the spectral transformation technique. We further show that stable PLSR models can be derived in multiple ordination directions whereby an appropriate variable selection using suitability surface optimization reduces feature mismatch between field and image spectra.

[1]  Michael Förster,et al.  Remote sensing for mapping natural habitats and their conservation status - New opportunities and challenges , 2015, Int. J. Appl. Earth Obs. Geoinformation.

[2]  Teemu Tahvanainen,et al.  Water chemistry of mires in relation to the poor-rich vegetation gradient and contrasting geochemical zones of the north-eastern fennoscandian Shield , 2004, Folia Geobotanica.

[3]  B. Turner,et al.  Estimating foliage nitrogen concentration from HYMAP data using continuum, removal analysis , 2004 .

[4]  Hannes Feilhauer,et al.  Combining Isomap ordination and imaging spectroscopy to map continuous floristic gradients in a heterogeneous landscape , 2011 .

[5]  Yichun Xie,et al.  Remote sensing imagery in vegetation mapping: a review , 2008 .

[6]  R. Whittaker,et al.  GRADIENT ANALYSIS OF VEGETATION* , 1967, Biological reviews of the Cambridge Philosophical Society.

[7]  Rick L. Lawrence,et al.  Mapping invasive plants using hyperspectral imagery and Breiman Cutler classifications (RandomForest) , 2006 .

[8]  Angela Lausch,et al.  Reduction of Radiometric Miscalibration—Applications to Pushbroom Sensors , 2011, Sensors.

[9]  Z. Niu,et al.  Effects of spectral transformations in statistical modeling of leaf biochemical concentrations , 2003, IEEE Workshop on Advances in Techniques for Analysis of Remotely Sensed Data, 2003.

[10]  J. J. Colls,et al.  Use of hyperspectral derivative ratios in the red-edge region to identify plant stress responses to gas leaks , 2004 .

[11]  J. Kruskal.  Multidimensional scaling by optimizing goodness of fit to a nonmetric hypothesis , 1964 .

[12]  Arko Lucieer,et al.  Combining vegetation indices, constrained ordination and fuzzy classification for mapping semi-natural vegetation units from hyperspectral imagery , 2010 .

[13]  Kalle Ruokolainen,et al.  Mapping gradual landscape-scale floristic changes in Amazonian primary rain forests by combining ordination and remote sensing , 2005 .

[14]  Daniel Schläpfer,et al.  SPECCHIO: a spectrum database for remote sensing applications , 2003 .

[15]  Pablo J. Zarco-Tejada,et al.  High-resolution airborne hyperspectral and thermal imagery for early detection of Verticillium wilt of olive using fluorescence, temperature and narrow-band spectral indices , 2013 .

[16]  Nina Buchmann,et al.  Effects of plant diversity, community composition and environmental parameters on productivity in montane European grasslands , 2005, Oecologia.

[17]  S. Schmidtlein,et al.  Mapping of continuous floristic gradients in grasslands using hyperspectral imagery , 2004 .

[18]  M. Hill,et al.  Reciprocal Averaging : an eigenvector method of ordination , 1973 .

[19]  Wouter Dorigo,et al.  Mapping Bush Encroaching Species by Seasonal Differences in Hyperspectral Imagery , 2010, Remote. Sens..

[20]  M. Cochrane.  Using vegetation reflectance variability for species level classification of hyperspectral data , 2000 .

[21]  Mark Cutler,et al.  Estimating Canopy Chlorophyll Concentration from Field and Airborne Spectra , 1999 .

[22]  D. Vitt,et al.  The relationships of vegetation to surface water chemistry and peat chemistry in fens of Alberta, Canada , 1990, Vegetatio.

[23]  L. Buydens,et al.  Exploring field vegetation reflectance as an indicator of soil contamination in river floodplains. , 2004, Environmental pollution.

[24]  Jane R. Foster,et al.  Application of imaging spectroscopy to mapping canopy nitrogen in the forests of the central Appalachian Mountains using Hyperion and AVIRIS , 2003, IEEE Trans. Geosci. Remote. Sens..

[25]  D. M. Gates,et al.  Spectral Properties of Plants , 1965 .

[26]  S. Ollinger.  Sources of variability in canopy reflectance and the convergent properties of plants. , 2011, The New phytologist.

[27]  Michael E. Schaepman,et al.  Using spectral information from the NIR water absorption features for the retrieval of canopy water content , 2008, Int. J. Appl. Earth Obs. Geoinformation.

[28]  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 .

[29]  F. Artigas,et al.  Hyperspectral remote sensing of marsh species and plant vigour gradient in the New Jersey Meadowlands , 2005 .

[30]  Madhur Anand,et al.  Uncertainty in ecosystem mapping by remote sensing , 2013, Comput. Geosci..

[31]  Thomas Blaschke,et al.  Spatial indicators for nature conservation from European to local scale , 2005 .

[32]  Joydeep Ghosh,et al.  Investigation of the random forest framework for classification of hyperspectral data , 2005, IEEE Transactions on Geoscience and Remote Sensing.

[33]  H. Hotelling.  Analysis of a complex of statistical variables into principal components. , 1933 .

[34]  Lorenzo Bruzzone,et al.  Classification of hyperspectral remote sensing images with support vector machines , 2004, IEEE Transactions on Geoscience and Remote Sensing.

[35]  Hannes Feilhauer,et al.  On variable relations between vegetation patterns and canopy reflectance , 2011, Ecol. Informatics.

[36]  Mike P. Austin,et al.  Continuum Concept, Ordination Methods, and Niche Theory , 1985 .

[37]  Ana Belen Garcia Hernando,et al.  Environmental diagnosis: Integrating biodiversity conservation in management of Natura 2000 forest spaces , 2010 .

[38]  Patrick Hostert,et al.  The EnMAP Spaceborne Imaging Spectroscopy Mission for Earth Observation , 2015, Remote. Sens..

[39]  Kai Wang,et al.  Remote Sensing of Ecology, Biodiversity and Conservation: A Review from the Perspective of Remote Sensing Specialists , 2010, Sensors.

[40]  Martin Evans,et al.  Empirical Modelling of Vegetation Abundance from Airborne Hyperspectral Data for Upland Peatland Restoration Monitoring , 2014, Remote. Sens..

[41]  E. Milton,et al.  The use of the empirical line method to calibrate remotely sensed data to reflectance , 1999 .

[42]  J. Evans,et al.  Gradient modeling of conifer species using random forests , 2009, Landscape Ecology.

[43]  Angela Lausch,et al.  Gradient-Based Assessment of Habitat Quality for Spectral Ecosystem Monitoring , 2015, Remote. Sens..

[44]  Elizabeth M. Middleton,et al.  Selection of Hyperspectral Narrowbands (HNBs) and Composition of Hyperspectral Twoband Vegetation Indices (HVIs) for Biophysical Characterization and Discrimination of Crop Types Using Field Reflectance and Hyperion/EO-1 Data , 2013, IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing.

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

[46]  Roger N. Clark,et al.  Automatic continuum analysis of reflectance spectra , 1987 .

[47]  J. C. Price.  How unique are spectral signatures , 1994 .

[48]  D. Sims,et al.  Relationships between leaf pigment content and spectral reflectance across a wide range of species, leaf structures and developmental stages , 2002 .

[49]  M. Fladeland,et al.  Remote sensing for biodiversity science and conservation , 2003 .

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

[51]  C.J.F. ter Braak,et al.  A Theory of Gradient Analysis , 2004 .

[52]  Onisimo Mutanga,et al.  Continuum - removed absorption features estimate tropical savanna grass quality in situ , 2003 .

[53]  R. Richter,et al.  Geo-atmospheric processing of airborne imaging spectrometry data. Part 2: Atmospheric/topographic correction , 2002 .

[54]  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.

[55]  G. De’ath.  PRINCIPAL CURVES: A NEW TECHNIQUE FOR INDIRECT AND DIRECT GRADIENT ANALYSIS , 1999 .

[56]  Tahir Mehmood,et al.  A review of variable selection methods in Partial Least Squares Regression , 2012 .

[57]  Pablo J. Zarco-Tejada,et al.  Estimating leaf carotenoid content in vineyards using high resolution hyperspectral imagery acquired from an unmanned aerial vehicle (UAV) , 2013 .

[58]  R. Clark,et al.  Spectroscopic Determination of Leaf Biochemistry Using Band-Depth Analysis of Absorption Features and Stepwise Multiple Linear Regression , 1999 .

[59]  S. Hook,et al.  NASA’s Hyperspectral Infrared Imager (HyspIRI) , 2013 .

[60]  S. Schmidtlein,et al.  Mapping the floristic continuum: Ordination space position estimated from imaging spectroscopy , 2007 .

[61]  Henning Buddenbaum,et al.  Comparison of Feature Reduction Algorithms for Classifying Tree Species With Hyperspectral Data on Three Central European Test Sites , 2014, IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing.

[62]  K. R. Clarke,et al.  Change in marine communities : an approach to statistical analysis and interpretation , 2001 .

[63]  Matthijs C. Dorst.  Distinctive Image Features from Scale-Invariant Keypoints , 2011 .

[64]  M. Ashton,et al.  Accuracy assessments of hyperspectral waveband performance for vegetation analysis applications , 2004 .

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

[66]  S. Ustin,et al.  Building spectral libraries for wetlands land cover classification and hyperspectral remote sensing. , 2009, Journal of Environmental Management.

[67]  J. Kerr,et al.  From space to species: ecological applications for remote sensing , 2003 .