Seasonal Trends in Separability of Leaf Reflectance Spectra for Ailanthus altissima and Four Other Tree Species

The separability of Ailanthus altissima (tree of heaven) from four native species was investigated using spectral reflectance measurements (350 to 2,500 nm) of leaves collected from 13 May through 24 August 2008. For both the original reflectance and a continuum removed dataset, least angle regression (LARS) and random forest classification were used to identify a single set of optimal wavelengths across all sampled dates, a set of optimal wavelengths for each date, and the dates for which Ailanthus is most separable from other species. Leaf classification accuracy was found to vary with both dates and bands used. Contrary to expectations that early spring would provide the best separability, July and August were also identified as potentially good months for species differentiation. Applying continuum removal generally reduced classification error. Band selection using LARS improved classification accuracy. The optimal spectral bands were selected from across the spectrum, typically including 401 to 431 nm, 1,115 nm, and 1,985 to 1,995 nm.

[1]  G. F. Hughes,et al.  On the mean accuracy of statistical pattern recognizers , 1968, IEEE Trans. Inf. Theory.

[2]  J. Woolley.  Reflectance and transmittance of light by leaves. , 1971, Plant physiology.

[3]  C. Tucker,et al.  Leaf optical system modeled as a stochastic process. , 1977, Applied optics.

[4]  R. Clark,et al.  Reflectance spectroscopy: Quantitative analysis techniques for remote sensing applications , 1984 .

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

[6]  R. Heisey.  Allelopathic and herbicidal effects of extracts from tree of heaven (Ailanthus altissima). , 1990 .

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

[8]  I. Kowarik.  Clonal growth in Ailanthus altissima on a natural site in West Virginia , 1995 .

[9]  P. Niemelä,et al.  Invasion of North American Forests by European Phytophagous Insects Legacy of the European crucible , 1996 .

[10]  Susan L. Ustin,et al.  Multivariate statistical classification of soil spectra , 1996 .

[11]  P. Vitousek,et al.  INTRODUCED SPECIES: A SIGNIFICANT COMPONENT OF HUMAN-CAUSED GLOBAL CHANGE , 1997 .

[12]  Craig S. T. Daughtry,et al.  Spectral Discrimination of Cannabis sativa L. Leaves and Canopies , 1998 .

[13]  T. A. Warner,et al.  An evaluation of spatial autocorrelation feature selection , 1999 .

[14]  Richard G. Oderwald,et al.  Spectral Separability among Six Southern Tree Species , 2000 .

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

[16]  A. Skidmore,et al.  Exploring spectral discrimination of grass species in African rangelands , 2001 .

[17]  A. Gitelson,et al.  Optical Properties and Nondestructive Estimation of Anthocyanin Content in Plant Leaves¶ , 2001, Photochemistry and photobiology.

[18]  Mary Ann Fajvan,et al.  A Comparison of Multispectral and Multitemporal Information in High Spatial Resolution Imagery for Classification of Individual Tree Species in a Temperate Hardwood Forest , 2001 .

[19]  M. Lewis,et al.  Spectral characterization of Australian arid zone plants , 2002 .

[20]  A. Bannari,et al.  Spectroradiometric analysis in a hyperspectral use perspective to discriminate between forest species , 2003, IGARSS 2003. 2003 IEEE International Geoscience and Remote Sensing Symposium. Proceedings (IEEE Cat. No.03CH37477).

[21]  A. Skidmore,et al.  Spectral discrimination of vegetation types in a coastal wetland , 2003 .

[22]  Leo Breiman,et al.  Random Forests , 2001, Machine Learning.

[23]  R. Tibshirani,et al.  Least angle regression , 2004, math/0406456.

[24]  E. Nilsen,et al.  Analysis of interactions between the invasive tree-of-heaven (Ailanthus altissima) and the native black locust (Robinia pseudoacacia) , 2005, Plant Ecology.

[25]  Tom Bylander,et al.  Estimating Generalization Error on Two-Class Datasets Using Out-of-Bag Estimates , 2002, Machine Learning.

[26]  S. Stephenson,et al.  Vegetation–site relationships of roadside plant communities in West Virginia, USA , 2005 .

[27]  Thomas Lengauer,et al.  ROCR: visualizing classifier performance in R , 2005, Bioinform..

[28]  Scott J. Goetz,et al.  Observed and predicted responses of plant growth to climate across Canada , 2005 .

[29]  D. Pimentel,et al.  Update on the environmental and economic costs associated with alien-invasive species in the United States , 2005 .

[30]  Mahesh Pal,et al.  Random forest classifier for remote sensing classification , 2005 .

[31]  Niklaus E. Zimmermann,et al.  SEASONAL VARIABILITY IN SPECTRAL REFLECTANCE FOR DISCRIMINATING GRASSLANDS ALONG A DRY-MESIC GRADIENT IN SWITZERLAND , 2005 .

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

[33]  James Theiler,et al.  Sparse linear filters for detection and classification in hyperspectral imagery , 2006, SPIE Defense + Commercial Sensing.

[34]  Tom Fawcett,et al.  An introduction to ROC analysis , 2006, Pattern Recognit. Lett..

[35]  Rick E. Landenberger,et al.  Seed dispersal of the non-native invasive tree Ailanthus altissima into contrasting environments , 2007, Plant Ecology.

[36]  Rick E. Landenberger,et al.  Germination and early growth of Ailanthus and tulip poplar in three levels of forest disturbance , 2007, Biological Invasions.

[37]  Andy Liaw,et al.  Classification and Regression by randomForest , 2007 .

[38]  I. Kowarik,et al.  Biological flora of Central Europe: Ailanthus altissima (Mill.) Swingle , 2007 .

[39]  Timothy A. Warner,et al.  Integrating visible, near‐infrared and short wave infrared hyperspectral and multispectral thermal imagery for geologic mapping: simulated data , 2007 .

[40]  Roberta E. Martin,et al.  Invasive species detection in Hawaiian rainforests using airborne imaging spectroscopy and LiDAR. , 2008 .

[41]  P. Kempeneers,et al.  Model inversion for chlorophyll estimation in open canopies from hyperspectral imagery , 2008 .

[42]  Roberta E. Martin,et al.  Remote sensing of native and invasive species in Hawaiian forests , 2008 .

[43]  Stephen P. Hubbell,et al.  Species Invasions and Extinction: The Future of Native Biodiversity on Islands , 2008 .

[44]  Rick E. Landenberger,et al.  Spatial patterns of female Ailanthus altissima across an urban-to-rural land use gradient , 2009, Urban Ecosystems.

[45]  Timothy A. Warner,et al.  Does single broadband or multispectral thermal data add information for classification of visible, near‐ and shortwave infrared imagery of urban areas? , 2009 .

[46]  M. Schaepman,et al.  Quantitative forest canopy structure assessment using an inverted geometric‐optical model and up‐scaling , 2009 .

[47]  Thomas H. Painter,et al.  Radiometry and Reflectance: From Terminology Concepts to Measured Quantities , 2009 .

[48]  Jennifer A. Miller,et al.  Contextual land-cover classification: incorporating spatial dependence in land-cover classification models using random forests and the Getis statistic , 2010 .

[49]  Nicholas C. Coops,et al.  Employing ground-based spectroscopy for tree-species differentiation in the Gulf Islands National Park Reserve , 2010 .

[50]  Xiaofeng Li,et al.  Improved land cover mapping using random forests combined with landsat thematic mapper imagery and ancillary geographic data. , 2010 .

[51]  Timothy A. Warner,et al.  Remote-Sensing Analysis: From Project Design to Implementation , 2010 .

[52]  Lalit Kumar,et al.  Mapping Lantana camara: accuracy comparison of various fusion techniques. , 2010 .

[53]  T. Warner,et al.  Integrating visible, near-infrared and short-wave infrared hyperspectral and multispectral thermal imagery for geological mapping at Cuprite, Nevada: a rule-based system , 2010 .

[54]  Mark Chopping,et al.  CANAPI: canopy analysis with panchromatic imagery , 2011 .

[55]  J. Pisek,et al.  Estimation of vegetation clumping index using MODIS BRDF data , 2011 .