Mapping an invasive species, kudzu (Pueraria montana), using hyperspectral imagery in western Georgia

Invasive plant species are causing severe environmental and ecological impacts. This study utilized airborne hyperspectral image data and digital image processing techniques to map one of the most aggressive weeds, kudzu (Pueraria montana), in western Georgia. Minimum Noise Fraction (MNF) transform followed by Spectral Angle Mapper (SAM) produced the best map results among several other procedures. Validation with field data show that this procedure delivered user's accuracy of 83.02% for kudzu-invaded plots and 95.90% for non-invaded plots, with Producer's accuracy of 73.26% and 82.47%, respectively. Further analysis using a GIS-based CART analysis indicates the importance of elevation in limiting the spatial distribution of kudzu.

[1]  P. Cai,et al.  Survey of phytophagous insects and foliar pathogens in China for a biocontrol perspective on kudzu, Pueraria montana var. lobata (Willd.) Maesen and S. Almeida (Fabaceae) , 2006 .

[2]  S. Ustin,et al.  Application of multiple endmember spectral mixture analysis (MESMA) to AVIRIS imagery for coastal salt marsh mapping: a case study in China Camp, CA, USA , 2005 .

[3]  T. Harrington,et al.  Kudzu (Pueraria montana) community responses to herbicides, burning, and high-density loblolly pine , 2003, Weed Science.

[4]  Jacob T. Mundt,et al.  Hyperspectral data processing for repeat detection of small infestations of leafy spurge , 2005 .

[5]  A. Hastings,et al.  Use of lidar to study changes associated with Spartina invasion in San Francisco bay marshes , 2006 .

[6]  James H. Everitt,et al.  Use of Remote Sensing for Detecting and Mapping Leafy Spurge (Euphorbia esula) , 1995, Weed Technology.

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

[8]  T. M. Lillesand,et al.  Remote Sensing and Image Interpretation , 1980 .

[9]  I. Forseth,et al.  Kudzu (Pueraria montana): History, Physiology, and Ecology Combine to Make a Major Ecosystem Threat , 2004 .

[10]  G. De’ath,et al.  CLASSIFICATION AND REGRESSION TREES: A POWERFUL YET SIMPLE TECHNIQUE FOR ECOLOGICAL DATA ANALYSIS , 2000 .

[11]  J. Greenberg,et al.  Mapping Invasive Aquatic Vegetation in the Sacramento-San Joaquin Delta using Hyperspectral Imagery , 2006, Environmental monitoring and assessment.

[12]  S. Ustin,et al.  Mapping nonnative plants using hyperspectral imagery , 2003 .

[13]  G. H. Rosenfield,et al.  A coefficient of agreement as a measure of thematic classification accuracy. , 1986 .

[14]  P. Bush,et al.  Leaching and persistence of herbicides for kudzu (Pueraria montana) control on pine regeneration sites , 2006, Weed Science.

[15]  Nancy F. Glenn,et al.  A review of remote sensing of invasive weeds and example of the early detection of spotted knapweed (Centaurea maculosa) and babysbreath (Gypsophila paniculata) with a hyperspectral sensor , 2005, Weed Science.

[16]  James W. E. Dickey,et al.  Intriguing World of Weeds , 2000 .

[17]  Amy E. Parker Williams,et al.  Estimation of leafy spurge cover from hyperspectral imagery using mixture tuned matched filtering , 2002 .

[18]  Susan L. Ustin,et al.  Spectral and physiological uniqueness of perennial pepperweed (Lepidium latifolium) , 2006, Weed Science.

[19]  John F. Mustard,et al.  Identifying land cover variability distinct from land cover change: Cheatgrass in the Great Basin , 2005 .

[20]  T. M. Lillesand,et al.  Remote sensing and image interpretation. Second edition , 1987 .