Performance of one-class classifiers for invasive species mapping using airborne imaging spectroscopy

Abstract Most remote sensing approaches for mapping invasive plant species focus on species in a prominent phenological stage, such as during flowering, and do not systematically evaluate the performance for mapping lower cover fractions. In this study, we used airborne imaging spectroscopy (also known as hyperspectral imaging) to detect the invasive grass Phalaris aquatica and the invasive herb Centaurea solstitialis in a pre-flowering stage in the Jasper Ridge Biological Preserve, California, and compared the performance of three different one-class classifiers: Maxent, biased support vector machines and boosted regression trees. We collected presence data for C. solstitialis and P. aquatica to calibrate each approach and additional presence-absence data to validate model performance on 3 m × 3 m plots. The imaging spectroscopy data were acquired using the Carnegie Airborne Observatory Visible-to-Shortwave Infrared (VSWIR) imaging spectrometer (400–2500 nm range) with a pixel size of 1 m × 1 m. The resulting overall accuracies were 72–74% for C. solstitialis, and 83–88% for P. aquatica. For both species, the overall performance was slightly better for Maxent and BRT than for biased SVM. The detection rates for low cover plots were considerably higher for C. solstitialis than for P. aquatica. The models relied on different areas of the reflectance spectrum, but still produced the same general pattern of predicted species occurrences. We conclude that the different one-class classifiers allow for the detection and monitoring of target species with similar success rates.

[1]  Annekatrin Metz,et al.  Remote sensing of scattered Natura 2000 habitats using a one-class classifier , 2014, Int. J. Appl. Earth Obs. Geoinformation.

[2]  B. Bradley.  Remote detection of invasive plants: a review of spectral, textural and phenological approaches , 2014, Biological Invasions.

[3]  Riyad Ismail,et al.  Mapping Bugweed (Solanum mauritianum) Infestations in Pinus patula Plantations Using Hyperspectral Imagery and Support Vector Machines , 2014, IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing.

[4]  J. Drake,et al.  Modelling ecological niches with support vector machines , 2006 .

[5]  Michael E. Schaepman,et al.  Retrieval of foliar information about plant pigment systems from high resolution spectroscopy , 2009 .

[6]  Bridget Fowler,et al.  A Sociological Analysis of the Satanic Verses Affair , 2000 .

[7]  M. Neteler,et al.  Benefits of hyperspectral remote sensing for tracking plant invasions , 2011 .

[8]  Gregory Asner,et al.  Single-Species Detection With Airborne Imaging Spectroscopy Data: A Comparison of Support Vector Techniques , 2015, IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing.

[9]  J Elith,et al.  A working guide to boosted regression trees. , 2008, The Journal of animal ecology.

[10]  J. Elith,et al.  Do they? How do they? WHY do they differ? On finding reasons for differing performances of species distribution models , 2009 .

[11]  Ribana Roscher,et al.  Can I Trust My One-Class Classification? , 2014, Remote. Sens..

[12]  T. Bernhardsen.  Geographic Information Systems: An Introduction , 1999 .

[13]  Harris David,et al.  A statistical explanation of MaxEnt for ecologists , 2013 .

[14]  Izumi Washitani,et al.  Early detection of the invasive alien plant Solidago altissima in moist tall grassland using hyperspectral imagery , 2013 .

[15]  Nicholas C. Coops,et al.  Spectral Wavelength Selection and Detection of Two Invasive Plant Species in an Urban Area , 2016 .

[16]  R. Kokaly,et al.  Characterizing canopy biochemistry from imaging spectroscopy and its application to ecosystem studies , 2009 .

[17]  Roberta E. Martin,et al.  Carnegie Airborne Observatory: in-flight fusion of hyperspectral imaging and waveform light detection and ranging for three-dimensional studies of ecosystems , 2007 .

[18]  David C. Jones,et al.  Remote Distinction of A Noxious Weed (Musk Thistle: CarduusNutans) Using Airborne Hyperspectral Imagery and the Support Vector Machine Classifier , 2013, Remote. Sens..

[19]  José M. Paruelo,et al.  Grass species differentiation through canopy hyperspectral reflectance , 2009 .

[20]  Lawrence W. Lass,et al.  Detection of Yellow Starthistle (Centaurea solstitialis) and Common St. Johnswort (Hypericum perforatum) with Multispectral Digital Imagery , 1996, Weed Technology.

[21]  Edwin Arnold,et al.  Chronic suprapubic catheterization in the management of patients with spinal cord injuries: analysis of upper and lower urinary tract complications , 2008, BJU International.

[22]  M. Day,et al.  Hyperspectral discrimination of halophytic vegetation as an indicator of stressed arable land , 2006 .

[23]  Ruiliang Pu,et al.  Estimation of yellow starthistle abundance through CASI-2 hyperspectral imagery using linear spectral mixture models , 2006 .

[24]  Miroslav Dudík,et al.  A maximum entropy approach to species distribution modeling , 2004, ICML.

[25]  Lalit Kumar,et al.  Imaging Spectrometry and Vegetation Science , 2001 .

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

[27]  Matthew J. Smith,et al.  Protected areas network is not adequate to protect a critically endangered East Africa Chelonian: Modelling distribution of pancake tortoise, Malacochersus tornieri under current and future climates , 2013, bioRxiv.

[28]  Kevin McGarigal,et al.  Species distribution modelling for the people: unclassified landsat TM imagery predicts bird occurrence at fine resolutions , 2013 .

[29]  Jonne Kotta,et al.  Predicting Species Cover of Marine Macrophyte and Invertebrate Species Combining Hyperspectral Remote Sensing, Machine Learning and Regression Techniques , 2013, PloS one.

[30]  Duccio Rocchini,et al.  Will remote sensing shape the next generation of species distribution models? , 2015 .

[31]  Gregory Asner,et al.  Determining Subcanopy Psidium cattleianum Invasion in Hawaiian Forests Using Imaging Spectroscopy , 2016, Remote. Sens..

[32]  P. Treitz,et al.  Predicting fine-scale tree species abundance patterns using biotic variables derived from LiDAR and high spatial resolution imagery , 2014 .

[33]  S. Ustin,et al.  The role of environmental context in mapping invasive plants with hyperspectral image data , 2008 .

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

[35]  M. Neteler,et al.  Potential of remote sensing to predict species invasions , 2015 .

[36]  Roberta E. Martin,et al.  Carnegie Airborne Observatory-2: Increasing science data dimensionality via high-fidelity multi-sensor fusion , 2012 .

[37]  A. Townsend Peterson,et al.  Novel methods improve prediction of species' distributions from occurrence data , 2006 .

[38]  Paul J. Curran,et al.  Imaging spectrometry , 1994 .

[39]  C. Caldwell,et al.  Estimating suitable environments for invasive plant species across large landscapes: a remote sensing strategy using Landsat 7 ETM+. , 2013 .

[40]  Chih-Jen Lin,et al.  A Practical Guide to Support Vector Classication , 2008 .

[41]  L. Buydens,et al.  Visualisation and interpretation of Support Vector Regression models. , 2007, Analytica chimica acta.

[42]  Roberta E. Martin,et al.  Multi-method ensemble selection of spectral bands related to leaf biochemistry , 2015 .

[43]  Bjoern H. Menze,et al.  A comparison of random forest and its Gini importance with standard chemometric methods for the feature selection and classification of spectral data , 2009, BMC Bioinformatics.

[44]  W. Verhoef,et al.  Hyperspectral analysis of mangrove foliar chemistry using PLSR and support vector regression , 2013 .

[45]  Ribana Roscher,et al.  Mapping raised bogs with an iterative one-class classification approach , 2016 .

[46]  M. Pitcairn,et al.  Yellow starthistle continues its spread in California , 2006 .

[47]  Millenium Ecosystem Assessment.  Ecosystems and human well-being: synthesis , 2005 .

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

[49]  Bruce W. Pengra,et al.  Non-commercial Research and Educational Use including without Limitation Use in Instruction at Your Institution, Sending It to Specific Colleagues That You Know, and Providing a Copy to Your Institution's Administrator. All Other Uses, Reproduction and Distribution, including without Limitation Comm , 2022 .

[50]  Wei Zhang,et al.  Multiple Classifier System for Remote Sensing Image Classification: A Review , 2012, Sensors.

[51]  Conghe Song,et al.  Where's woolly? An integrative use of remote sensing to improve predictions of the spatial distribution of an invasive forest pest the Hemlock Woolly Adelgid. , 2015 .

[52]  Ming Xu,et al.  Estimating Yellow Starthistle (Centaurea solstitialis) Leaf Area Index and Aboveground Biomass with the Use of Hyperspectral Data , 2007, Weed Science.

[53]  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.

[54]  Robert P. Anderson,et al.  Maximum entropy modeling of species geographic distributions , 2006 .