Integrating conventional classifiers with a GIS expert system to increase the accuracy of invasive species mapping

Mapping the cover of invasive species using remotely sensed data alone is challenging, because many invaders occur as mid-level canopy species or as subtle understorey species and therefore contribute little to the spectral signatures captured by passive remote sensing devices. In this study, two common non-parametric classifiers namely, the neural network and support vector machine were used to map four cover classes of the invasive shrub Lantana camara in a protected game reserve and the adjacent area under communal land management in Zimbabwe. These classifiers were each combined with a geographic information system (GIS) expert system, in order to test whether the new hybrid classifiers yielded significantly more accurate invasive species cover maps than the single classifiers. The neural network, when used on its own, mapped the cover of L. camara with an overall accuracy of 71% and a Kappa index of agreement of 0.61. When the neural network was combined with an expert system, the overall accuracy and Kappa index of agreement significantly increased to 83% and 0.77, respectively. Similarly, the support vector machine achieved an overall accuracy of 64% with a Kappa index of agreement of 0.52, whereas the hybrid support vector machine and expert system classifier achieved a significantly higher overall accuracy of 76% and a Kappa index of agreement of 0.67. These results suggest that integrating conventional image classifiers with an expert system increases the accuracy of invasive species mapping.

[1]  H. C. Hanson,et al.  An Agricultural Survey of Southern Rhodesia. Part I. Agro-Ecological Survey , 1962 .

[2]  M. Madden,et al.  Remote Sensing and Geographic Information System Operations for Vegetation Mapping of Invasive Exotics1 , 2004 .

[3]  A. Skidmore,et al.  An Operational GIS Expert System for Mapping Forest Soils , 1996 .

[4]  A. Skidmore.  Terrain position as mapped from a gridded digital elevation model , 1990 .

[5]  Russell G. Congalton,et al.  A review of assessing the accuracy of classifications of remotely sensed data , 1991 .

[6]  G. Foody.  Thematic map comparison: Evaluating the statistical significance of differences in classification accuracy , 2004 .

[7]  F. Chapin,et al.  Consequences of changing biodiversity , 2000, Nature.

[8]  J. Leeuw,et al.  Indirect remote sensing of a cryptic forest understorey invasive species , 2006 .

[9]  Andrew K. Skidmore,et al.  Improved understorey bamboo cover mapping using a novel hybrid neural network and expert system , 2009 .

[10]  P. Vitousek,et al.  Remote analysis of biological invasion and biogeochemical change. , 2005, Proceedings of the National Academy of Sciences of the United States of America.

[11]  A. Skidmore,et al.  A post-classifier for mangrove mapping using ecological data , 2006 .

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

[13]  L. Foxcroft,et al.  Seven decades of institutional learning: managing alien plant invasions in the Kruger National Park, South Africa , 2007, Oryx.

[14]  M. Zalucki,et al.  Lantana: Current Management Status and Future Prospects , 2003 .

[15]  D. Simberloff,et al.  BIOTIC INVASIONS: CAUSES, EPIDEMIOLOGY, GLOBAL CONSEQUENCES, AND CONTROL , 2000 .

[16]  J. Hierro.  A biogeographical approach to plant invasions: Ecology and evolution of an invasive ruderal in native and introduced ranges , 2005 .

[17]  J. Duggin,et al.  Lantana camara L. invasions in dry rainforest ‐ open forest ecotones: The role of disturbances associated with fire and cattle grazing , 1997 .

[18]  Lloyd L. Coulter,et al.  Detecting Tamarisk species (Tamarix spp.) in riparian habitats of Southern California using high spatial resolution hyperspectral imagery , 2007 .

[19]  A. Stein,et al.  Spatial statistics for remote sensing , 2002 .

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

[21]  Doria Gordon.  Cronk, Q. C. B., and J. L. Fuller. 2001. Plant Invaders: the Threat to Natural Ecosystems. Earthscan Publications, London, UK. , 2002 .

[22]  James H. Everitt,et al.  Using Satellite Data to Map False Broomweed (Ericameria austrotexana) Infestations on South Texas Rangelands , 1993, Weed Technology.

[23]  J. Seibert,et al.  On the calculation of the topographic wetness index: evaluation of different methods based on field observations , 2005 .

[24]  Qihao Weng,et al.  A survey of image classification methods and techniques for improving classification performance , 2007 .

[25]  Roberta E. Martin,et al.  Invasive plants transform the three-dimensional structure of rain forests , 2008, Proceedings of the National Academy of Sciences.

[26]  J. Duggin,et al.  Interference of shape Choricarpia leptopetala by shape Lantana camara with nutrient enrichment in mesic forests on the Central Coast of NSW , 1998, Plant Ecology.

[27]  Giles M. Foody,et al.  Toward intelligent training of supervised image classifications: directing training data acquisition for SVM classification , 2004 .

[28]  D. C. Le Maitre,et al.  Invasive alien trees and water resources in South Africa: case studies of the costs and benefits of management , 2002 .

[29]  A. K. Skidmore,et al.  Derivation of the red edge index using the MERIS standard band setting , 2002 .

[30]  S. Neser,et al.  Biological control of Lantana camara (Verbenaceae) in South Africa , 1991 .

[31]  Luc Lens,et al.  Airborne remote sensing of spatiotemporal change (1955-2004) in indigenous and exotic forest cover in the Taita Hills, Kenya , 2009, Int. J. Appl. Earth Obs. Geoinformation.

[32]  F. Chapin,et al.  EFFECTS OF BIODIVERSITY ON ECOSYSTEM FUNCTIONING: A CONSENSUS OF CURRENT KNOWLEDGE , 2005 .

[33]  J. Maron,et al.  A biogeographical approach to plant invasions: the importance of studying exotics in their introduced and native range , 2005 .

[34]  A. Jermy,et al.  Plant invaders: The threat to natural ecosystems , 1997 .

[35]  Richard J. Hobbs,et al.  Deliberate Introductions of Species: Research Needs Benefits can be reaped, but risks are high , 1999 .

[36]  Giles M. Foody,et al.  The use of small training sets containing mixed pixels for accurate hard image classification: Training on mixed spectral responses for classification by a SVM , 2006 .

[37]  Z. Syed,et al.  Tsetse flies are attracted to the invasive plant Lantana camara. , 2004, Journal of insect physiology.

[38]  R. Schmid,et al.  World Weeds: Natural Histories and Distribution , 1997 .

[39]  S. Prasher,et al.  Application of support vector machine technology for weed and nitrogen stress detection in corn , 2006 .

[40]  N. Fowler.  THE JOINT EFFECTS OF GRAZING, COMPETITION, AND TOPOGRAPHIC POSITION ON SIX SAVANNA GRASSES , 2002 .

[41]  I. A. Ross,et al.  Lantana camara L , 2003 .

[42]  D. C. L. Maitrea,et al.  Invasive alien trees and water resources in South Africa : case studies of the costs and benefits of management , 2002 .

[43]  Lalit Kumar,et al.  Mapping Coastal Vegetation Using an Expert System and Hyperspectral Imagery , 2004 .

[44]  Andrew K. Skidmore,et al.  Accuracy assessment of spatial information , 1999 .

[45]  Richard N. Mack,et al.  Assessing invasive alien species across multiple spatial scales: working globally and locally , 2007 .

[46]  Vladimir Vapnik,et al.  An overview of statistical learning theory , 1999, IEEE Trans. Neural Networks.

[47]  Andrew K. Skidmore,et al.  Integration of classification methods for improvement of land-cover map accuracy , 2002 .

[48]  D. Maitre,et al.  Invasive plants and water resources in the Western Cape Province, South Africa: modelling the consequences of a lack of management. , 1996 .

[49]  B. Turner,et al.  Performance of a neural network: mapping forests using GIS and remotely sensed data , 1997 .

[50]  K. Reinhart.  Invasive Plants , 2006, Science.

[51]  Frank Puppe.  Integration of Classification Methods , 1993 .

[52]  A. Skidmore.  An expert system classifies eucalypt forest types using thematic mapper data and a digital terrain model , 1989 .

[53]  Giles M. Foody,et al.  Mapping specific habitats from remotely sensed imagery: Support vector machine and support vector data description based classification of coastal saltmarsh habitats , 2007, Ecol. Informatics.

[54]  M. Abrams.  The Advanced Spaceborne Thermal Emission and Reflection Radiometer (ASTER): Data products for the high spatial resolution imager on NASA's Terra platform , 2000 .

[55]  S. Lavorel,et al.  Invasibility and diversity of plant communities:from patterns to processes , 1999 .

[56]  Keith Beven,et al.  Environmental Modelling , 2007 .

[57]  M. Ramsey,et al.  Monitoring urban land cover change: An expert system approach to land cover classification of semiarid to arid urban centers , 2001 .

[58]  P. Hocking,et al.  The Biology of Australian Weeds. 12. , 1983 .

[59]  Panetta,et al.  The Biology Of Australian Weeds , 1995 .

[60]  Andrew K. Skidmore,et al.  Use of an expert system to map forest soils from a geographical information system , 1991, Int. J. Geogr. Inf. Sci..

[61]  Andrew K. Skidmore,et al.  Mapping East African tropical forests and woodlands — A comparison of classifiers , 2007 .

[62]  D. Richardson,et al.  Plant Invasions and Invasibility of Plant Communities , 2013 .

[63]  F. V. Oudtshoorn.  Guide to Grasses of Southern Africa , 2012 .

[64]  S. Scherr.  Soil Degradation: A Threat to Developing-Country Food Security by 2020? , 1999 .

[65]  K. C. Palgrave.  Trees of Southern Africa , 1977 .

[66]  L. Henderson.  Invasive, naturalized and casual alien plants in southern Africa: a sum- mary based on the Southern African Plant Invaders Atlas (SAPIA) , 2007 .