Mapping natural habitats using remote sensing and sparse partial least square discriminant analysis

This work presents a novel approach for mapping the spatial distribution of natural habitats in the ‘Foothills of Larzac’ Natura 2000 listed site located in a French Mediterranean biogeographical region. Sparse partial least square discriminant analysis was used to analyse two RapidEye data sets (June 2009 and July 2010) with the purpose of choosing the most informative spectral, textural, and thematic variables that allow discrimination of habitat classes. The sparse partial least square discriminant analysis selected relevant and stable variables for the discrimination of habitat classes that could be linked to ecological or biophysical characteristics. It also gave insight into the similarities and differences between habitat classes with comparable physiognomic characteristics. The highest user accuracy was obtained for dry improved grasslands (u = 91.97%) followed by riparian ash woods (u = 88.38%). These results are very encouraging given that these two classes were identified in Annex 1 of the EC Habitats Directive as of Community interest. Due to limited data input requirements and its computational efficiency, the approach developed in this article is a good alternative to other types of variable selection approaches in a supervised classification framework and can be easily transferred to other Natura 2000 sites.

[1]  Ramanathan Gnanadesikan,et al.  Methods for statistical data analysis of multivariate observations , 1977, A Wiley publication in applied statistics.

[2]  N. Sifakis,et al.  Towards a wider uptake of remote sensing in Natura 2000 monitoring: Streamlining remote sensing products with users' needs and expectations , 2011, 2011 2nd International Conference on Space Technology.

[3]  Clemens Reimann,et al.  Multivariate outlier detection in exploration geochemistry , 2005, Comput. Geosci..

[4]  Xiaoli Li,et al.  Rule-Based Classification , 2014, Data Classification: Algorithms and Applications.

[5]  H. Nagendra,et al.  Remote sensing for conservation monitoring: Assessing protected areas, habitat extent, habitat condition, species diversity, and threats , 2013 .

[6]  S. Keleş,et al.  Sparse partial least squares regression for simultaneous dimension reduction and variable selection , 2010, Journal of the Royal Statistical Society. Series B, Statistical methodology.

[7]  Michael Bock,et al.  Remote sensing and GIS-based techniques for the classification and monitoring of biotopes: Case examples for a wet grass- and moor land area in Northern Germany , 2003 .

[8]  Chad Hendrix,et al.  A Comparison of Urban Mapping Methods Using High-Resolution Digital Imagery , 2003 .

[9]  Thomas Blaschke,et al.  Object based image analysis for remote sensing , 2010 .

[10]  Daniel Clewley,et al.  Updating the Phase 1 habitat map of Wales, UK, using satellite sensor data , 2011 .

[11]  R. Tibshirani.  Regression Shrinkage and Selection via the Lasso , 1996 .

[12]  H. Nagendra.  Using remote sensing to assess biodiversity , 2001 .

[13]  Godela Rossner,et al.  Mapping and indicator approaches for the assessment of habitats at different scales using remote sensing and GIS methods , 2004 .

[14]  Liu Xianming,et al.  A Time Petri Net Extended with Price Information , 2007 .

[15]  C. Romão,et al.  Interpretation manual of European Union habitats. , 1996 .

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

[17]  Choen Kim,et al.  Identification of tree species from high-resolution satellite imagery by using crown parameters , 2008, Remote Sensing.

[18]  Nicole Krämer,et al.  An overview on the shrinkage properties of partial least squares regression , 2007, Comput. Stat..

[19]  A. Rango,et al.  Combining Decision Trees with Hierarchical Object-oriented Image Analysis for Mapping Arid Rangelands , 2007 .

[20]  S. Weiss,et al.  GLM versus CCA spatial modeling of plant species distribution , 1999, Plant Ecology.

[21]  Stephen P. Hubbell,et al.  Local neighborhood effects on long-term survival of individual trees in a neotropical forest , 2001, Ecological Research.

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

[23]  M. Bock,et al.  Object-oriented methods for habitat mapping at multiple scales – Case studies from Northern Germany and Wye Downs, UK , 2005 .

[24]  Robert M. Haralick,et al.  Textural Features for Image Classification , 1973, IEEE Trans. Syst. Man Cybern..

[25]  Davide Ballabio,et al.  Evaluation of model predictive ability by external validation techniques , 2010 .

[26]  C. Muñoz Sobrino,et al.  Automatic habitat classification methods based on satellite images: A practical assessment in the NW Iberia coastal mountains , 2008, Environmental monitoring and assessment.

[27]  Luis A. Sarabia,et al.  Outliers in partial least squares regression: Application to calibration of wine grade with mean infrared data , 2005 .

[28]  Peter Filzmoser,et al.  Robust Multivariate Methods in Chemometrics , 2020, Comprehensive Chemometrics.

[29]  M. Barker,et al.  Partial least squares for discrimination , 2003 .

[30]  A. Rango,et al.  Object-oriented image analysis for mapping shrub encroachment from 1937 to 2003 in southern New Mexico , 2004 .

[31]  R. Lucas,et al.  Rule-based classification of multi-temporal satellite imagery for habitat and agricultural land cover mapping , 2007 .

[32]  Philippe Besse,et al.  Sparse PLS discriminant analysis: biologically relevant feature selection and graphical displays for multiclass problems , 2011, BMC Bioinformatics.

[33]  Jianhua Z. Huang,et al.  Sparse principal component analysis via regularized low rank matrix approximation , 2008 .

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

[35]  Clayton C. Kingdon,et al.  Remote sensing of the distribution and abundance of host species for spruce budworm in Northern Minnesota and Ontario , 2008 .

[36]  Charlotte MacAlister,et al.  Mapping wetlands in the Lower Mekong Basin for wetland resource and conservation management using Landsat ETM images and field survey data. , 2009, Journal of environmental management.

[37]  Ron Wehrens,et al.  The pls Package: Principal Component and Partial Least Squares Regression in R , 2007 .

[38]  Peter Filzmoser,et al.  Review of sparse methods in regression and classification with application to chemometrics , 2012 .

[39]  Sunduz Keles,et al.  Sparse Partial Least Squares Classification for High Dimensional Data , 2010, Statistical applications in genetics and molecular biology.

[40]  Philippe Besse,et al.  Statistical Applications in Genetics and Molecular Biology A Sparse PLS for Variable Selection when Integrating Omics Data , 2011 .

[41]  Philippe Besse,et al.  Sparse canonical methods for biological data integration: application to a cross-platform study , 2009, BMC Bioinformatics.

[42]  R. Tibshirani,et al.  Regression shrinkage and selection via the lasso: a retrospective , 2011 .

[43]  Charalambos Kontoes,et al.  Kernel based re-classification of Earth observation data for fine scale habitat mapping , 2005 .

[44]  A. Boulesteix.  Statistical Applications in Genetics and Molecular Biology PLS Dimension Reduction for Classification with Microarray Data , 2011 .