Use of high-resolution satellite imagery in an integrated model to predict the distribution of shade coffee tree hybrid zones.

Abstract In New Caledonia (21°S, 165°E), shade-grown coffee plantations were abandoned for economic reasons in the middle of the 20th century. Coffee species ( Coffea arabica , C. canephora and C. liberica ) were introduced from Africa in the late 19th century, they survived in the wild and spontaneously cross-hybridized. Coffee species were originally planted in native forest in association with leguminous trees (mostly introduced species) to improve their growth. Thus the canopy cover over rustic shade coffee plantations is heterogeneous with a majority of large crowns, attributed to leguminous trees. The aim of this study was to identify suitable areas for coffee inter-specific hybridization in New Caledonia using field based environmental parameters and remotely sensed predictors. Due to the complex structure of tropical vegetation, remote sensing imagery needs to be spatially accurate and to have the appropriate bands for monitoring vegetation cover. Quickbird panchromatic (black and white) imagery at 0.6 to 0.7 m spatial resolutions and multispectral imagery at 2.4 m spatial resolution were pansharpened and used for this study. The two most suitable remotely sensed indicators, canopy heterogeneity and tree crown size, were acquired by the sequential use of tree crown detection (neural network), image processing (such as textural analysis) and classification. All models were supervised and trained on learning data determined by human expertise. The final model has two remotely sensed indicators and three physical parameters based on the Digital Elevation Model: elevation, slope and water flow accumulation. Using these five predictive variables as inputs, two modelling methods, a decision tree and a neural network, were implemented. The decision tree, which showed 96.9% accuracy on the test set, revealed the involvement of ecological parameters in the hybridization of Coffea species. We showed that hybrid zones could be characterized by combinations of modalities, underlining the complexity of the environment concerned. For instance, forest heterogeneity and large crown size, steep slopes (> 53.5%) and elevation between 194 and 429 m asl, are favourable factors for Coffea inter-specific hybridization. The application of the neural network on the whole area gave a predictive map that distinguished the most suitable areas by means of a nonlinear continuous indicator. The map provides a confidence level for each area. The most favourable areas were geographically localized, providing a clue for the detection and conservation of favourable areas for Coffea species neo-diversity.

[1]  Steven A. Sader,et al.  Spectral analysis and classification accuracy of coffee crops using Landsat and a topographic‐environmental model , 2007 .

[2]  Whitmore Tc.  On pattern and process in forests. , 1982 .

[3]  J. Chambers,et al.  Regional ecosystem structure and function: ecological insights from remote sensing of tropical forests. , 2007, Trends in ecology & evolution.

[4]  Fergus L. Sinclair,et al.  The role of local knowledge in determining shade composition of multistrata coffee systems in Chiapas, Mexico , 2007, Biodiversity and Conservation.

[5]  E. Næsset,et al.  Classifying species of individual trees by intensity and structure features derived from airborne laser scanner data , 2009 .

[6]  J. Ross Quinlan,et al.  C4.5: Programs for Machine Learning , 1992 .

[7]  P. Mayaux,et al.  A vegetation map of Central Africa derived from satellite imagery , 1999 .

[8]  Sovan Lek,et al.  Artificial neural networks as a tool in ecological modelling, an introduction , 1999 .

[9]  Brenda B. Lin,et al.  Agroforestry management as an adaptive strategy against potential microclimate extremes in coffee agriculture , 2007 .

[10]  S. Lavorel,et al.  Do we need land‐cover data to model species distributions in Europe? , 2004 .

[11]  Larry A. Rendell,et al.  A Practical Approach to Feature Selection , 1992, ML.

[12]  R. Plant,et al.  Classification trees: An alternative non‐parametric approach for predicting species distributions , 2000 .

[13]  R. Manson,et al.  Quantitative classification of coffee agroecosystems spanning a range of production intensities in central Veracruz, Mexico , 2009 .

[14]  R. Manson,et al.  Tree species diversity and vegetation structure in shade coffee farms in Veracruz, Mexico , 2008 .

[15]  Peter M. Atkinson,et al.  Texture classification of Mediterranean land cover , 2007, Int. J. Appl. Earth Obs. Geoinformation.

[16]  T. Dawson,et al.  Modelling species distributions in Britain: a hierarchical integration of climate and land-cover data , 2004 .

[17]  W. Barthlott,et al.  A global assessment of endemism and species richness across island and mainland regions , 2009, Proceedings of the National Academy of Sciences.

[18]  William J. Emery,et al.  A neural network approach using multi-scale textural metrics from very high-resolution panchromatic imagery for urban land-use classification , 2009 .

[19]  Andrew K. Skidmore,et al.  Remotely sensed estimation of forest canopy density: A comparison of the performance of four methods , 2006 .

[20]  Antoine Guisan,et al.  Prediction of plant species distributions across six millennia. , 2008, Ecology letters.

[21]  J. P. Grime,et al.  The Plant community as a working mechanism , 1982 .

[22]  P. Couteron,et al.  Predicting tropical forest stand structure parameters from Fourier transform of very high‐resolution remotely sensed canopy images , 2005 .

[23]  Kenneth Mullen,et al.  Decision conflicts: Within-trial resampling in Richardson's method of triads , 1989 .

[24]  S. Frolking,et al.  Forest disturbance and recovery: A general review in the context of spaceborne remote sensing of impacts on aboveground biomass and canopy structure , 2009 .

[25]  M. Kirkpatrick,et al.  Evolution of a Species' Range , 1997, The American Naturalist.

[26]  P. Defourny,et al.  Retrieving forest structure variables based on image texture analysis and IKONOS-2 imagery , 2006 .

[27]  Douglas J. King,et al.  Automated tree crown detection and delineation in high-resolution digital camera imagery of coniferous forest regeneration , 2002 .

[28]  M. Araújo,et al.  Validation of species–climate impact models under climate change , 2005 .

[29]  J. Pezzopane,et al.  Exigência térmica do café arábica cv. Mundo Novo no subperíodo florescimento-colheita , 2008 .

[30]  M. Erikson.  Species classification of individually segmented tree crowns in high-resolution aerial images using radiometric and morphologic image measures , 2004 .

[31]  V. Poncet,et al.  Favourable habitats for Coffea inter-specific hybridization in central New Caledonia: combined genetic and spatial analyses , 2010 .

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

[33]  Antoine Guisan,et al.  Niche dynamics in space and time. , 2008, Trends in ecology & evolution.

[34]  Eben N. Broadbent,et al.  Spatial partitioning of biomass and diversity in a lowland Bolivian forest: Linking field and remote sensing measurements , 2008 .

[35]  Christopher M. Bishop,et al.  Neural networks for pattern recognition , 1995 .

[36]  H. Keselman,et al.  Backward, forward and stepwise automated subset selection algorithms: Frequency of obtaining authentic and noise variables , 1992 .

[37]  M. Combes,et al.  Introgressive hybridization between the allotetraploid Coffea arabica and one of its diploid ancestors, Coffea canephora, in an exceptional sympatric zone in New Caledonia. , 2007, Genome.

[38]  M. Keller,et al.  Amazon Forest Structure from IKONOS Satellite Data and the Automated Characterization of Forest Canopy Properties , 2008 .

[39]  Víctor M. Toledo,et al.  Biodiversity Conservation in Traditional Coffee Systems of Mexico , 1999 .

[40]  T. Dawson,et al.  SPECIES: A Spatial Evaluation of Climate Impact on the Envelope of Species , 2002 .

[41]  W. Thuiller,et al.  Predicting species distribution: offering more than simple habitat models. , 2005, Ecology letters.

[42]  Darius S. Culvenor,et al.  TIDA: an algorithm for the delineation of tree crowns in high spatial resolution remotely sensed imagery , 2002 .

[43]  R. DeFries,et al.  INCREASING ISOLATION OF PROTECTED AREAS IN TROPICAL FORESTS OVER THE PAST TWENTY YEARS , 2005 .

[44]  N. Coops,et al.  Application of high spatial resolution satellite imagery for riparian and forest ecosystem classification , 2007 .

[45]  Shade management in coffee and cacao plantations , 1998 .

[46]  P. Cramer.  A review of literature of Coffee research in Indonesia , 1957 .

[47]  L. Soto-Pinto,et al.  Woody plant diversity and structure of shade-grown-coffee plantations in northern Chiapas, Mexico. , 2001, Revista de biologia tropical.

[48]  J. Meave,et al.  The role of rustic coffee plantations in the conservation of wild tree diversity in the Chinantec region of Mexico , 2005, Biodiversity & Conservation.

[49]  Leo Breiman,et al.  Classification and Regression Trees , 1984 .

[50]  Ian H. Witten,et al.  Data mining: practical machine learning tools and techniques, 3rd Edition , 1999 .

[51]  David B. Clark,et al.  Application of merged 1-m and 4-m resolution satellite data to research and management in tropical forests , 2003 .

[52]  Russell Greenberg,et al.  Biodiversity Loss in Latin American Coffee Landscapes: Review of the Evidence on Ants, Birds, and Trees , 2008, Conservation biology : the journal of the Society for Conservation Biology.

[53]  J. Blackard,et al.  Journal of Applied , 2006 .