Using Remote Sensing and Random Forest to Assess the Conservation Status of Critical Cerrado Habitats in Mato Grosso do Sul, Brazil

Brazil’s Cerrado is a highly diverse ecosystem and it provides critical habitat for many species. Cerrado habitats have suffered significant degradation and decline over the past decades due to expansion of cash crops and livestock farming across South America. Approximately 1,800,000 km 2 of the Cerrado remain in Brazil, but detailed maps and conservation assessments of the Cerrado are lacking. We developed a land cover classification for the Cerrado, focusing on the state of Mato Grosso do Sul, which may also be used to map critical habitat for endangered species. We used a Random Forest algorithm to perform a supervised classification on a set of Landsat 8 images. To determine habitat fragmentation for the Cerrado, we used Fragstats. A habitat connectivity analysis was performed using Linkage Mapper. Our final classification had an overall accuracy of 88%. Our classification produced higher accuracies (72%) in predicting Cerrado than existing government maps. We found that remaining Cerrado habitats were severely fragmented. Four potential corridors were identified in the southwest of Mato Grosso do Sul, where large Cerrado patches are located. Only two large patches remain in Mato Grosso do Sul: one within the Kadiweu Indian Reserve, and one near the southeastern edge of the Pantanal-dominated landscape. These results are alarming for rare species requiring larger tracts of habitat such as the giant armadillo ( Priodontes maximus ).

[1]  Eduardo S Brondízio,et al.  Indigenous Burning as Conservation Practice: Neotropical Savanna Recovery amid Agribusiness Deforestation in Central Brazil , 2013, PloS one.

[2]  P. Fearnside Soybean cultivation as a threat to the environment in Brazil , 2001, Environmental Conservation.

[3]  G. Powell,et al.  Terrestrial Ecoregions of the World: A New Map of Life on Earth , 2001 .

[4]  Jeffrey T. Walton Subpixel urban land cover estimation: comparing cubist, random forests, and support vector regression , 2008 .

[5]  A. Desbiez,et al.  The Role of Giant Armadillos (Priodontes maximus) as Physical Ecosystem Engineers , 2013 .

[6]  C. Jacobi,et al.  Conservation in Brazil needs to include non‐forest ecosystems , 2015 .

[7]  L. Silveira,et al.  Ecology of the Giant Armadillo (Priodontes maximus) in the Grasslands of Central Brazil , 2009 .

[8]  G. Asner,et al.  Spatial and temporal probabilities of obtaining cloud‐free Landsat images over the Brazilian tropical savanna , 2007 .

[9]  A. Prasad,et al.  Newer Classification and Regression Tree Techniques: Bagging and Random Forests for Ecological Prediction , 2006, Ecosystems.

[10]  J. Lamarque,et al.  Global Biodiversity: Indicators of Recent Declines , 2010, Science.

[11]  Jie Wang,et al.  Comparison of Classification Algorithms and Training Sample Sizes in Urban Land Classification with Landsat Thematic Mapper Imagery , 2014, Remote. Sens..

[12]  John G. Robinson,et al.  Hunting for Sustainability in Tropical Forests , 1999 .

[13]  Simon D. Jones,et al.  The Performance of Random Forests in an Operational Setting for Large Area Sclerophyll Forest Classification , 2013, Remote. Sens..

[14]  L. Fahrig Effects of Habitat Fragmentation on Biodiversity , 2003 .

[15]  R. Machado,et al.  Conservation of the Brazilian Cerrado , 2005 .

[16]  Ned Horning,et al.  Random Forests : An algorithm for image classification and generation of continuous fields data sets , 2010 .

[17]  Jonathan Cheung-Wai Chan,et al.  Evaluation of random forest and adaboost tree-based ensemble classification and spectral band selection for ecotope mapping using airborne hyperspectral imagery , 2008 .

[18]  Daniel C. Nepstad,et al.  Land-use in Amazonia and the Cerrado of Brazil: State of Knowledge and GIS Database , 1997 .

[19]  Mario Chica-Olmo,et al.  An assessment of the effectiveness of a random forest classifier for land-cover classification , 2012 .

[20]  M. Pal,et al.  Random forests for land cover classification , 2003, IGARSS 2003. 2003 IEEE International Geoscience and Remote Sensing Symposium. Proceedings (IEEE Cat. No.03CH37477).

[21]  Robert J. Marquis,et al.  18. Biodiversity and Conservation Priorities in the Cerrado Region , 2002 .

[22]  Christian Wohlfart,et al.  Mapping Threatened Dry Deciduous Dipterocarp Forest in South-East Asia for Conservation Management , 2014 .

[23]  T. Brooks,et al.  Global Biodiversity Conservation Priorities , 2006, Science.

[24]  Nir Bitansky,et al.  The Hunting of the SNARK , 2016, Journal of Cryptology.

[25]  E. Ostrom,et al.  Connectivity and the Governance of Multilevel Social-Ecological Systems: The Role of Social Capital , 2009 .

[26]  Juan F. Silva,et al.  Spatial heterogeneity, land use and conservation in the cerrado region of Brazil , 2006 .

[27]  Mahesh Pal,et al.  Random forest classifier for remote sensing classification , 2005 .

[28]  J. A. Ratter,et al.  The Brazilian Cerrado Vegetation and Threats to its Biodiversity , 1997 .

[29]  M. A. Damascos,et al.  Bud composition, branching patterns and leaf phenology in cerrado woody species. , 2005, Annals of botany.

[30]  Martin Jung,et al.  Exploiting synergies of global land cover products for carbon cycle modeling , 2006 .

[31]  Matthew E. Watts,et al.  Global Gap Analysis: Priority Regions for Expanding the Global Protected-Area Network , 2004 .

[32]  A. Rylands,et al.  Brazilian Protected Areas , 2005 .

[33]  G. Eiten,et al.  The cerrado vegetation of Brazil , 1972, The Botanical Review.

[34]  C. Brannstrom,et al.  Land change in the Brazilian Savanna (Cerrado), 1986–2002: Comparative analysis and implications for land-use policy , 2008 .

[35]  Leo Breiman,et al.  Random Forests , 2001, Machine Learning.

[36]  Ned Horning,et al.  Land Cover or Image Classification Approaches , 2016 .

[37]  Rosana Cristina Grecchi,et al.  Land cover changes in the Brazilian Cerrado and Caatinga biomes from 1990 to 2010 based on a systematic remote sensing sampling approach , 2015 .

[38]  P. Hostert,et al.  Mining dense Landsat time series for separating cropland and pasture in a heterogeneous Brazilian savanna landscape , 2015 .

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

[40]  M. Barnes,et al.  Effectiveness of terrestrial protected areas in reducing habitat loss and population declines , 2013 .

[41]  G. Colli,et al.  Habitat loss and the effectiveness of protected areas in the Cerrado Biodiversity Hotspot , 2015, Natureza & Conservação.

[42]  Ernesto Camelo de Castro Aerial photo land cover classification of cerrado physiognomies: detailed or accurate maps , 2005 .

[43]  D. R. Cutler,et al.  Utah State University From the SelectedWorks of , 2017 .

[44]  W. McShea,et al.  The ecology and conservation of seasonally dry forests in Asia , 2016 .