Discriminating Land Use and Land Cover Classes in Brazil Based on the Annual PROBA-V 100 m Time Series

Brazil, with more than 8 million km2, presents six different biomes, ranging from natural grasslands (Pampa biome) to tropical rainfall forests (Amazônia biome), with different land-use types (mostly pasturelands and croplands) and pressures (mainly in the Cerrado biome). The objective of this article is to present a new method to discriminate the most representative land use and land cover (LULC) classes of Brazil, based on the PROBA-V images. The images were converted into vegetation, soil, and shade fraction images by applying the linear spectral mixing model. Then, the pixel-based, highest proportion, annual mosaics of the fraction images, and their corresponding standard deviation images were derived and classified using the random forest algorithm. The following LULC classes were considered: forestlands, shrublands, grasslands, croplands, pasturelands, water bodies, and others. An agreement analysis was conducted with two available LULC maps derived from the Landsat satellite, the MapBiomas, and the Finer Resolution Observation and Monitoring-Global Land Cover (FROM-GLC) projects. Forestlands (412 million ha) and pasturelands (242 million ha) were the two most representative LULC classes; and croplands accounted for 30 million ha. The results presented an overall agreement of 69% and 58% with the MapBiomas and FROM-GLC projects, respectively. The proposed method is a good alternative to support operational projects of LULC map production that are important for planning biodiversity conservation or environmentally sustainable land occupation.

[1]  Myrian de Moura Abdon,et al.  DESMATAMENTO NO BIOMA PANTANAL ATÉ O ANO 2002: RELAÇÕES COM A FITOFISIONOMIA E LIMITES MUNICIPAIS , 2009, Revista Brasileira de Cartografia.

[2]  G. Asner,et al.  Cloud cover in Landsat observations of the Brazilian Amazon , 2001 .

[3]  W. Junk,et al.  Biodiversity in wetlands: an introduction. , 2000 .

[4]  Michael Dixon,et al.  Google Earth Engine: Planetary-scale geospatial analysis for everyone , 2017 .

[5]  Jean Paul Metzger,et al.  The Brazilian Atlantic Forest: How much is left, and how is the remaining forest distributed? Implications for conservation , 2009 .

[6]  Mariana Belgiu,et al.  Random forest in remote sensing: A review of applications and future directions , 2016 .

[7]  G. Fernandes,et al.  Caatinga: The Scientific Negligence Experienced by a Dry Tropical Forest , 2011 .

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

[9]  Corinne Le Quéré,et al.  Carbon emissions from land use and land-cover change , 2012 .

[10]  M. Clark,et al.  Vegetation change in Brazil’s dryland ecoregions and the relationship to crop production and environmental factors: Cerrado, Caatinga, and Mato Grosso, 2001–2009 , 2013 .

[11]  P. Fearnside,et al.  The Lavrados of Roraima: Biodiversity and Conservation of Brazil's Amazonian Savannas , 2007 .

[12]  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 .

[13]  Giles M. Foody,et al.  Good practices for estimating area and assessing accuracy of land change , 2014 .

[14]  Laerte Guimarães Ferreira,et al.  Monitoring the brazilian pasturelands: A new mapping approach based on the landsat 8 spectral and temporal domains , 2017, Int. J. Appl. Earth Obs. Geoinformation.

[15]  Limin Yang,et al.  An analysis of the IGBP global land-cover characterization process , 1999 .

[16]  Juan Carlos Castilla-Rubio,et al.  Land-use and climate change risks in the Amazon and the need of a novel sustainable development paradigm , 2016, Proceedings of the National Academy of Sciences.

[17]  C. Tucker.  Red and photographic infrared linear combinations for monitoring vegetation , 1979 .

[18]  Javier Tomasella,et al.  Desertification trends in the Northeast of Brazil over the period 2000-2016 , 2018, Int. J. Appl. Earth Obs. Geoinformation.

[19]  Valério D. Pillar,et al.  Brazil's neglected biome: The South Brazilian Campos , 2007 .

[20]  W. Dierckx,et al.  PROBA-V mission for global vegetation monitoring: standard products and image quality , 2014 .

[21]  Yosio Edemir Shimabukuro,et al.  The least-squares mixing models to generate fraction images derived from remote sensing multispectral data , 1991, IEEE Trans. Geosci. Remote. Sens..

[22]  B. Wardlow,et al.  Using USDA Crop Progress Data for the Evaluation of Greenup Onset Date Calculated from MODIS 250-Meter Data , 2006 .

[23]  R. Mittermeier,et al.  From hotspot to hopespot: An opportunity for the Brazilian Atlantic Forest , 2018, Perspectives in Ecology and Conservation.

[24]  J. V. Soares,et al.  EVALUATION OF THE CONVERSION FROM FOREST TO PASTURE USING REMOTE SENSING FOR SOIL FERTILILY ANALYSIS , 2000 .

[25]  E. Lambin,et al.  Dynamics of Land-Use and Land-Cover Change in Tropical Regions , 2003 .

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

[27]  Yosio Edemir Shimabukuro,et al.  Monitoring deforestation and forest degradation using multi-temporal fraction images derived from Landsat sensor data in the Brazilian Amazon , 2017, 2017 IEEE International Geoscience and Remote Sensing Symposium (IGARSS).

[28]  M. Bustamante,et al.  Cerrado ecoregions: A spatial framework to assess and prioritize Brazilian savanna environmental diversity for conservation. , 2019, Journal of environmental management.

[29]  Edson E. Sano,et al.  Land cover mapping of the tropical savanna region in Brazil , 2010, Environmental monitoring and assessment.

[30]  A. Huete,et al.  Overview of the radiometric and biophysical performance of the MODIS vegetation indices , 2002 .

[31]  Jan Verbesselt,et al.  Evaluating the Potential of PROBA-V Satellite Image Time Series for Improving LC Classification in Semi-Arid African Landscapes , 2016, Remote. Sens..

[32]  G. Hyman,et al.  Forest law enforcement in the Brazilian Amazon: costs and income effects , 2014 .

[33]  Fabio Rubio Scarano,et al.  Brazilian Atlantic forest: impact, vulnerability, and adaptation to climate change , 2015, Biodiversity and Conservation.

[34]  Stefano Santandrea,et al.  The PROBA-V mission: the space segment , 2014 .

[35]  E. Sano,et al.  Spatiotemporal dynamics of soybean crop in the Matopiba region, Brazil (1990–2015) , 2019, Land Use Policy.

[36]  C. Justice,et al.  Satellite Data Reveal Cropland Losses in South-Eastern Ukraine Under Military Conflict , 2019, Front. Earth Sci..

[37]  D. Morton,et al.  Reevaluating Suitability Estimates Based on Dynamics of Cropland Expansion in the Brazilian Amazon , 2016 .

[38]  Ruben Van De Kerchove,et al.  Crop Area Mapping Using 100-m Proba-V Time Series , 2016, Remote. Sens..

[39]  Stefan Adriaensen,et al.  The PROBA-V mission: image processing and calibration , 2014 .

[40]  Hankui K. Zhang,et al.  Finer resolution observation and monitoring of global land cover: first mapping results with Landsat TM and ETM+ data , 2013 .

[41]  D. Roberts,et al.  Large area mapping of land‐cover change in Rondônia using multitemporal spectral mixture analysis and decision tree classifiers , 2002 .

[42]  Joao dos Santos Vila da Silva,et al.  Cattle ranching and deforestation in the Brazilian Pantanal , 2001 .

[43]  Keith R. McCloy,et al.  Development and Evaluation of Phenological Change Indices Derived from Time Series of Image Data , 2010, Remote. Sens..

[44]  R. Lunetta,et al.  Land-cover change detection using multi-temporal MODIS NDVI data , 2006 .

[45]  Damien Sulla-Menashe,et al.  MODIS Collection 5 global land cover: Algorithm refinements and characterization of new datasets , 2010 .

[46]  Thomas M. Brooks,et al.  Global Biodiversity Conservation: The Critical Role of Hotspots , 2011 .

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

[48]  S. Fritz,et al.  A land cover map of South America , 2004 .

[49]  J. Townshend,et al.  Global land cover classifications at 8 km spatial resolution: The use of training data derived from Landsat imagery in decision tree classifiers , 1998 .

[50]  Yosio Edemir Shimabukuro,et al.  Vegetation Fraction Images Derived from PROBA-V Data for Rapid Assessment of Annual Croplands in Brazil , 2020, Remote. Sens..

[51]  M. Hansen,et al.  Near doubling of Brazil’s intensive row crop area since 2000 , 2018, Proceedings of the National Academy of Sciences.

[52]  Gilles Lemaire,et al.  Campos in Southern Brazil , 2000 .

[53]  Jun Yang,et al.  The first all-season sample set for mapping global land cover with Landsat-8 data. , 2017, Science bulletin.

[54]  W. Junk.  The flood pulse concept in river-floodplain systems , 1989 .

[55]  Gregory P. Asner,et al.  Objective indicators of pasture degradation from spectral mixture analysis of Landsat imagery , 2008 .