Generalized space-time classifiers for monitoring sugarcane areas in Brazil

Abstract Spatially and temporally accurate information on crop areas is a prerequisite for monitoring the multiannual dynamics of crop production. Satellite images have proven their high potential for mapping crop areas at large scales, even at the crop-species level, when a classifier is calibrated on the same image with reference data corresponding to the same period. For operational monitoring purposes, however, it is critical to develop generalized classification methodologies applicable to large scales and different years. Generalized classifiers were presented in this study as follows: a) simple cross-year calibration and application (M1); b) multiyear calibrations (M2); and c) map updating through change detection with multiyear calibrations (M3). These three methods were developed in a classical frame of object-based classifications for a time series of Landsat images with the Random Forest machine learning algorithm. Therein, we tested these methods for sugarcane classification in Sao Paulo state, Brazil, as sugarcane is an economically important crop that has developed substantially in the past decades. Eight years of sugarcane reference maps were used to calibrate and validate the classifiers at four different sites. The cross-year application of M1 provided a low average accuracy Dice coefficient (DC) of 0.84, while it was, on average, 0.94 for the classical same-year calibration. When the classifier was trained on a multiyear dataset (M2), the accuracies achieved average values of 0.91 in independent years. The map updating method M3 showed promising results but was not able to reach the accuracy of visual interpretation methods for detecting annual sugarcane land use change. The multiyear classifier M2 was applied to four contrasting sites and provided reliable results for new sites and years for sugarcane classification. Calibration of the machine learning algorithm on a multiyear dataset of standardized and gap-filled satellite images and reference data proved to give an accurate and space-time generalized classifier, reducing the time, cost and resources for mapping sugarcane areas at large scales.

[1]  Prasad S. Thenkabail,et al.  An Automated Cropland Classification Algorithm (ACCA) for Tajikistan by Combining Landsat, MODIS, and Secondary Data , 2012, Remote. Sens..

[2]  Fabian Löw,et al.  The impact of training class proportions on binary cropland classification , 2017 .

[3]  A. Huete.  A soil-adjusted vegetation index (SAVI) , 1988 .

[4]  Elfatih M. Abdel-Rahman,et al.  The application of remote sensing techniques to sugarcane (Saccharum spp. hybrid) production: a review of the literature , 2008 .

[5]  Geoffrey J. Hay,et al.  Object-based change detection , 2012 .

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

[7]  Bernardo Friedrich Theodor Rudorff,et al.  Multi‐temporal analysis of MODIS data to classify sugarcane crop , 2006 .

[8]  Russell G. Congalton,et al.  Spectral matching techniques (SMTs) and automated cropland classification algorithms (ACCAs) for mapping croplands of Australia using MODIS 250-m time-series (2000–2015) data , 2017, Int. J. Digit. Earth.

[9]  Gregory J. McDermid,et al.  Object-based approaches to change analysis and thematic map update: challenges and limitations , 2008 .

[10]  C. Woodcock,et al.  Continuous change detection and classification of land cover using all available Landsat data , 2014 .

[11]  S. Robinson,et al.  Food Security: The Challenge of Feeding 9 Billion People , 2010, Science.

[12]  C. Woodcock,et al.  Continuous monitoring of forest disturbance using all available Landsat imagery , 2012 .

[13]  Alexander Brenning,et al.  Using spectrotemporal indices to improve the fruit-tree crop classification accuracy , 2017 .

[14]  Stéphane Dupuy,et al.  A Combined Random Forest and OBIA Classification Scheme for Mapping Smallholder Agriculture at Different Nomenclature Levels Using Multisource Data (Simulated Sentinel-2 Time Series, VHRS and DEM) , 2017, Remote. Sens..

[15]  J. Fry,et al.  Updating the 2001 National Land Cover Database land cover classification to 2006 by using Landsat imagery change detection methods , 2009 .

[16]  Shanti Reddy,et al.  An Evaluation of the Use of Atmospheric and BRDF Correction to Standardize Landsat Data , 2010, IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing.

[17]  S. K. McFeeters.  The use of the Normalized Difference Water Index (NDWI) in the delineation of open water features , 1996 .

[18]  Dongmei Chen,et al.  Change detection from remotely sensed images: From pixel-based to object-based approaches , 2013 .

[19]  A. Huete,et al.  The use of vegetation indices in forested regions: issues of linearity and saturation , 1997, IGARSS'97. 1997 IEEE International Geoscience and Remote Sensing Symposium Proceedings. Remote Sensing - A Scientific Vision for Sustainable Development.

[20]  Daniel Alves Aguiar,et al.  Remote Sensing Images in Support of Environmental Protocol: Monitoring the Sugarcane Harvest in São Paulo State, Brazil , 2011, Remote. Sens..

[21]  R. Congalton,et al.  Automated cropland mapping of continental Africa using Google Earth Engine cloud computing , 2017 .

[22]  Chris Derksen,et al.  Identification of snow cover regimes through spatial and temporal clustering of satellite microwave brightness temperatures , 2010 .

[23]  S. Sader,et al.  Detection of forest harvest type using multiple dates of Landsat TM imagery , 2002 .

[24]  Susan L. Ustin,et al.  Classification Trees for Aquatic Vegetation Community Prediction From Imaging Spectroscopy , 2012, IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing.

[25]  S. Stehman,et al.  Validation of the 2008 MODIS-MCD45 global burned area product using stratified random sampling , 2014 .

[26]  Robert E. Wolfe,et al.  A Landsat surface reflectance dataset for North America, 1990-2000 , 2006, IEEE Geoscience and Remote Sensing Letters.

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

[28]  F. Gao,et al.  Improved forest change detection with terrain illumination corrected Landsat images , 2013 .

[29]  Ian T. Jolliffe.  The Dice co‐efficient: a neglected verification performance measure for deterministic forecasts of binary events , 2016 .

[30]  Christopher B. Field,et al.  Direct impacts on local climate of sugar-cane expansion in Brazil , 2011 .

[31]  J. A. Schell,et al.  Monitoring vegetation systems in the great plains with ERTS , 1973 .

[32]  Daniel Alves Aguiar,et al.  Studies on the Rapid Expansion of Sugarcane for Ethanol Production in São Paulo State (Brazil) Using Landsat Data , 2010, Remote. Sens..

[33]  Francesca Bovolo,et al.  Updating Land-Cover Maps by Classification of Image Time Series: A Novel Change-Detection-Driven Transfer Learning Approach , 2013, IEEE Transactions on Geoscience and Remote Sensing.

[34]  John E. Estes,et al.  Studying the Earth's Vegetation from Space , 1984 .

[35]  Taghi M. Khoshgoftaar,et al.  An Empirical Study of Learning from Imbalanced Data Using Random Forest , 2007 .

[36]  P. Gong,et al.  Efficient corn and soybean mapping with temporal extendability: A multi-year experiment using Landsat imagery , 2014 .

[37]  Gilberto Câmara,et al.  Spring: integrating remote sensing and gis by object-oriented data modelling , 1996, Comput. Graph..

[38]  Conghe Song,et al.  Radiometric correction of multi-temporal Landsat data for characterization of early successional forest patterns in western Oregon , 2006 .

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

[40]  Johannes R. Sveinsson,et al.  Random Forests for land cover classification , 2006, Pattern Recognit. Lett..

[41]  Robert H. Fraser,et al.  Signature extension through space for northern landcover classification: A comparison of radiometric correction methods , 2005 .

[42]  J. Six,et al.  Object-based crop identification using multiple vegetation indices, textural features and crop phenology , 2011 .

[43]  Irmgard Niemeyer,et al.  Object-based Change Detection , 2011 .

[44]  C. Conrad,et al.  Mapping abandoned agricultural land in Kyzyl-Orda, Kazakhstan using satellite remote sensing , 2015 .

[45]  Joanne C. White,et al.  Optical remotely sensed time series data for land cover classification: A review , 2016 .

[46]  A. Brenning,et al.  Assessing fruit-tree crop classification from Landsat-8 time series for the Maipo Valley, Chile , 2015 .

[47]  Russell G. Congalton,et al.  MODIS phenology-derived, multi-year distribution of conterminous U.S. crop types , 2017 .

[48]  L. S. Davis,et al.  An assessment of support vector machines for land cover classi(cid:142) cation , 2002 .

[49]  Hankui K. Zhang,et al.  Characterization of Landsat-7 to Landsat-8 reflective wavelength and normalized difference vegetation index continuity. , 2016, Remote sensing of environment.

[50]  Giandomenico Spezzano,et al.  An Adaptive Distributed Ensemble Approach to Mine Concept-Drifting Data Streams , 2007 .

[51]  Gregory S. Biging,et al.  Automated mapping of soybean and corn using phenology , 2016 .

[52]  Curtis E. Woodcock,et al.  Monitoring large areas for forest change using Landsat: Generalization across space, time and Landsat sensors , 2001 .

[53]  P. Atkinson,et al.  Random Forest classification of Mediterranean land cover using multi-seasonal imagery and multi-seasonal texture , 2012 .

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

[55]  Francisca López-Granados,et al.  Object- and pixel-based analysis for mapping crops and their agro-environmental associated measures using QuickBird imagery , 2009 .

[56]  Stéphane Dupuy,et al.  Mapping short-rotation plantations at regional scale using MODIS time series: Case of eucalypt plantations in Brazil , 2014 .

[57]  Clement Atzberger,et al.  Object Based Image Analysis and Data Mining applied to a remotely sensed Landsat time-series to map sugarcane over large areas , 2012 .

[58]  M. Claverie,et al.  Evaluation of the Landsat-5 TM and Landsat-7 ETM+ surface reflectance products , 2015 .

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

[60]  François Waldner,et al.  Automated annual cropland mapping using knowledge-based temporal features , 2015 .

[61]  Brian L. Markham,et al.  Landsat cross-calibration based on near simultaneous imaging of common ground targets , 2006 .

[62]  James P. Verdin,et al.  Automated Cropland Classification Algorithm (ACCA) for California Using Multi-sensor Remote Sensing , 2014 .

[63]  Conghe Song,et al.  Forest mapping with a generalized classifier and Landsat TM data , 2001 .

[64]  A. Rogers,et al.  Reducing signature variability in unmixing coastal marsh Thematic Mapper scenes using spectral indices , 2004 .

[65]  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.

[66]  Alice G. Laborte,et al.  Spectral Signature Generalization and Expansion Can Improve the Accuracy of Satellite Image Classification , 2010, PloS one.

[67]  Alfredo José Barreto Luiz,et al.  CLASSIFICAÇÃO ORIENTADA A OBJETOS EM IMAGENS MULTITEMPORAIS LANDSAT APLICADA NA IDENTIFICAÇÃO DE CANA-DE-AÇÚCAR E SOJA , 2016, Revista Brasileira de Cartografia.

[68]  C. Justice,et al.  High-Resolution Global Maps of 21st-Century Forest Cover Change , 2013, Science.

[69]  Weiqi Zhou,et al.  A new approach for land cover classification and change analysis: Integrating backdating and an object-based method , 2016 .

[70]  D. Lu,et al.  Change detection techniques , 2004 .

[71]  C. Woodcock,et al.  Making better use of accuracy data in land change studies: Estimating accuracy and area and quantifying uncertainty using stratified estimation , 2013 .

[72]  P. Varshney,et al.  Multisource Classification Using Support Vector Machines: An Empirical Comparison with Decision Tree and Neural Network Classifiers , 2008 .

[73]  Daniel Alves Aguiar,et al.  A Web Platform Development to Perform Thematic Accuracy Assessment of Sugarcane Mapping in South-Central Brazil , 2012, Remote. Sens..