Unsupervised Fuzzy ARTMAP Classification of Hyperspectral Hyperion Data for Savanna and Agriculture Discrimination in the Brazilian Cerrado

The Brazilian Cerrado is threatened by agricultural land use conversion. Accurate quantification of overall and subtype Cerrado distributions is essential for regional monitoring. In this research, unsupervised fuzzy ARTMAP was compared against conventional k-means classification of Cerrado and agriculture, based on Hyperion satellite data. We systematically tested a range of fuzzy ARTMAP parameters, determining the best parameter combinations. The effect of an additional surface liquid-water input vector was also tested. Similar results were obtained when only Hyperion apparent surface reflectance data were used; fuzzy ARTMAP, however, was generally markedly more accurate than k-means when the additional surface liquid-water input was included.

[1]  Donald A. Walker,et al.  Accuracy Assessment of a Land-Cover Map of the Kuparu k River Basin, Alaska: Considerations for Remote Regions , 1998 .

[2]  B. McCune,et al.  Analysis of Ecological Communities , 2002 .

[3]  Weiguo Liu,et al.  ART-MMAP: a neural network approach to subpixel classification , 2004, IEEE Transactions on Geoscience and Remote Sensing.

[4]  F. Dell'Acqua,et al.  A comparison of fuzzy and neuro-fuzzy data fusion for flooded area mapping using SAR images , 2004 .

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

[6]  A. Waxman,et al.  Multisensor Image Fusion , Mining , and Reasoning : Rule Sets for Higher-Level AFE in a COTS Environment , 2004 .

[7]  Janet Franklin,et al.  Mapping land-cover modifications over large areas: A comparison of machine learning algorithms , 2008 .

[8]  Wendy Jepson,et al.  A disappearing biome? Reconsidering land‐cover change in the Brazilian savanna , 2005 .

[9]  Elisabetta Binaghi,et al.  Comparison of the multilayer perceptron with neuro-fuzzy techniques in the estimation of cover class mixture in remotely sensed data , 2001, IEEE Trans. Geosci. Remote. Sens..

[10]  B. Mannan,et al.  Fuzzy ARTMAP supervised classification of multi-spectral remotely-sensed images , 1998 .

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

[12]  James Williamson,et al.  A Gaussian adaptive resonance theory neural network classification algorithm applied to supervised land cover mapping using multitemporal vegetation index data , 2001, IEEE Trans. Geosci. Remote. Sens..

[13]  Jorge Luis Silva Brito,et al.  Mapeamento semidetalhado do uso da terra do Bioma Cerrado , 2008 .

[14]  Zhe Li.  Fuzzy ARTMAP Based Neurocomputational Spatial Uncertainty Measures , 2008 .

[15]  P. Gamba,et al.  Using image magnification techniques to improve classification of hyperspectral data , 2003, IGARSS 2003. 2003 IEEE International Geoscience and Remote Sensing Symposium. Proceedings (IEEE Cat. No.03CH37477).

[16]  Gail A. Carpenter,et al.  ART neural networks for remote sensing: vegetation classification from Landsat TM and terrain data , 1997, IEEE Trans. Geosci. Remote. Sens..

[17]  John R. Jensen,et al.  Fuzzy learning vector quantization for hyperspectral coastal vegetation classification , 2006 .

[18]  C. Lippitt,et al.  Mapping Selective Logging in Mixed Deciduous Forest: A Comparison of Machine Learning Algorithms , 2008 .

[19]  W. D. Ross,et al.  Change Detection using Adaptive Fuzzy neural networks : Environmental damage assessment after the Gulf War , 1999 .

[20]  L. Ferreira,et al.  Spectral linear mixture modelling approaches for land cover mapping of tropical savanna areas in Brazil , 2007 .

[21]  K. R. Clarke,et al.  Non‐parametric multivariate analyses of changes in community structure , 1993 .

[22]  J. Borak.  Feature selection and land cover classification of a MODIS-like data set for a semiarid environment , 1999 .

[23]  Jon Atli Benediktsson,et al.  Exploiting spectral and spatial information in hyperspectral urban data with high resolution , 2004, IEEE Geoscience and Remote Sensing Letters.

[24]  Weiguo Liu,et al.  Comparison of non-linear mixture models: sub-pixel classification , 2005 .

[25]  L. Ferreiraa,et al.  Seasonal landscape and spectral vegetation index dynamics in the Brazilian Cerrado : An analysis within the Large-Scale Biosphere – Atmosphere Experiment in Amazônia ( LBA ) , 2003 .

[26]  R. Ehrlich,et al.  Generation and validation of characteristic spectra from EO1 Hyperion image data for detecting the occurrence of the invasive species, Chinese tallow , 2005 .

[27]  Robert J. Marquis,et al.  The Cerrados of Brazil: Ecology and Natural History of a Neotropical Savanna , 2002 .

[28]  Anthony M. Filippi,et al.  Hyperion and CBERS satellite image classification intercomparison for Cerrado and agricultural mapping , 2007, SPIE Remote Sensing.

[29]  Alfredo Huete,et al.  Assessing the seasonal dynamics of the Brazilian Cerrado vegetation through the use of spectral vegetation indices , 2004 .

[30]  Athanasios V. Vasilakos,et al.  Comparison of computational intelligence based classification techniques for remotely sensed optical image classification , 2006, IEEE Transactions on Geoscience and Remote Sensing.

[31]  R. E. Roger.  Sparse inverse covariance matrices and efficient maximum likelihood classification of hyperspectral data , 1996 .

[32]  John Rogan,et al.  Mapping fire-induced vegetation depletion in the Peloncillo Mountains, Arizona and New Mexico , 2001 .

[33]  Paolo Gamba,et al.  Increased accuracy multiband urban classification using a neuro-fuzzy classifier , 2003 .

[34]  Christie Allan,et al.  The Cerrados of Brazil: Ecology and Natural History of a Neotropical Savanna , 2003 .

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

[36]  Simon A. Corne,et al.  Predicting forest attributes In southeast Alaska using artificial neural networks , 2004 .

[37]  C. Brannstrom,et al.  Remote classification of Cerrado (Savanna) and agricultural land covers in northeastern Brazil , 2008 .

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

[39]  Alan H. Strahler,et al.  Fuzzy Neural Network Classification of Global Land Cover from a 1° AVHRR Data Set , 1999 .

[40]  R. Goodland.  A Physiognomic Analysis of the `Cerrado' Vegetation of Central Brasil , 1971 .

[41]  Sucharita Gopal,et al.  Uncertainty and Confidence in Land Cover Classification Using a Hybrid Classifier Approach , 2004 .

[42]  Michael Georgiopoulos,et al.  Order of Search in Fuzzy ART and Fuzzy ARTMAP: Effect of the Choice Parameter , 1996, Neural Networks.

[43]  D. C. Robertson,et al.  MODTRAN cloud and multiple scattering upgrades with application to AVIRIS , 1998 .

[44]  Julius T. Tou,et al.  Pattern Recognition Principles , 1974 .

[45]  Gail A. Carpenter,et al.  A Neural Network Method for Mixture Estimation for Vegetation Mapping , 1999 .

[46]  Luciano Vieira Dutra,et al.  Feature extraction and selection for ERS-1/2 InSAR classification , 1999 .

[47]  Leopoldo Magno Coutinho,et al.  O conceito do cerrado , 1978 .

[48]  J. F. Ribeiro,et al.  Fitofisionomias do bioma cerrado. , 1998 .

[49]  A. Huete,et al.  Optical characterization of the Brazilian Savanna physiognomies for improved land cover monitoring of the cerrado biome: preliminary assessments from an airborne campaign over an LBA core site , 2004 .

[50]  Stephen Grossberg,et al.  Fuzzy ARTMAP: A neural network architecture for incremental supervised learning of analog multidimensional maps , 1992, IEEE Trans. Neural Networks.

[51]  F. G.,et al.  DISCRIMINATION AND BIOPHYSICAL CHARACTERIZATION OF CERRADO PHYSIOGNOMIES WITH EO-1 HYPERSPECTRAL HYPERION , 2003 .

[52]  Alfredo Huete,et al.  Discrimination And Biophysical Characterization Of Brazilian Cerrado Physiognomies With Eo-1 Hyperspectral Hyperion , 2004 .