Comparison of Machine Learning Algorithms for Mapping the Phytophysiognomies of the Brazilian Cerrado

This present work describes the classification of the Phytophysiognomies present in the Brazilian Cerrado biome through the means Artificial Intelligence; data from remote sensing images and other sources served as input for these algorithms to generate the vegetation maps. The data acquired was of many types so that it fully described the various Phytophysiognomies present in biome and served as training data for the machine learning algorithms. Various statistical and neuro-computation based algorithms were used for pattern recognition in the data so that we could build a good generalization model for the biome. A vegetation map was successfully generated with each algorithm. Finally a comparison among these algorithms was made so that we could find the best algorithm that fitted the problem of mapping this biome.

[1]  Stephen Grossberg,et al.  ARTMAP: supervised real-time learning and classification of nonstationary data by a self-organizing neural network , 1991, [1991 Proceedings] IEEE Conference on Neural Networks for Ocean Engineering.

[2]  J. R. Landis,et al.  The measurement of observer agreement for categorical data. , 1977, Biometrics.

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

[4]  Eric P. Crist,et al.  A Physically-Based Transformation of Thematic Mapper Data---The TM Tasseled Cap , 1984, IEEE Transactions on Geoscience and Remote Sensing.

[5]  M. Molenaar.  An Introduction To The Theory Of Spatial Object Modelling For GIS , 1998 .

[6]  Graeme G. Wilkinson,et al.  Open Questions in Neurocomputing for Earth Observation , 1997 .

[7]  Fabio Roli,et al.  Neurocomputation in Remote Sensing Data Analysis , 1997, Springer Berlin Heidelberg.

[8]  J.A. Anderson,et al.  Neural Network Models for Pattern Recognition and Associative Memory , 2002 .

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

[10]  Teuvo Kohonen,et al.  The self-organizing map , 1990, Neurocomputing.

[11]  Gail A. Carpenter,et al.  Neural network models for pattern recognition and associative memory , 1989, Neural Networks.

[12]  B. S. Daya Sagar.  Computer processing of remotely sensed images: an introduction. 2nd Edition: Paul M. Mather. Wiley, Chichester, 1999, 292pp., US$ 65.00 (Includes CD with image processing software for Windows), ISBN 0-471-98550-3. , 2001 .

[13]  L. M. T. de Carvalho.  Mapping and monitoring forest remnants: a multiscale analysis of spatio-temporal data , 2001 .

[14]  George Alan Blackburn,et al.  Introducing New Indices for Accuracy Evaluation of Classified Images Representing Semi-Natural Woodland Environments. , 2001 .

[15]  L. T. Oliveira,et al.  Mineração de dados geográficos para mapear as fitofisionomias do bioma cerrado , 2005 .

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

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

[18]  Russell G. Congalton,et al.  Assessing the accuracy of remotely sensed data : principles and practices , 1998 .