01979nam a2200337 a 450000100080000000500110000800800410001910000210006024500910008126002270017230000120039950000250041152008600043665000280129665000180132465000110134265000090135365000210136265000080138365300290139165300220142065300260144265300330146865300090150165300250151065300280153565300150156370000230157870000170160170000230161820858902020-01-21       2017    bl uuuu     u00u1 u    #d1 aMACIEL, R. J. S.  aA neural qualitative approach for automatic territorial zoning.h[electronic resource]  aA neural qualitative approach for automatic territorial zoning. In: INTERNATIONAL CONFERENCE ON GEOCOMPUTATION, 21., 2017, Leeds. Celebrating 21 years of GeoComputation: extended abstracts. Leeds: University of Leedsc2017  ap. 1-7.  aGeoComputation 2017.  aThis article presents the application of the Self-Organizing Maps (SOM) as an exploratory tool for automatic territorial zoning by combining the handle of categorical data and the other for automatic clustering. The SOM online learning algorithm had been chosen to treat categorical data by using the dot product method and the Sorense-Dice binary similarity coefficient. To automatically perform a spatial clustering, an adaptation of the automatic clustering Costa-Netto algorithm had been also proposed. The correspondence analysis had been used to examine the profiles of each homogeneous zones. To explore the approach it has been performed the territorial zoning of the Alto Taquari River Basin, Brazil, using as input data a set of thematic maps. The results indicate the applicability of the approach to perform the exploratory territorial zoning.  aCorrespondence analysis  aThematic maps  aZoning  aMapa  aRecurso hídrico  aRio  aAlto Taquari River Basin  aAnálise espacial  aBacia do Alto Taquari  aExploratory spatial analysis  aMaps  aSelf-organizing maps  aSimilarity coefficients  aZoneamento1 aSILVA, M. A. S. da1 aMATOS, L. N.1 aDOMPIERI, M. H. G.