A Self-Organizing Map (SOM) was designed with the aim of integrating and searching for patterns in airborne geological and geophysical gammaspectrometric and magnetic data of the Serra Leste region, Carajás Mineral Province. SOM is an unsupervised Artificial Neural Network method that performs a non-linear mapping from a high-dimensional data space to a 2-dimensional grid, whereas preserving the topological relations in the original data. The SOM grid can be efficiently used in an integrated visualization and understanding of the internal relationships in the data. The K-means algorithm is applied to the SOM grid to reduce the number of mapped patterns so as to facilitate interpretation. Unfolding of the clustered SOM grid associates each mapped pattern with the spatial position of each data point. The SOM reclassified map was compared with a classified map obtained with the Fuzzy C-means method for the same input data and with the same number of classes. The results show the potentiality of SOM in producing higher quality integrated maps to support mineral exploration. © 2010 Sociedade Brasileira de Geofísica.283397409Bezdek, J.C., (1981) Pattern Recognition with fuzzy objective function algorithms, p. 256. , Kluwer Academic Publishers, NorwellBriggs, I.C., Machine contouring using minimum curvature (1974) Geophysics, 39, pp. 39-48Cabral, A.R., Lehmann, B., Kwitko, R., Cravo, C.H.C., The Serra Pelada Au-Pd-Pt deposit, Carajás Mineral Province, northern Brazilreconnaissance mineralogy and chemistry of very high grade palladian gold mineralization (2002) Econ. Geol., 97, pp. 1127-1138Cabral, A.R., Lehmann, B., Kwitko, R., Cravo, C.H.C., Palladium and platinum minerals from the Serra Pelada Au-Pd-Pt deposit, Carajás Mineral Province, Northern Brazil (2002) Can. Mineral, 40, pp. 1451-1463Cios, K.J., Pedrycz, W., Swiniarsk, R.M., (1998) Data Mining Methods for Knowledge Discovery, p. 495. , Kluwer Academic Publishers, NorwellCoelho, C.E.S., Rodrigues, O.B., Jazida de manganês do azul, Serra dos Carajás, Pará (1986) Principais depósitos minerais do Brasil, 2, pp. 145-152. , In: SCHOBBENHAUS C & COELHO CES (Eds.), DNPM/CVRDDavies, D., Bouldin, D., A Cluster Separation Measure (1979) IEEE Trans. Pattern Anal. Mach. Intell., 1 (2), pp. 224-227Demicco, R.V., Klir, G.J., (2003) Fuzzy Logic in Geology, p. 347. , Elsevier Science Academic Press, San DiegoRevisão litoestratigr áfica da Província Mineral de Carajás - litoestratigrafia e principais depósitos minerais (1988) Congresso Brasileiro de Geologia, pp. 11-54. , DOCEGEO. Rio Doce Geologia e Mineração S.A., In:, 35., Belém: SBG, Anexo aos AnaisInternational geomagnetic reference field, 1995, revision (1996) Geophys. J. Int., 125, pp. 318-321. , IAGA DIVISION 5, WORKING GROUP 8Klose, C.D., Self-Organizing Maps for Geoscientific Data Analysis: Geological Interpretation of Multidimensional Geophysical Data (2006) Comput. Geosci., 10, pp. 265-277Kohonen, T., (2001) Self-Organizing Map, p. 113. , 3 ed., Springer-Verlag, BerlinLeite, E.P., Souza Filho, C.R., Probabilistic neural networks applied to mineral potential mapping for platinum-group elements in the Serra Leste region, Carajás Mineral Province, Brazil (2009) Comput. Geosci. (UK), 35, pp. 675-689Leite, E.P., Souza Filho, C.R., Artificial neural networks applied to mineral potential mapping for copper-gold mineralizations in the Carajás Mineral Province (2009) Geophys. Prospect., 57 (6), pp. 1049-1065Mansour, Z., Ali, P., Mahdi, Z., A computational optimized extended model for mineral potential mapping based on WofE method (2009) Am. J. Applied Sci., 6 (2), pp. 200-203Marschik, R., Mathur, R., Ruiz, J., Leveille, R.A., Almeida, A.J.D.E., Late Archean Cu-Au-Mo mineralization at Gameleira and Serra Verde, Carajás Mineral Province, Brazil: Constraints from Re-Os molybdenite ages (2005) Miner. Deposita, 39, pp. 983-991Penn, S.B., Using self-organizing maps, histograms, and standard deviation to detect anomalies in hyperspectral imagery data (2002) Proceedings of the Fifth International Airborne Remote Sensing Conference, pp. 22-24. , In:, Miami, FloridaPenn, S.B., Using self-organizing maps to visualize highdimensional data (2004) Comput. Geosci. (UK), 31 (5), pp. 531-544Roest, W.R., Verhoef, J., Pilkington, M., Magnetic interpretation using the 3-D analytical signal (1992) Geophysics, 57, pp. 116-125Saveliev, A.A., Dobrinin, D.V., Hierarchical multispectral image classification based on self organized maps (1999) IEEE 1999 International Geoscience and Remote Sensing Symposium. IGARSS'99, 5, pp. 2510-2512. , In:, Piscataway, NJSeber, G.A.F., (2004) Multivariate observations, p. 686. , 2 ed., John Wiley & Sons, Inc., Hoboken, NJSouza Filho, C.R., Nunes, A.R., Leite, E.P., Monteiro, L.V.S., Xavier, R.P., Spatial analysis of airborne geophysical data applied to geological mapping and mineral prospecting in the Serra Leste region, Carajás Mineral Province, Brazil (2007) Surv. Geophys., 28, pp. 377-405Suita, M.T.F., (1988) Geologia da área Luanga com ênfase na petrologia do complexo básico-ultrabásico Luanga e depósitos de cromita associados, Pará, p. 83. , Dissertação de Mestrado, Brasília, UnBUltsch, A., Knowledge acquisition with self-organizing neural networks (1992) Artificial Neural Networks, pp. 735-740. , In: ALEKSANDER I & TAYLOR J (Eds.), Elsevier Science Publishers, B.VUltsch, A., U*-matrix: A tool to visualize clusters in high dimensional data (1993) Technical Report, 36, p. 12. , University of Marburg, Department of Computer ScienceVeneziani, P., Okida, R., (2001) Mapeamento geológico-estrutural da região do Projeto Platina (Serra Pelada) baseado em dados integrados RADARSAT-TM e aerogeofísica, p. 52. , Relatório TécnicoVesanto, J., Himberg, J., Alhoniemi, E., Parhankangas, J., SOM Toolbox for Matlab 5 (2000) Technical Report, A57, p. 59. , Helsinki University of TechnologyVillas, R.N., Santos, M.D., Gold deposits of the Carajá's Mineral Province: Deposit types and metallogenesis (2001) Miner. Deposita, 36, pp. 300-331