This paper presents a probabilistic unsupervised neural method in order to construct the lithofacies of the wells HM2 and HM3 situated in the south of Algeria (Sahara). Our objective is to facilitate the experts' work in geological domain and to allow them to obtain the structure and the nature of lands around the drilling quickly. For this, we propose the use of the Self-Organized Map (SOM) of Kohonen. We introduce a set of labeled log’s data in some points of the hole. Once the obtained map is the best deployed one (the neuronal network is well adapted to the data of the wells), a probabilistic formalism is introduced to enhance the classification process. Our system provides a lithofacies of the concerned hole in an aspect easy to read by a geology expert who identifies the potential for oil production at a given source and so forms the basis for estimating the financial returns and economic benefits. The obtained results show that the approach is robust and effective.

[1] Adegbenga O. E., “High Resolution Sequence Stratigraphic and Reservoir Characterization Studies of D-07, D-08 and E-01 Sands, Block 2 Meren Field, Offshore Niger Delta,” in Proceedings of the American Association of Petroleum Geologists (AAPG) Conference and Exhibition, Barcelona, Spain, September 2003.

[2] Aider H., “Contribution des Diagraphies Différées à L’évaluation de Paramètres des Réservoirs,” Second Scientific and Technical Days of the Sonatrach, Algiers, pp 115-130, April 1996.

[3] Aliev M., Ait Laoussine N., Avrov V., Aleksine G., Barouline G., Lakov-lev B., Korj M., Kouvykine J., Makarov V., Mazanov V., Medvedev E., Mkrtchiane O., Moustafinov R., Oriev L., Oroudjeva D., Oulmi M., and Said A., “Structures Géologiques et Perspectives en Pétrole et en Gaz du Sahara Algérien,” Sonatrach Editions, Algiers, 1971.

[4] Aminzadeh F., “Challenging Problems in the Oil Industry and Applications of AI and Soft Computing,” in Proceedings of the International Joint Conference on Artificial Intelligence (IJCAI), Mexico, August 2003. Using Probabilistic Unsupervised Neural Method for Lithofacies Identification 65

[5] Anouar F., “Modélisation Probabiliste des Cartes Auto-Organisées: Application en Classification et en Régression,” PhD Thesis, National Conservatory of Arts and Professions, CNAM, Paris V, 1996.

[6] Baddari K. and Nikitin A. A., “Statistical Processing of Geophysical Data,” The Second Scientific and Technical Days of the Sonatrach, Algiers, pp 205-220, April 1996.

[7] Barbaroux J. M., Germinet F., and Tcheremchantsev S., “Generalized Fractal Dimensions: Equivalences and Basic Properties,” Journal de Mathématiques Pures et Appliquées, September 2000.

[8] Blume M. and Esener S. C., “An Efficient Mapping of Fuzzy Art onto a Neural Architecture,” Reaserch Report, University of California at San Diego, La Jolla, CA, 1997.

[9] Bougrain L. and Alexandre F., “Unsupervised Connectionist Algorithms for Clustering an Environmental Data Set: A Comparison,” Neurocomputing, vol. 28, pp. 177-189, 1999.

[10] Chikhi S. and Shout H., “Using Probabilistic Neural Networks to Construct Well Facies,” WSEAS Transactions on Systems, vol. 2, no. 4, pp. 839-843, October 2003.

[11] Claude C. S., “Practical Analysis for Reservoir Uncertainty,” in Proceedings of the AAPG Conference and Exhibition, Barcelona, Spain, September 2003.

[12] Derguini K., “Applications Sédimentologiques des Diagraphies,” The Algerian Geology Journal, pp.1-29, September 1995.

[13] Dreyfus G., Martinez J. M., Samuelides M., Gordon M. B., Badran F., Thiria S., and Hérault L., “Réseaux de Neurones. Méthodologie et Applications,” Eyrolles Editions, Paris, 2002

[14] Durand M. D. and White S. R., “Trading Accuracy for Speed in Parallel Simulated Annealing with Simultaneous Moves,” Parallel Computing, vol. 26, no. 1, pp 135-150, January 2000

[15] Frayssinet D., “Utilisation des Réseaux de Neurones en Traitement des Données de Diagraphies: Prédiction et Reconstitution de Faciès Lithologiques,” Master Thesis, National Conservatory of Arts and Professions, Paris, 2000.

[16] Gedeon T. D., Kuo H., and Wong P. M., “Rule Extraction Using Fuzzy Clustering for a Sedimentary Rock Data Set,” International Journal of Fuzzy Systems, vol. 4, no. 1, pp. 600- 605, March 2002.

[17] Gottlib-Zeh S., Briqueu L., and Veillerette A., “Indexed Self-Organization Map: A New Calibration System for a Geological Interpretation of Logs,” in Proceedings of the IAMG'99, VI, Lippard, Naess and Sinding- Larsen, Editons Norway, pp. 183-188, 1999.

[18] Jerry F. L., “Applying Sequence Stratigraphic Methods to Constructing Petrophysical Models,” in Proceedings of the AAPG Conference and Exhibition, Barcelona, Spain, September 2003.

[19] Kohonen T., “Self Organization and Associative Memory,” Springer Series in Information Sciences, Sprinter Verlag, Berlin, vol. 8, 1988.

[20] Platon E., Gary A., and Glenn J., “Pattern Matching in Facies Analysis from Well Log Data: A Hybrid Neural Network-Based Application,” in Proceedings of the AAPG Conference and Exhibition, Barcelona, Spain, September 2003.

[21] Rabaute A., “Obtenir une Représentation en Continu de La Lithologie et de La Minéralogie: Exemples d'Applications du Traitement Statistique de Données de Diagraphie Aux Structures Sédimentaires en Régime de Convergence de Plaques,” PhD Thesis, Montpellier II University, 1999.

[22] Tamhane D., Wong P. M., and Aminzadeh F., “Integrating Linguistic Descriptions and Digital Signals in Petroleum Reservoirs,” International Journal of Fuzzy Systems, vol. 4, no. 1, pp 586- 591, March 2002.

[23] Thiria S., Lechevallier Y., Gascuel O., and Canu S., “Statistiques et Méthodes Neuronales,” Dunod Editions, Paris, 1997.

[24] Wong K. W., “A Neural Fuzzy Approach for Well Log and Hydrocyclone Data Interpretation,” PhD Thesis, Curtin University of Technology, December 1999.

[25] Yang H., Chen H. C., and Fang J. H., “Determination of Carbonate Lithofacies Using Hierarchical Neural Networks,” in Proceedings of the Artificial Neural Networks in Engineering Conference (ANNIE`96), Missouri, USA, pp. 481-486, 1996.

[26] Yong H.T. and Marzuki K., “Comparison of Fuzzy Artmap and MLP Neural Networks for Hand Written Character Recognition,” Symposium on Artificial Intelligence in Real Time Control (AIRTC`97), pp. 363-371, 1997. Salim Chikhi is a PhD student in computer science. He received his MSc degree in computer systems from the University of Constantine, Algeria, in collaboration with Glasgow University, UK. Very soon he is going to defend his PhD thesis. His research interests include neural networks, hybrid systems and soft computing application in petroleum reservoir modeling. 66 The International Arab Journal of Information Technology, Vol. 2, No. 1, January 2005 Mohamed Batouche received his MSc and PhD degrees in computer science from the Institut National Polytechnique de Lorraine, Nancy, France in 1989 and 1993, respectively. Currently, he is a full professor at the University of Constantine, Algeria. His research areas include artificial intelligence and pattern recognition.