GNGTS 2015 - Atti del 34° Convegno Nazionale

GNGTS 2015 S essione 3.1 19 other global search algorithms) circumvents this drawback by performing a wide and efficient exploration of the entire model space in a single inversion. Moreover, the main advantage of GA and SR over NN is that they directly provide simple equations characterized by easily interpretable rock-physical meanings. The blind test demonstrated that the high correlation coefficients associated to the NN approach are likely related to the well-known overfitting problem. The blind test ���� also demonstrated that the TRPM approach, thanks to its general validity, often ensures a higher prediction capability than the empirical, data-driven, approaches. This high prediction capability and the general validity are the main advantages of theoretical rock physics models with respect to the empirical methods. The prediction capability of theoretical rock physics models has been demonstrated worldwide and it is discussed in several papers (e.g. Avseth et al. 2005). However, such prediction capability is high in case of sedimentary basins formed by alternating shales-sand sequences subjected to hydrostatic pressure and mechanical compaction regime. In more complex geologic scenarios (fractured rocks, non-clastic rocks, overpressured rocks and chemical compaction regimes), the theoretical rock-physics models become very complex and their prediction capability decreases. In these cases, empirical, data-driven, approaches could be the only chance to obtain a reliable rock-physics model applicable for reservoir characterization. The previous considerations enable us to consider the rock-physics models derived by the SR and by the TRPM approaches in the following petrophysical-seismic inversion discussed in the companion paper “ Seismic reservoir characterization in offshore Nile Delta. Part II: Probabilistic petrophysical-seismic inversion”. Acknowledgments. The authors wish to thank EDISON E&P for making the well log data available and for the permission to publish this work. References Aleardi, M.; 2015: Seismic velocity estimation from well log data with genetic algorithms in comparison to neural networks and multilinear approaches . Journal of Applied Geophysics, 117, 13-22. Avseth, P., Mukerji, T. and Mavko, G.; 2005: Quantitative seismic interpretation: Applying rock physics tools to reduce interpretation risk . Cambridge University Press. Bachrach, R.; 2006: Joint estimation of porosity and saturation using stochastic rock-physics modeling . ����������� Geophysics, 71(5), O53-O63. Banchs, R., Jiménez, J. and Del Pino, E.; 2001: Nonlinear estimation of missing logs from existing well log data . 2001 SEG Annual Meeting. Society of Exploration Geophysicists, pp. 598–600. Bosch, M., Mukerji, T. and Gonzalez, E.F.; 2010: Seismic inversion for reservoir properties combining statistical rock physics and geostatistics: A review . Geophysics, 75(5), 75A165-75A176. Draper, N.R. and Smith, H.; 1985: Applied Regression Analysis . 2nd ed. JohnWiley & Sons Inc. Eberhart-Phillips, D., Han, D. H. and Zoback, M.D.; 1989: Empirical relationships among seismic velocity, effective pressure, porosity, and clay content in sandstone . Geophysics, 54(1), 82-89. Grana, D. and Della Rossa, E.; 2010: Probabilistic petrophysical-properties estimation integrating statistical rock physics with seismic inversion . Geophysics, 75(3), O21-O37. Haykin, S.; 1999: Self-organizing maps. Neural Networks—A Comprehensive Foundation . Prentice-Hall. Holland, J.H.; 1975: Adaptation in Natural and Artificial Systems . University of Michigan Press. Mazzotti, A. and Zamboni, E.; 2003; Petrophysical inversion of AVA data . Geophysical Prospecting, 51(6), 517-530. Mavko, G., Mukerji, T. and Dvorkin, J.; 2009: The rock physics handbook: Tools for seismic analysis of porous media . Cambridge university press. Mitchell, M.; 1996: An Introduction to Genetic Algorithms . MIT Press. Saggaf, M., Toksöz N., and Mustafa H.M.; 2003: Estimation of reservoir properties from seismic data by smooth neural networks . Geophysics, 68, 1969–1983. Van der Baan M., and Jutten, C.; 2000: Neural networks in geophysical applications . Geophysics 65 (4), 1032– 1047.