Authors : Ursula Iturrarán-Viveros, Andrés Muñoz-García, Luis Fernando Duque Gómez and Martin Eduardo Espitia Nery
Abstract: We train Artificial Neural Networks (ANN) to estimate the seismic scale of the rock parameters in the lithological units of petroleum interest in Colombia. We apply instantaneous seismic attributes to a stacked P-wave reflected seismic section in the Tenerife field located in the Middle Magdalena Valley Basin (MMVB) in Colombia to estimate effective porosity (ρe), water saturation (SW), density (ρ) and volume of clay (Vclay) at seismic scale. To compute ρe, we use Raymerver equation using the standard parameters for sand formations. The water saturation (Sw) was computed using Simandoux equation for sandstones when clays do not have high cationic interchanges such as in the Tenerife field. The well-logs and the seismic attributes associated to the seismic trace closer to one of the available wells is the information used to train some multi-layered Artificial Neural Networks (ANN). We perform data analysis via the Gamma test, a mathematically non-parametric nonlinear smooth modeling tool, to choose the best input combination of seismic attributes to train an Artificial Neural Network (ANN) for estimating porosity, density, SW and volume of clay. Once the ANN’s are trained these are applied to predict these parameters along the seismic line. This is a significant result that shows for the first time a petrophysical characterization of this field at seismic scale. From the continuous estimations of volume of clay we distinguish two facies: sands and shales, these estimations confirm the production of the Mugrosa C-Sands zone and we draw brown clay that correlate with the high amplitude attributes and the yellow sand correlate with the low amplitude attributes.
Ursula Iturrarán-Viveros, Andrés Muñoz-García, Luis Fernando Duque Gómez and Martin Eduardo Espitia Nery, 2020. Petrophysical Characterization of a Clastic Oil Reservoir in the Middle Magdalena Valley Basin in Colombia using Artificial Neural Networks, Seismic Attributes, Well Logs and Rock Physics. Journal of Engineering and Applied Sciences, 15: 2728-2733.