Fluid and Petrophysical Prediction in The Elastic Domain Using Neural Network Method

Hermana, Maman; Najmi, Muhammad; Tuan Harith, Zuhar; Sum, Chow W.
Universiti Teknologi Petronas, Tronoh, Malaysia.

Interpretation in elastic impedance domain is a new method in geophysical prospect evaluation and development in Oil & Gas industry. Inspired by the success in lithology and fluid discrimination in elastic domain, we applied Neural Network technique into elastic volume to predict fluid and petrophysical properties in the reservoir. This study consist of three phases: 1) Correlation study between Elastic Impedance log and Petrophysical Log to determine chi angle optimum, 2) AVO response and EEI projection performed to construct seismic equivalent to petrophysical properties. To convert the reflectivity of EEI into impedance domain, the colored inversion is applied. 3) The relative impedance of petrophysical volume evaluated using supervised ANN method to determined fluid and petrophysical properties. The result shows there is a good correlation between petrophysical log and EEI log: maximum coefficient correlation between porosity, water saturation and resistivity occur at 23, 25 and 32 degrees. Relative impedance domain which is obtained from colored inversion has been checked with well logs, there is good matching between seismic elastic impedance with logs. Finally, the absolute porosity, water saturation and resistivity estimated using supervised neural network. The results is consistent with petrophysical logs.

AAPG Search and Discovery Article #90155©2012 AAPG International Conference & Exhibition, Singapore, 16-19 September 2012