Comparison of linear regression and a probabilistic neural network to predict porosity from 3-D seismic attributes in Lower Brushy Canyon channeled sandstones, southeast New Mexico

The Lower Brushy Canyon Formation of the Delaware Basin, New Mexico, consis ts of a series of overlying sand-filled channels and associated fans separa ted by laterally extensive organic siltstone and carbonate interbeds. This laterally and vertically complex geology creates the need for precise inter well estimation of reservoir properties. In this paper we integrate wireline log and 3-D seismic data to directly pr edict porosity in the area of an existing oil field in southeast New Mexico . The 3-D seismic data were used to interpret the location of major stratig raphic markers between wells, and these seismic horizons were used to const rain a time window for a volume-based attribute analysis. Stepwise regressi on and crossvalidation were used to combine seismic attributes to predict p orosity in wells where the porosity was known from the well logs. The resul ts of a linear regression porosity model showed good correlation (r(2) = 0. 74) between seven seismic attributes and the observed porosity logs at 11 w ells in the study area, but the porosity volume created from the regression model did not display the known geologic features. A probabilistic neural network was then trained to look for a nonlinear relationship between the i nput data (the seven attributes) and the observed porosity at the 11 wells. The correlation was better (r(2) = 0.82), but the biggest improvement over the linear regression model came in the more geologically realistic predic ted porosity distribution.