About This Item
- Full TextFull Text(subscription required)
- Pay-Per-View PurchasePay-Per-View
Purchase Options Explain
Share This Item
The AAPG/Datapages Combined Publications Database
West Texas Geological Society
Abstract
Probabilistic Neural Network Used to Predict Porosity from 3-D Seismic Attributes in Lower Brushy Canyon Formation, southeast New Mexico
Abstract
The lower Brushy Canyon Formation of the Delaware Basin consists of a series of vertically stacked, sand-filled channel complexes interbedded with organic siltstones and carbonates. This complex stratigraphic framework creates the need for precise inter-well estimation of reservoir properties. Wireline log and 3-D seismic reflection data were integrated to predict porosity in the area of an existing oil field in southeast New Mexico. The lower Brushy Canyon and Bone Spring seismic horizons were used to constrain a time window for a volume-based seismic attribute analysis. Seven attributes were extracted from the seismic data and combined to predict porosity using standard linear regression. A probabilistic neural network (PNN) was then trained to look for a non-linear relationship between porosity and the seismic attributes. The results were statistically good, correlation coefficient (r) = 0.82, but more importantly, the porosity maps generated from the PNN model conformed to the known geology.
Pay-Per-View Purchase Options
The article is available through a document delivery service. Explain these Purchase Options.
| Watermarked PDF Document: $16 | |
| Open PDF Document: $28 |