الفهرس Only 14 pages are availabe for public view
 |  | from | 154 |  |  |
| | | from | 154 | | |
Abstract
De-risking hydrocarbon exploration and development by predicting of some reservoir parameters away from the wells are essential to characterize reservoirs effectively. Our developed workflows are predicting gas volume probability cube and lithology classification to gas-sand, by using probabilistic neural network. The supervised classification multi-layer perceptron neural network also used, to generate reservoir and chimney probability cubes. We demonstrate these developed workflows on a 3D seismic volume from the West Delta Deep Marine Concession over the study area, by using four wells. Our results shows reasonable power of integrated the resulting probability volumes to come up with a possibility of prospect presence and effectiveness