Predicting well-stimulation results in a gas-storage field in the absence of reservoir data with neural networks. S. Mohaghegh et al. SPE Reservoir Engng., November 1996, 11(4), 268--272.
Methodology is presented that is capable of forecasting the post fracture deliverability on the basis of historical data in Clinton sandstone gas-storage field without detailed reservoir data. Post fracture well deliverability was predicted with approximately 95% accuracy. The neural network developed in this study is in current usage for selection of candidate wells for the hydraulic fracturing in the Clinton sandstone. 9 refs.
- Journal title: SPE Reservoir Engineering
- Computer applications -