Prediction of formation damage during fluid injection into fractured, low permeability reservoirs via neural networks

M. Nikravesh*, A. R. Kovscek, R. M. Johnston, T. W. Patzek

*Corresponding author for this work

Research output: Contribution to conferencePaperpeer-review

16 Scopus citations

Abstract

Neural network models can be used to predict the dynamics of low permeability, fractured reservoirs undergoing fluid injection. One such model was developed using data from a waterflood project in the South Belridge Diatomite (Kern County, California) to predict wellhead pressure as a function of injection rate, and vice versa. Neural networks were also created using data from a dual injector steamdrive pilot in the same field to correlate injection pressures and rates and temperature responses in seven observation wells.

Original languageEnglish (US)
Pages351-365
Number of pages15
DOIs
StatePublished - Jan 1 1996
EventProceedings of the 1996 International Symposium on Formation Damage Control - Lafayette, LA, USA
Duration: Feb 14 1996Feb 15 1996

Other

OtherProceedings of the 1996 International Symposium on Formation Damage Control
CityLafayette, LA, USA
Period02/14/9602/15/96

ASJC Scopus subject areas

  • Energy Engineering and Power Technology
  • Geotechnical Engineering and Engineering Geology

Fingerprint Dive into the research topics of 'Prediction of formation damage during fluid injection into fractured, low permeability reservoirs via neural networks'. Together they form a unique fingerprint.

Cite this