A deep neural network for lithological facies classification: A case studyof the mid-cretaceous reservoir from the giant oil field, Iraq

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

Facies classification is a significant for characterization and evaluation of the reservoir due to the distribution of facies has important impact on optimum reservoir modelling which leads to the highest economy. Facies classification using other data (wells or outcrops) cannot capture all reservoir characterization in inter-well region due to the restricted coverage, and therefore as an alternative approaches, seismic facies classification schemes have to be applied to reduce the uncertainties in reservoir model. In this research, a machine learning neural network was introduced to predict the lithology which required to building a full field earth model for carbonate reservoir in Sothern Iraq. In the present research, probabilistic neural network (PNN) and deep forward neural network (DFNN) were undertaken to classify facies and its distribution. The well log that was used for litho-facies classification is porosity log. Finally, the spatial distribution of litho-facies was validated carefully using core data. Once successfully trained, final results show that PNN technique classified the carbonate reservoir into four facies, while the DFNN presented five facies. The final results on blind well, show that DFNN technique has the best performance on facies predication. These observations implied this reservoir consists of a wide range of lithology and porotype fluctuations due to the impact of depositional environment. The work and the methodology provide a significant improvement of the Mishrif litho-facies classification and revealed the capability of the deep learning neural network technique when tested against the probabilistic neural network. Therefore, it proved to be very successful as developed for facies modeling in carbonate rock types in the Middle East and similar heterogeneous carbonate reservoirs.

Original languageEnglish
Title of host publicationSPE Gas and Oil Technology Showcase and Conference 2019
PublisherSociety of Petroleum Engineers
ISBN (Print)9781613997048
DOIs
Publication statusPublished - Oct 2019
EventSPE Gas and Oil Technology Showcase and Conference 2019 - Dubai, United Arab Emirates
Duration: 21 Oct 201923 Oct 2019

Conference

ConferenceSPE Gas and Oil Technology Showcase and Conference 2019
Abbreviated titleGOTS 2019
CountryUnited Arab Emirates
CityDubai
Period21/10/1923/10/19

ASJC Scopus subject areas

  • Fuel Technology
  • Energy Engineering and Power Technology

Fingerprint Dive into the research topics of 'A deep neural network for lithological facies classification: A case studyof the mid-cretaceous reservoir from the giant oil field, Iraq'. Together they form a unique fingerprint.

  • Cite this