Deep Learning for Prediction of Complex Geology Ahead of Drilling

Kristian Fossum, Sergey Alyaev, Jan Tveranger, Ahmed Elsheikh

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

Abstract

During a geosteering operation the well path is intentionally adjusted in response to the new data acquired while drilling. To achieve consistent high-quality decisions, especially when drilling in complex environments, decision support systems can help cope with high volumes of data and interpretation complexities. They can assimilate the real-time measurements into a probabilistic earth model and use the updated model for decision recommendations. Recently, machine learning (ML) techniques have enabled a wide range of methods that redistribute computational cost from on-line to off-line calculations. In this paper, we introduce two ML techniques into the geosteering decision support framework. Firstly, a complex earth model representation is generated using a Generative Adversarial Network (GAN). Secondly, a commercial extra-deep electromagnetic simulator is represented using a Forward Deep Neural Network (FDNN). The numerical experiments demonstrate that the combination of the GAN and the FDNN in an ensemble randomized maximum likelihood data assimilation scheme provides real-time estimates of complex geological uncertainty. This yields reduction of geological uncertainty ahead of the drill-bit from the measurements gathered behind and around the well bore.

Original languageEnglish
Title of host publicationComputational Science. ICCS 2021
PublisherSpringer
Pages466-479
Number of pages14
ISBN (Electronic)9783030779641
ISBN (Print)9783030779634
DOIs
Publication statusPublished - 9 Jun 2021
Event21st International Conference on Computational Science 2021 - Virtual, Online
Duration: 16 Jun 202118 Jun 2021

Publication series

NameLecture Notes in Computer Science
Volume12743
ISSN (Print)0302-9743
ISSN (Electronic)1611-3349

Conference

Conference21st International Conference on Computational Science 2021
Abbreviated titleICCS 2021
CityVirtual, Online
Period16/06/2118/06/21

Keywords

  • Deep neural network
  • Ensemble randomized maximum likelihood
  • Generative Adversarial Network
  • Geosteering
  • Machine learning

ASJC Scopus subject areas

  • Theoretical Computer Science
  • Computer Science(all)

Fingerprint

Dive into the research topics of 'Deep Learning for Prediction of Complex Geology Ahead of Drilling'. Together they form a unique fingerprint.

Cite this