Change search
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf
Classifying reservoir rock quality from thin sections of core using Convolutional Neural Networks
KTH, School of Electrical Engineering and Computer Science (EECS).
2019 (English)Independent thesis Advanced level (degree of Master (Two Years)), 20 credits / 30 HE creditsStudent thesis
Abstract [en]

In the past few years, the use of Deep Learning in the petroleum industry has increased, especially for seismic interpretation and signal processing. However its use remains shy in image analysis and carbonates classification. This study aims at applying Deep Learning on reservoir rock images and produce an image classification algorithm. The images used are thin sections of core rocks gathered while drilling exploration wells. The purpose is to classify thin sections according to their level of porosity, their Dunham and Depositional Rock Types (DRT) classification, and to be able to identify the different components they contain. These predictions will assist geologists in their labeling tasks.

The algorithm is based on Convolutional Neural Network (CNN). We tested three different CNN with different hyperparamters, optimizers as well as initialization strategies. We compared the results in order to find the best setting to achieve the task. We found that the best performing network was Inception_v3 with random initialization. The best optimizer to use depends on the class we predict on. Our best accuracy on the test set is 76,1% to identify the level of porosity, 68,4% to classify the images according to their Dunham classification and 53,7% for the DRT classification. The network also manages to identify all the components in an image with a F1-score of 50,2%. The main misclassifications are between rocks that are adjacent in the classification. This means that our algorithm struggles to differentiate similar rocks. When we compare our results to experienced geologists with carbonate classification experience, we observe that they make similar mistakes.

The results of this study show great potential for the use of Deep Learning in classification of core thin sections.

Abstract [sv]

Under de senaste åren har användningen av Deep Learning inom petroleumindustrin ökat, speciellt för seismisk tolkning och signalbehandling. Men dess användning är fortfarande ringa inom bildanalys och karbonat-klassificering. Denna studie syftar till att använda Deep Learning på reservoarstenbilder och utveckla en bildklassificeringsalgoritm. Bilder av tunna sektioner av kärnstenar som har samlats under borrning av utforskningsbrunnar används. Syftet är att klassificera tunna sektioner efter deras porositetsnivå, Dunhamoch DRTklassificering, och identifiera de olika komponenter de innehåller. Dessa förutsägelser kommer att hjälpa geologer i sina märkningsuppgifter.

Algoritmen är baserad på CNN. Tre olika CNN med olika hyperparametrar, optimeringsoch initialiseringsstrategier testades. Resultaten jämfördes för att hitta den bästa inställningen för att lösa uppgiften.

Det bästa nätverket vissade sig vara Inception_v3 med slumpmässig initialisering. Bästa optimeringsverktyget varierar beroende på vilken klass vi förutspår. Bästa noggrannhet på testuppsättningen är 76,1% för identifiering av porositetsnivå, 68,4% för klassificering av bilderna enligt deras Dunham-klassificering och 53,7% enligt DRT-klassificering. Nätverket kan också identifiera alla komponenter i en bild med en F1poäng om 50,2%. De största felklassificeringarna är mellan stenar som ligger nära varandra i klassificeringen. Algoritmens felklassificeringar liknar dem som görs av geologer med erfarenhet av karbonatklassificering. Resultaten av denna studie visar stor potential för användningen av Deep Learning i klassificering av tunna kärnstensektioner.

Place, publisher, year, edition, pages
2019. , p. 87
Series
TRITA-EECS-EX ; 2019:43
National Category
Computer and Information Sciences
Identifiers
URN: urn:nbn:se:kth:diva-249718OAI: oai:DiVA.org:kth-249718DiVA, id: diva2:1305807
Educational program
Master of Science in Engineering - Computer Science and Technology
Supervisors
Examiners
Available from: 2019-04-30 Created: 2019-04-18 Last updated: 2019-04-30Bibliographically approved

Open Access in DiVA

fulltext(7121 kB)66 downloads
File information
File name FULLTEXT01.pdfFile size 7121 kBChecksum SHA-512
d7ed348f1575355f931004ee571a37e2d29855e88367cc4fb1c3156120d0a32d46cf2ce7c522fd6142e48e77d9021b5413d54155abcf3550f5fee3b01e74819b
Type fulltextMimetype application/pdf

By organisation
School of Electrical Engineering and Computer Science (EECS)
Computer and Information Sciences

Search outside of DiVA

GoogleGoogle Scholar
Total: 66 downloads
The number of downloads is the sum of all downloads of full texts. It may include eg previous versions that are now no longer available

urn-nbn

Altmetric score

urn-nbn
Total: 115 hits
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf