Jove
Visualize
Contact Us
JoVE
x logofacebook logolinkedin logoyoutube logo
ABOUT JoVE
OverviewLeadershipBlogJoVE Help Center
AUTHORS
Publishing ProcessEditorial BoardScope & PoliciesPeer ReviewFAQSubmit
LIBRARIANS
TestimonialsSubscriptionsAccessResourcesLibrary Advisory BoardFAQ
RESEARCH
JoVE JournalMethods CollectionsJoVE Encyclopedia of ExperimentsArchive
EDUCATION
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab ManualFaculty Resource CenterFaculty Site
Terms & Conditions of Use
Privacy Policy
Policies

Related Concept Videos

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by
Same author

Vertical Superior Epigastric Artery Perforator Flap for Autologous Breast Augmentation After Massive Weight Loss.

Plastic and reconstructive surgery·2026
Same author

Digital Cognitive Twins in mental health.

Nature. Mental health·2026
Same author

Assessing PRISM context domains and RE-AIM outcomes: data from use of the iterative PRISM webtool.

Implementation science communications·2026
Same author

Social determinants of health and temporospatial trends associated with Giardia duodenalis infection in Texas canines.

Scientific reports·2026
Same author

Mechanical and Bond Performance of Alkali-Activated Slag Concrete Incorporating Natural and Recycled Diatoms.

Materials (Basel, Switzerland)·2026
Same author

From Evaluation to Elevation: Standardized Letter of Evaluation Domains Tied to Future Emergency Medicine Chief Residents.

The western journal of emergency medicine·2026

Related Experiment Video

Updated: Oct 17, 2025

Data Processing Methods for 3D Seismic Imaging of Subsurface Volcanoes: Applications to the Tarim Flood Basalt
07:58

Data Processing Methods for 3D Seismic Imaging of Subsurface Volcanoes: Applications to the Tarim Flood Basalt

Published on: August 7, 2017

9.5K

Unsupervised Machine Learning Applied to Seismic Interpretation: Towards an Unsupervised Automated Interpretation

Alimed Celecia1, Karla Figueiredo2, Carlos Rodriguez3

  • 1Electrical Engineering Department, PUC-Rio, Rio de Janeiro 22451-900, Brazil.

Sensors (Basel, Switzerland)
|October 13, 2021
PubMed
Summary

Unsupervised machine learning models offer a novel approach to seismic interpretation for hydrocarbon exploration by identifying geological patterns without human bias. This study successfully correlated machine learning-derived seismic facies with well log data, improving exploration accuracy.

Keywords:
image segmentationseismic interpretationunsupervised machine learningwell logs clustering

More Related Videos

Author Spotlight: Efficient Image Recognition Using Directional Gradient Histogram Technique and Support Vector Machines
08:27

Author Spotlight: Efficient Image Recognition Using Directional Gradient Histogram Technique and Support Vector Machines

Published on: January 5, 2024

1.3K
Pore-scale Imaging and Characterization of Hydrocarbon Reservoir Rock Wettability at Subsurface Conditions Using X-ray Microtomography
12:18

Pore-scale Imaging and Characterization of Hydrocarbon Reservoir Rock Wettability at Subsurface Conditions Using X-ray Microtomography

Published on: October 21, 2018

14.3K

Related Experiment Videos

Last Updated: Oct 17, 2025

Data Processing Methods for 3D Seismic Imaging of Subsurface Volcanoes: Applications to the Tarim Flood Basalt
07:58

Data Processing Methods for 3D Seismic Imaging of Subsurface Volcanoes: Applications to the Tarim Flood Basalt

Published on: August 7, 2017

9.5K
Author Spotlight: Efficient Image Recognition Using Directional Gradient Histogram Technique and Support Vector Machines
08:27

Author Spotlight: Efficient Image Recognition Using Directional Gradient Histogram Technique and Support Vector Machines

Published on: January 5, 2024

1.3K
Pore-scale Imaging and Characterization of Hydrocarbon Reservoir Rock Wettability at Subsurface Conditions Using X-ray Microtomography
12:18

Pore-scale Imaging and Characterization of Hydrocarbon Reservoir Rock Wettability at Subsurface Conditions Using X-ray Microtomography

Published on: October 21, 2018

14.3K

Area of Science:

  • Geophysics
  • Machine Learning
  • Petroleum Geoscience

Background:

  • Seismic interpretation is crucial for hydrocarbon exploration but faces challenges like data volume, complexity, and human bias.
  • Unsupervised machine learning (ML) presents a potential solution by uncovering hidden patterns in seismic data without requiring labeled examples.
  • Automating seismic interpretation can reduce time consumption and uncertainty inherent in expert-driven analysis.

Purpose of the Study:

  • To explore and evaluate unsupervised ML methodologies for seismic data interpretation.
  • To compare classical clustering and image segmentation techniques for seismic facies analysis.
  • To integrate seismic interpretation with well log data for enhanced lithological information.

Main Methods:

  • Applied unsupervised learning algorithms, including clustering and image segmentation.
  • Utilized feature selection to optimize the input data for ML models.
  • Correlated unsupervised ML-generated seismic groups with well log data groups from the same geological area.

Main Results:

  • Identified and evaluated multiple unsupervised ML strategies for seismic interpretation.
  • The proposed methods successfully grouped seismic data based on underlying patterns.
  • Resultant seismic groups accurately represented main seismic facies and correlated well with well log data groups.

Conclusions:

  • Unsupervised machine learning provides an effective, bias-free approach to seismic interpretation.
  • The integration of seismic and well log data through ML enhances geological understanding.
  • This methodology holds promise for more accurate and efficient hydrocarbon exploration.