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

Measuring the association between the opening of a new multi-national restaurant with young people's eating behaviours.

Appetite·2024
Same author

Extensive pipeline location data resource: Integrating reported incidents, past environmental loadings, and potential geohazards for integrity evaluations in the U.S. Gulf of Mexico.

Data in brief·2024
Same author

A curated data resource to support safe carbon dioxide transport-route planning.

Data in brief·2023
Same author

A mixed-method systematic review and meta-analysis of the influences of food environments and food insecurity on obesity in high-income countries.

Food science & nutrition·2022
Same author

Healthy plant-based diets and their short-term effects on weight loss, nutrient intake and serum cholesterol levels.

Nutrition bulletin·2022
Same author

A database and framework for carbon ore resources and associated supply chain data.

Data in brief·2022

Related Experiment Video

Updated: Jul 6, 2025

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications
03:31

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications

Published on: December 15, 2023

557

Enhancing knowledge discovery from unstructured data using a deep learning approach to support subsurface modeling

Brendan Hoover1,2,3, Dakota Zaengle1,2, MacKenzie Mark-Moser1,2

  • 1National Energy Technology Laboratory, Albany, OR, United States.

Frontiers in Big Data
|January 3, 2024
PubMed
Summary

An artificial intelligence (AI) tool enhances subsurface knowledge discovery by extracting and labeling geological images from various sources with high accuracy. This AI-powered approach improves the National Energy Technology Laboratory's Subsurface Trend Analysis (STA) workflow.

Keywords:
artificial intelligencedeep learningknowledge discovery (data mining)modelingsubsurfaceunstructured data

More Related Videos

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography
04:48

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography

Published on: November 30, 2022

2.8K
Author Spotlight: Advancing Alzheimer's Research – Exploring Early Detection and Multi-Omics Approaches
09:47

Author Spotlight: Advancing Alzheimer's Research – Exploring Early Detection and Multi-Omics Approaches

Published on: December 15, 2023

1.1K

Related Experiment Videos

Last Updated: Jul 6, 2025

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications
03:31

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications

Published on: December 15, 2023

557
Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography
04:48

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography

Published on: November 30, 2022

2.8K
Author Spotlight: Advancing Alzheimer's Research – Exploring Early Detection and Multi-Omics Approaches
09:47

Author Spotlight: Advancing Alzheimer's Research – Exploring Early Detection and Multi-Omics Approaches

Published on: December 15, 2023

1.1K

Area of Science:

  • Geoscience
  • Artificial Intelligence
  • Data Science

Background:

  • Subsurface interpretation relies on expert knowledge from unstructured data like images and maps.
  • Existing methods for knowledge discovery can be time-consuming and lack systematic approaches.
  • Accurate contextualization of measured subsurface data (cores, well logs, seismic surveys) is crucial for reliable models.

Purpose of the Study:

  • To enhance knowledge discovery in subsurface science.
  • To advance the National Energy Technology Laboratory's (NETL) Subsurface Trend Analysis (STA) workflow.
  • To integrate an artificial intelligence (AI) deep learning approach for image embedding into the STA workflow.

Main Methods:

  • Developed an AI deep learning tool for image embedding within the STA workflow.
  • The tool extracts images from unstructured knowledge products (publications, maps, websites, presentations).
  • Images are categorically labeled, creating a repository for geologic domain postulation.

Main Results:

  • The STA image embedding tool successfully extracts images from diverse sources.
  • The tool achieves high accuracy in categorical labeling, ranging from approximately 90% to 95%.
  • A case study on Gulf of Mexico (GOM) literature demonstrated the tool's effectiveness.

Conclusions:

  • The AI-powered STA image embedding tool significantly improves the efficiency and accuracy of subsurface knowledge discovery.
  • This advancement provides a validated, science-based approach for combining geologic knowledge, statistical modeling, and datasets.
  • The tool facilitates better predictions of subsurface properties through enhanced data interpretation.