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

Methods of Obtaining Topography01:25

Methods of Obtaining Topography

101
Topography involves measuring and mapping land elevations, natural features, and artificial structures to create accurate representations of the terrain. Topographic surveying relies on traditional and modern methods, each with distinct advantages and limitations.Traditional Surveying Methods:Transit stadia surveys and plane table surveys were widely used traditional surveying methods. These techniques relied on instruments like theodolites and stadia rods for measuring distances and angles,...
101

You might also read

Related Articles

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

Sort by
Same author

Generation of carbonated peridotite melts via biogenic sediment recycling in modern subduction zones.

Science advances·2026
Same author

Human Brucellosis in Southeast Iran (2019-2023): Descriptive Epidemiology and Temporal Trends Based on Surveillance Data.

Zoonoses and public health·2026
Same author

Correction: Fast-moving dislocations trigger flash weakening in carbonate-bearing faults during earthquakes.

Scientific reports·2026
Same author

Nanostructures as indicator for deformation dynamics.

Nature communications·2025
Same author

Coupling antigorite deformation and dehydration in high-pressure experiments.

Contributions to mineralogy and petrology. Beitrage zur Mineralogie und Petrologie·2025
Same author

Deep crustal deformation driven by reaction-induced weakening.

Nature communications·2025

Related Experiment Video

Updated: Aug 12, 2025

Measuring the Structure, Composition, and Change of Underwater Environments with Large-area Imaging
09:19

Measuring the Structure, Composition, and Change of Underwater Environments with Large-area Imaging

Published on: April 18, 2025

710

Quantifying microstructures of earth materials using higher-order spatial correlations and deep generative

Hamed Amiri1, Ivan Vasconcelos2, Yang Jiao3

  • 1Department of Earth Sciences, Utrecht University, Utrecht, The Netherlands. h.amiri@uu.nl.

Scientific Reports
|January 31, 2023
PubMed
Summary
This summary is machine-generated.

Generative adversarial networks (GANs) can reconstruct complex earth material microstructures. Evaluating GANs with statistical microstructural descriptors (SMDs) reveals their ability to capture spatial patterns and identify training artefacts.

More Related Videos

Correlative Microscopy for 3D Structural Analysis of Dynamic Interactions
13:43

Correlative Microscopy for 3D Structural Analysis of Dynamic Interactions

Published on: June 24, 2013

14.2K
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

600

Related Experiment Videos

Last Updated: Aug 12, 2025

Measuring the Structure, Composition, and Change of Underwater Environments with Large-area Imaging
09:19

Measuring the Structure, Composition, and Change of Underwater Environments with Large-area Imaging

Published on: April 18, 2025

710
Correlative Microscopy for 3D Structural Analysis of Dynamic Interactions
13:43

Correlative Microscopy for 3D Structural Analysis of Dynamic Interactions

Published on: June 24, 2013

14.2K
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

600

Area of Science:

  • Geosciences
  • Materials Science
  • Computational Science

Background:

  • Understanding subsurface processes requires linking microstructural features to macroscopic properties of earth materials.
  • Imaging technologies face resolution-sample size trade-offs, limiting microstructure characterization.
  • Image reconstruction offers a solution by generating statistically equivalent microstructures at larger scales.

Purpose of the Study:

  • To reconstruct 2D images of hydrothermal rock microstructures using generative adversarial networks (GANs) and a stochastic method.
  • To evaluate and compare the performance of different GANs (DCGAN, WGAN-GP, StyleGAN2-ADA) against a stochastic method.
  • To assess the utility of multi-point spatial correlation functions (statistical microstructural descriptors - SMDs) for evaluating reconstruction quality.

Main Methods:

  • Reconstruction of two hydrothermal rock microstructures using a stochastic method and three GANs: DCGAN, WGAN-GP, and StyleGAN2-ADA.
  • Performance evaluation using statistical microstructural descriptors (SMDs), specifically multi-point spatial correlation functions, as external assessment tools.
  • Comparative analysis of GANs and the stochastic method based on their ability to capture higher-order spatial correlations.

Main Results:

  • Well-trained GANs successfully reconstructed higher-order, spatially-correlated patterns in complex earth material microstructures.
  • GANs demonstrated superior performance over stochastic methods in capturing structural and morphological properties.
  • Statistical microstructural descriptors (SMDs) proved effective in quantifying reconstruction quality and identifying GAN training artefacts.

Conclusions:

  • Generative adversarial networks (GANs) are powerful tools for reconstructing complex microstructures in earth materials.
  • The use of higher-order statistical microstructural descriptors (SMDs) is crucial for robust GAN training and assessment.
  • SMDs provide valuable interpretability for synthetic microstructures, aiding in the detection of artefacts and failure modes.