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

Predicting the accuracy of genomic predictions.

Genetics, selection, evolution : GSE·2021
Same author

Activation of UCP2 by anethole trithione suppresses neuroinflammation after intracerebral hemorrhage.

Acta pharmacologica Sinica·2021
Same author

Effects of moisture content and tillage methods on creep properties of paddy soil.

PloS one·2021
Same author

Nickel (ii) effects on Anammox reaction: reactor performance, dehydrogenase, sludge morphology and microbial community changes.

Environmental technology·2021
Same author

Comparative Efficacy and Safety of Vancomycin, Linezolid, Tedizolid, and Daptomycin in Treating Patients with Suspected or Proven Complicated Skin and Soft Tissue Infections: An Updated Network Meta-Analysis.

Infectious diseases and therapy·2021
Same author

Metal-free carbon monoxide-releasing micelles undergo tandem photochemical reactions for cutaneous wound healing.

Chemical science·2021

Related Experiment Video

Updated: Jan 8, 2026

Dynamic Pore-scale Reservoir-condition Imaging of Reaction in Carbonates Using Synchrotron Fast Tomography
10:18

Dynamic Pore-scale Reservoir-condition Imaging of Reaction in Carbonates Using Synchrotron Fast Tomography

Published on: February 21, 2017

8.8K

Reservoir-enhanced segment anything model for subsurface diagnosis.

Xiren Zhou1, Shikang Liu1, Xinyu Yan1

  • 1School of Computer Science and Technology, University of Science and Technology of China, Hefei, Anhui, China.

Nature Communications
|December 12, 2025
PubMed
Summary

This study introduces a new AI model for detecting underground road defects using Ground Penetrating Radar (GPR). The Reservoir-enhanced Segment Anything Model improves accuracy and efficiency in identifying subsurface anomalies, enhancing urban infrastructure safety.

More Related Videos

Reservoir Condition Pore-scale Imaging of Multiple Fluid Phases Using X-ray Microtomography
08:02

Reservoir Condition Pore-scale Imaging of Multiple Fluid Phases Using X-ray Microtomography

Published on: February 25, 2015

13.0K
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

14.5K

Related Experiment Videos

Last Updated: Jan 8, 2026

Dynamic Pore-scale Reservoir-condition Imaging of Reaction in Carbonates Using Synchrotron Fast Tomography
10:18

Dynamic Pore-scale Reservoir-condition Imaging of Reaction in Carbonates Using Synchrotron Fast Tomography

Published on: February 21, 2017

8.8K
Reservoir Condition Pore-scale Imaging of Multiple Fluid Phases Using X-ray Microtomography
08:02

Reservoir Condition Pore-scale Imaging of Multiple Fluid Phases Using X-ray Microtomography

Published on: February 25, 2015

13.0K
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

14.5K

Area of Science:

  • Geophysics
  • Artificial Intelligence
  • Civil Engineering

Background:

  • Urban infrastructure relies on subsurface integrity, threatened by anomalies like cracks and cavities.
  • Ground Penetrating Radar (GPR) visualizes subsurface conditions but faces challenges in accurate anomaly detection due to data limitations and indistinct boundaries.
  • Radar data, while image-like, fundamentally represents electromagnetic waves where variations are key to anomaly identification.

Purpose of the Study:

  • To develop an advanced framework for precise subsurface anomaly detection in urban infrastructure using GPR data.
  • To enhance the accuracy and efficiency of anomaly detection by integrating visual and wave-property analysis.
  • To provide a scalable and resource-efficient solution for urban safety monitoring.

Main Methods:

  • Proposed the Reservoir-enhanced Segment Anything Model, a framework leveraging both visual features and electromagnetic wave properties of GPR data.
  • The model first identifies visually apparent anomaly candidates and then refines detection by analyzing wave variations within local radar scans.
  • Utilized minimal non-target data, avoiding intensive training, and supported both automatic and interactive operation.

Main Results:

  • Achieved high detection accuracy (> 85%) in real-world experiments, outperforming existing methods.
  • Demonstrated precise and complete extraction and categorization of anomaly regions.
  • Showcased the model's ability to work with limited labeled data and varying subsurface conditions.

Conclusions:

  • The Reservoir-enhanced Segment Anything Model offers a scalable, resource-efficient solution for rapid subsurface anomaly detection.
  • The framework improves urban safety monitoring by reducing manual effort and computational costs.
  • This approach enhances the reliability and applicability of GPR for infrastructure assessment.