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

Quantitative correlation of rock fragment gradation parameters and TBM disc cutter efficiency: Insights from DEM simulations.

PloS one·2026
Same author

Association of triglyceride-cholesterol-body weight index with in-hospital mortality in critically ill patients with heart failure.

Scientific reports·2026
Same author

Capture-SELEX of DNA Aptamers for Highly Selective Binding of Folate.

Chembiochem : a European journal of chemical biology·2026
Same author

Relationship between the triglyceride-glucose index and non-alcoholic fatty liver disease among individuals with atrial fibrillation.

American journal of cardiovascular disease·2026
Same author

Controlling mechanisms and health risk assessment of high fluoride geothermal water in the Pearl River Delta region, South China.

Journal of hazardous materials·2026
Same author

Spectroscopic and structural insights into magnetized water: Evidence of hydrogen-bond reorganization.

Talanta·2026

Related Experiment Video

Updated: May 23, 2025

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

937

Comparison of machine learning models for rock UCS prediction using measurement while drilling data.

Yachen Xie1, Xianrui Li2, Zhao Min3

  • 1School of Civil Engineering and Transportation, South China University of Technology, Guangzhou, 510641, China. xyc61246@163.com.

Scientific Reports
|March 12, 2025
PubMed
Summary

Machine learning models can now predict rock uniaxial compressive strength (UCS) using measurement-while-drilling data. Random Trees (RT) and Support Vector Regression (SVR) models show the most promising results for efficient UCS estimation in rock engineering.

Keywords:
Machine learningMeasurement while drillingUniaxial compressive strength

More Related Videos

Mechanical Expansion of Steel Tubing as a Solution to Leaky Wellbores
09:32

Mechanical Expansion of Steel Tubing as a Solution to Leaky Wellbores

Published on: November 20, 2014

12.2K
Atomic Force Microscopy Cantilever-Based Nanoindentation: Mechanical Property Measurements at the Nanoscale in Air and Fluid
08:58

Atomic Force Microscopy Cantilever-Based Nanoindentation: Mechanical Property Measurements at the Nanoscale in Air and Fluid

Published on: December 2, 2022

2.8K

Related Experiment Videos

Last Updated: May 23, 2025

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

937
Mechanical Expansion of Steel Tubing as a Solution to Leaky Wellbores
09:32

Mechanical Expansion of Steel Tubing as a Solution to Leaky Wellbores

Published on: November 20, 2014

12.2K
Atomic Force Microscopy Cantilever-Based Nanoindentation: Mechanical Property Measurements at the Nanoscale in Air and Fluid
08:58

Atomic Force Microscopy Cantilever-Based Nanoindentation: Mechanical Property Measurements at the Nanoscale in Air and Fluid

Published on: December 2, 2022

2.8K

Area of Science:

  • Geotechnical Engineering
  • Machine Learning Applications
  • Rock Mechanics

Background:

  • Accurate determination of uniaxial compressive strength (UCS) is vital for rock engineering projects.
  • Traditional UCS testing methods are time-consuming, labor-intensive, and not suitable for fractured rock.
  • Measurement-while-drilling (MWD) data offers a promising alternative for rapid UCS estimation.

Purpose of the Study:

  • To develop a rapid, efficient, and economical method for estimating UCS using while-drilling tests.
  • To evaluate the performance of various machine learning models for UCS prediction based on MWD data.
  • To identify the most suitable machine learning models for UCS estimation across diverse rock types and conditions.

Main Methods:

  • Compiled a comprehensive dataset of drilling parameters and UCS values from existing literature.
  • Trained and evaluated five machine learning models: Multilayer Perceptron (MLP), Support Vector Regression (SVR), Convolutional Neural Networks (CNN), Random Trees (RT), and Long Short-Term Memory Networks (LSTM).
  • Validated model performance on an independent, unseen dataset.

Main Results:

  • Random Trees (RT) exhibited superior predictive performance with an R² of 0.959 and the lowest RMSE (15.851).
  • Support Vector Regression (SVR) also showed strong performance with an R² of 0.922.
  • RT and SVR demonstrated the best generalization capabilities and accuracy on the independent dataset.

Conclusions:

  • Machine learning models, particularly RT and SVR, can effectively predict uniaxial compressive strength (UCS) using measurement-while-drilling data.
  • This approach offers a faster, more economical alternative to traditional UCS testing methods.
  • The findings support the use of RT and SVR for real-time UCS estimation in rock engineering applications.