Related Experiment Video
Updated: Jul 20, 2025
08:53
Dependence of Laser-induced Breakdown Spectroscopy Results on Pulse Energies and Timing Parameters Using Soil Simulants
Published on: September 23, 2013
11.4K
Investigating the Soil Unconfined Compressive Strength Based on Laser-Induced Breakdown Spectroscopy Emission
Yakubu Sani Wudil1,2, Osama Atef Al-Najjar3, Mohammed A Al-Osta1,3
1Interdisciplinary Research Center for Construction and Building Materials, King Fahd University of Petroleum and Minerals, Dhahran 31261, Saudi Arabia.
ACS Omega
|July 31, 2023
Summary
This study introduces an AI-driven method using Laser-Induced Breakdown Spectroscopy (LIBS) to predict soil unconfined compressive strength (UCS). The approach offers a faster, more cost-effective alternative to traditional geotechnical testing.
Area of Science:
- Geotechnical Engineering
- Spectroscopy
- Machine Learning
Background:
- Laser-induced breakdown spectroscopy (LIBS) is vital for elemental analysis.
- Accurate soil unconfined compressive strength (UCS) is crucial for geotechnical applications.
- Traditional UCS testing is expensive and time-consuming.
Purpose of the Study:
- To develop a novel, AI-based method for estimating soil UCS using LIBS spectra.
- To explore the efficacy of machine learning models for calibration-free LIBS in geotechnical contexts.
- To provide a cost-effective and efficient alternative to conventional UCS measurement techniques.
Main Methods:
- Utilized LIBS to obtain soil spectra.
- Employed machine learning algorithms, including decision tree regression (DTR) and support vector regression (SVR).
- Applied adaptive boosting to enhance the performance of single machine learning learners.
Main Results:
- Boosted DTR achieved a high coefficient of correlation (99.52%) and R² score (99.03%).
- The developed models demonstrated strong prediction accuracy for soil UCS.
- Validated models showed suitability for predicting UCS in lime and cement-stabilized soils.
Conclusions:
- The AI-powered LIBS technique offers a promising and accurate approach for soil UCS estimation.
- This method significantly reduces the cost and time associated with traditional geotechnical testing.
- The models exhibit good generalization strength for diverse soil UCS investigations.
