Laser-Induced Spectroscopy-Based Prediction of Soil Unconfined Compressive Strength: A Machine Learning Approach

Laser-induced breakdown spectroscopy (LIBS) is a remarkable elemental identification and quantification technique used in multiple sectors, including science, engineering, and medicine. Machine learning techniques have recently sparked a widespread interest in the development of calibration-free LIBS due to their ability to generate a defined pattern for complex systems. In geotechnical engineering, understanding soil mechanics in relation to the applications is of paramount importance. The knowledge of soil unconfined compressive strength (UCS) enables engineers to identify the behaviors of a particular soil and propose effective solutions to given geotechnical problems. However, the experimental techniques involved in the measurements of soil UCS are incredibly expensive and time-consuming. In this work, we propose a pioneering technique to estimate the soil UCS using machine learning algorithms based on the emission spectra obtained from the LIBS system. Support vector regression (SVR) and decision tree regression (DTR) learners were initially employed, and consequently, the adaptive boosting method was applied to improve the performance of the two single learners. The performance of the models was assessed based on the standard metric performance indicators R2-score, mean absolute error (MAE), root means square error (RMSE), and correlation coefficient (CC) between the predicted and actual soil UCS values. Our results revealed that the boosted DTR exhibited the highest coefficient of correlation of 99.52% and R2 value of 99.03% during the testing phase. To validate the models, the UCS of soils stabilized with cement and lime were predicted with a high degree of accuracy, confirming the models' suitability and generalization strength for soil UCS investigations.