Investigating the Soil Unconfined Compressive Strength Based on Laser-Induced Breakdown Spectroscopy Emission Intensities and Machine Learning Techniques.

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 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 develop a pioneering technique to estimate the soil unconfined compressive strength using artificial intelligent methods based on the spectra obtained from the LIBS system. Decision tree regression (DTR) and support vector regression learners were initially employed, and consequently, the adaptive boosting method was applied to improve the performance of the two single learners. The prediction power of the established models was determined using the standard performance evaluation metrics such as the root-mean-square error, CC between the predicted and actual soil UCS values, mean absolute error, and R2 score. Our results revealed that the boosted DTR exhibited the highest coefficient of correlation of 99.52% and an R2 value of 99.03% during the testing phase. To validate the models, the UCS values of soils stabilized with lime and cement were predicted with an optimum degree of accuracy, confirming the models' suitability and generalization strength for soil UCS investigations.

Role of casting and curing conditions on the strength and drying shrinkage of greener concrete.

The shrinkage of cement-based materials is a critical dimensional property that needs proper attention as it can influence the corresponding characteristics especially when the preparation of such cement-based material is done in hot weather. Studies have shown that the casting or curing conditions influence the performance of concrete. However, there is limited understanding of the combined role of casting temperature and curing conditions, especially for concrete made with unconventional binders. In this study, five supplementary cementitious materials (SCMs) were utilized as the substitute of the ordinary Portland cement (OPC) at different ratios to produce greener concrete and improve its characteristics and sustainability. The influence of four casting temperatures (i.e., 25 °C, 32 °C, 38 °C, and 45 °C) and two curing regimes (i.e., covering of samples using wet burlap and applying curing compound on the surface of samples) on the corresponding compressive strength and drying shrinkage at various ages was studied. The outcomes of this research revealed that the composition of the binders has a substantial impact on the characteristics of concrete. In addition, the casting temperature and curing regimes also have a huge role on the compressive strength of concrete produced with binary binders. For example, the compressive strength at 3 days of concrete made at 25 °C made with binary binders was reduced up to 31% compared to that made with only OPC as the binder when cured using wet burlap. Nonetheless, less than 38 ℃ was suitable to minimize the durability issues in the studied blended cement mixes.