Field dry density is a soil compaction characteristic that is useful for geotechnical engineering design. Laboratory methods are laborious and time-consuming. The purpose of this paper is to determine and compare the effectiveness of MLR and SVM models in predicting this essential parameter from the fundamental soil property index level. A dataset of 86 soil samples with various geotechnical qualities was used, containing data such as gravel, sand, fines, liquid limit, and plastic limit. The dataset was split into 80% training and 20% testing. Using $R^{2},$ RMSE, and MSE, the performance of the built MLR and SVM prediction models was thoroughly examined. With an R2 value of 0.988 (on the test set), the SVM model outperforms the MLR model in terms of prediction accuracy for FDD $(R2=0.814)$. Compaction behavior and soil property index properties have a complicated relationship, as seen by the performance gap. According to feature importance analysis, the SVM model's predictions heavily relied on the fines content. According to this study, SVM is a useful method that geotechnical engineers can employ to quickly and affordably estimate compaction parameters in the early phases of site investigations and design optimization.
The performance of foundations located adjacent to natural slopes continues to pose significant technical challenges in geotechnical engineering, attributed to compromised soil stability, reduced bearing capacity, and increased foundation settlement. These phenomena are especially pronounced for ring foundations, which are adopted extensively for axi-symmetric superstructures such as silos, oil tanks, chimneys, and wind turbines. PLAXIS 3D software was used for numerical analysis. Some of the most critical parameters studied are the effect of soil properties and the differential settlement between two different regions on the ring foundation. The internal stress responses of the foundation structure, including the distribution of shear force and bending moment, are also studied. Important soil properties, including the friction angle and elastic modulus, exert comparable influences on foundation performance. The research reveals differential settlement between nodes situated nearest the slope and those positioned farther away. The resultant of bending and shearing forces in the ring foundation is proven to be most greatly influenced by slope geometry. The results are essential for the foundation of modern construction. The data will lead to the development of resilient designs for ring foundations on slopes.
Pile foundations are essential to transmit structural loads to the underlying soils and rocks. Piles may functionally or accidently be subjected to lateral soil movements, most often due to the slope's failing nature, deep excavation, soil liquefaction and seismic activities, which significantly affect its stability and safety. This study uses PLAXIS 3D software to predict the response of pile foundations subjected to lateral soil movements. Two case studies were analysed to validate the predictive ability of the software, to test the sensitivity of the input parameters, and to serve as a practical guide for the selection of the parameters in case of lack of availability of complete in-situ information. The behaviour of soil-pile interaction in different types of soils, particularly clay soils, was also considered. The results underline the importance of advanced modelling and accurate parameter selection for the stability and reliability of pile foundations under passive loading and lateral soil movement conditions.