Initial applications of micropiles have involved retrofitting foundations of existing buildings. In these applications, the overall performance of the micropiles–raft (MPR) foundation system is similar to a piled raft foundation where the load is transmitted through both the raft and micropiles. However, there is no guidance available regarding the performance of MPR foundations. In this study, geotechnical centrifuge testing was conducted to investigate the behavior of MPR foundations in sand and evaluate their performance characteristics. The study investigated the effect of raft flexibility on a number of important design parameters, including raft total and differential settlements, raft contact pressure, raft bending moment, and load sharing between the raft and micropiles. In addition, the use of micropiles as settlement reducers was investigated. The results showed that the micropiles carried 42%–59% of the applied load for the MPR configuration considered, which resulted in redistribution of the raft contact pressure. It was found that the Poulos–Davis–Randolph (PDR) method can be used to evaluate the performance of MPR systems with relatively stiff rafts; however, it is not applicable for MPR with flexible raft. A correction factor was proposed to account for the raft flexibility in the PDR method.

According to an extensive evaluation of published studies, there is a shortage of research on systematic literature reviews related to machine learning prediction techniques and methodologies in soil improvement using green materials. A literature review suggests that machine learning algorithms are effective at predicting various soil characteristics, including compressive strength, deformations, bearing capacity, California bearing ratio, compaction performance, stress–strain behavior, geotextile pullout strength behavior, and soil classification. The current study aims to comprehensively evaluate recent breakthroughs in machine learning algorithms for soil improvement using a systematic procedure known as PRISMA and meta-analysis. Relevant databases, including Web of Science, ScienceDirect, IEEE, and SCOPUS, were utilized, and the chosen papers were categorized based on: the approach and method employed, year of publication, authors, journals and conferences, research goals, findings and results, and solution and modeling. The review results will advance the understanding of civil and geotechnical designers and practitioners in integrating data for most geotechnical engineering problems. Additionally, the approaches covered in this research will assist geotechnical practitioners in understanding the strengths and weaknesses of artificial intelligence algorithms compared to other traditional mathematical modeling techniques.