Marine clay soils are problematic soils in the construction industry when they are subjected to construction loads. When these soils are loaded, they lose their structure. This leads to the soil being unable to withstand loads of any magnitude without exhibiting significant, permanent deformations. In order to stabilize the marine soil, new methods for soil improvement were built upon biogrouting by incorporating physical, biological and chemical treatments into the soil. However, the biggest challenge of this method is the bacteria migration through the soil medium. To overcome this issue, the electrokinetic phenomenon can be utilized alongside biogrouting to prevent the bacteria migration. In this regard, the present study applied electrobiogrouting stabilization to investigate the improvement of acidic marine clay soil with a pH of 3.69. To accomplish this, two large-scale physical models with dimensions of 500 × 300 × 1200 mm were fabricated to examine the influence of two different treated distances between the inlet and outlet—450 mm (D45) and 600 mm (D60)—on the stability of the treated soil. It was observed that the shear strength of the treated soil improved significantly. The shear strength at the D45 treated distance increased from 3.65 kPa (untreated soil) to 28.14 kPa (treated soil). However, the strength increased by increasing the treated distance. In addition, compressibility and soil electrical conductivity were reduced significantly, and the Atterberg limits were significantly enhanced from OH to OL. The reasons for the enhancement of treated soil were the formation of CaCO3, which filled the soil voids, and that the water content was reduced. To address issues with marine clay soil, this study aims to minimize the high cost of a special foundation system and the use of non-environmentally friendly materials such as calcium-based binders, aside from the reduction of deformations caused by loading. The findings of this study can be used for acidic soils and the improvement of soil’s geotechnical behavior in general.

Calcium-based binders, such as ordinary Portland cement (OPC) and lime (CaO), are the most common artificial cementitious materials used worldwide for concrete and soil improvement. However, using cement and lime has become one of the main concerns for engineers because they negatively affect the environment and economy, prompting research into alternative materials. The energy consumption involved in producing cementitious materials is high, and the subsequent CO2 emissions account for 8% of the total CO2 emissions. In recent years, an investigation into cement concrete’s sustainable and low-carbon characteristics has become the industry’s focus, achieved by using supplementary cementitious materials. This paper aims to review the problems and challenges encountered when using cement and lime. Calcined clay (natural pozzolana) has been used as a possible supplement or partial substitute to produce low-carbon cement or lime from 2012–2022. These materials can improve the concrete mixture’s performance, durability, and sustainability. Calcined clay has been utilized widely in concrete mixtures because it produces a low-carbon cement-based material. Owing to the large amount of calcined clay used, the clinker content of cement can be lowered by as much as 50% compared with traditional OPC. It helps conserve the limestone resources used in cement manufacture and helps reduce the carbon footprint associated with the cement industry. Its application is gradually growing in places such as Latin America and South Asia.

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.