Geopolymers have attracted wide attention as effective soil stabilisers, presenting significant potential for several geotechnical engineering applications. These binders offer environmental benefits by utilising abandoned aluminosilicate industrial by-products, such as fly ash and slag, through mixing with an alkaline solution. In addition, they also decrease dependency on conventional Ordinary Portland Cement (OPC), which is identified with substantial artificial greenhouse gas emissions and high energy consumption during manufacture. However, the practical utilisation of geopolymers for the stabilisation of road materials is hindered by the intricate preparation process, which necessitates precise control over the proportions of the ingredients to achieve the required mechanical properties. This complexity becomes more pronounced when compared to the relatively simple method of using conventional cement, which requires fewer safety precautions while mixing with soil. This study investigates the development of a One-Part Geopolymer (OPG) powder, specifically formulated for the stabilisation of a Crushed Rock Base (CRB) material used for road construction. The optimal blend of OPG powder, comprising fly ash, slag and sodium metasilicate, is identified by assessing the monotonic and dynamic mechanical performances of the treated CRB compacted at the optimum moisture content using Unconfined Compressive Strength (UCS) and Repeated Load Triaxial (RLT) tests. The results of the study indicate that enhancing the strength performance of the OPG-treated CRB requires the calibration of the sodium oxide (Na2O) content in the alkaline activator with the total binder. It was also found that increasing the OPG content from 1% to 3% significantly enhances both the uniaxial strength and resilient modulus of the treated CRB, while simultaneously reducing the permanent deformation. Notably, the CRB specimens stabilised with 2% OPG exhibit mechanical properties comparable to those of bound Portland cemented materials.

To achieve environmental and economic goals in ground improvement, a one-part geopolymer (OPG), synthesized from binary precursors (fly ash [FA] and granulated blast furnace slag [GGBFS]) and a solid activator (solid sodium silicate [NS]), was used to replace ordinary Portland cement (OPC) for stabilizing high-water-content soft clay. The effects of different initial water content (50%, 80%, 100%, and 120%) and various OPG binder content (10%, 20%, 30%, and 40%) on the strength development of the OPG-stabilized soft clay were investigated through unconfined compressive strength (UCS) and unconsolidated undrained (UU) triaxial tests. Additionally, the microstructure evolution and the distribution of pores in the OPG-stabilized soft clay were examined by the utilization of mercury intrusion porosimetry (MIP) and scanning electron microscopy-energy-dispersive spectroscopy (SEM-EDS) techniques, respectively. The life cycle assessment (LCA) methodology was then used to analyze the environmental and economic advantages of employing an OPG binder for soil stabilization. It was revealed that the optimal content of OPG binder was contingent upon the water content of soft clay, with variations in requirements for strength development. Specifically, for soft clay not demanding early strength, a maximum binder content of 20% is proposed. Conversely, for soft clay that necessitated rapid strength gain, the OPG binder content escalated with increasing water content of the soft clay, in which soft clays with different water contents had corresponding required amounts of OPG binder. For soil with water content ranging from 50% to 80%, the recommended OPG binder content is 20%. While for soil with 100% and 120% water content, the designed OPG binder content is suggested to be 30% and 40%, respectively. The environmental assessment demonstrated that the utilization of OPG as a binder for the stabilization of soft clay reduces costs and carbon emissions in comparison to OPC. The present study provides substantial theoretical validation for the utilization of OPG as a novel binder to stabilize soft clay with elevated water content, which holds promise as an eco-friendly and cost-effective solution in ground improvement.

The mechanical properties of soil located at cold areas may be deteriorated under freeze-thaw cycle condition. One-part geopolymer (OPG) is a kind of alkaline-activated material by using industrial by-products and solid alkali. Obviously, OPG can replace ordinary portland cement (OPC) as a soil stabilizer in ground improvement, which presents environmental and low-carbon benefits. The assessment of unconfined compressive strength (UCS) is vital for evaluating OPGstabilized soil durability under freeze-thaw conditions, typically demanding extensive resources. Leveraging artificial intelligence, a predictive model can be developed for this purpose. This study collected a small sample size of 216 data points of the OPG-stabilized soil's freeze-thaw behaviour. Three deep learning (DL) models, Backpropagation Neural Network [BPNN], Convolutional Neural Network [CNN], Gated Recurrent Unit [GRU], were trained on the small dataset to predict freeze-thaw performance efficiently, offering a promising approach to streamline assessment processes. In the DL models, the ratio of fly ash (FA) and ground granulated blast furnace slag (GGBFS), freezing temperature and freeze-thaw cycle were taken as the input variables, and the target output was the UCS of the OPG-stabilized soil. Among all the models, the CNN achieved the highest prediction accuracy with R2 of 0.9966, and followed by the BPNN (R2=0.9893) and the GRU (R2=0.9872). After that, the interpretable machine learning methods (i.e., Shapley Additive Explanation [SHAP] and Partial Dependence Plot [PDP]) were utilized for the developed CNN model to further understand the impact of input variables on the outcome predictions. In addition, the morphological analysis was used to verify the freeze-thaw mechanism of the OPG-stabilized soil derived from the interpretable CNN model. It is revealed that the inclusion of FA in the OPG crucially enhanced the freeze-thaw resistance of the OPG-stabilized soil. However, beyond a certain threshold, the addition of FA negatively impacted the freezethaw resistance of OPG-stabilized soil. Freezing temperature was pinpointed as the key factor affecting the properties of the stabilized soil.

This study focused on exploring the utilization of a one-part geopolymer (OPG) as a sustainable alternative binder to ordinary Portland cement (OPC) in soil stabilization, offering significant environmental advantages. The unconfined compressive strength (UCS) was the key index for evaluating the efficacy of OPG in soil stabilization, traditionally demanding substantial resources in terms of cost and time. In this research, four distinct deep learning (DL) models (Artificial Neural Network [ANN], Backpropagation Neural Network [BPNN], Convolutional Neural Network [CNN], and Long Short-Term Memory [LSTM]) were employed to predict the UCS of OPG-stabilized soft clay, providing a more efficient and precise methodology. Among these models, CNN exhibited the highest performance (MAE = 0.022, R2 = 0.9938), followed by LSTM (MAE = 0.0274, R2 = 0.9924) and BPNN (MAE = 0.0272, R2 = 0.9921). The Wasserstein Generative Adversarial Network (WGAN) was further utilized to generate additional synthetic samples for expanding the training dataset. The incorporation of the synthetic samples generated by WGAN models into the training set for the DL models led to improved performance. When the number of synthetic samples achieved 200, the WGAN-CNN model provided the most accurate results, with an R2 value of 0.9978 and MAE value of 0.9978. Furthermore, to assess the reliability of the DL models and gain insights into the influence of input variables on the predicted outcomes, interpretable Machine Learning techniques, including a sensitivity analysis, Shapley Additive Explanation (SHAP), and 1D Partial Dependence Plot (PDP) were employed for analyzing and interpreting the CNN and WGAN-CNN models. This research illuminates new aspects of the application of DL models with training on real and synthetic data in evaluating the strength properties of the OPG-stabilized soil, contributing to saving time and cost.

To address the issues of low early strength in cement-stabilized soft soil, as well as the high pollution, energy consumption, and costs associated with cement binder application, one-part geopolymer (OPG) is prepared by using solid sodium silicate (Na2O center dot SiO2, NS) to activate a mixture of binary precursors, namely fly ash (FA) and ground granulated blast furnace slag (GGBFS), along with water. The factors, including FA dosage, solid NS molarity, alkali molar concentration, and water-cement ratio, are considered for assessing the physical and mechanical properties of OPG. Based on this, optimized proportioning tests were conducted to determine the best mixing ratio of OPG for soft soil stabilization. The effects of the FA/GGBFS ratio in the precursor and curing ages on the unconfined compressive strength (UCS), porosity, and pore size distribution of OPG-stabilized soft soil were further investigated. Micro-analysis was performed using mercury intrusion porosimetry (MIP), scanning electron microscope-energy dispersive spectrometer (SEM-EDS) to reveal the stabilization mechanism. The results indicated that the OPG prepared with solid NS could effectively stabilize soft soil, with hydrated gels (N-A-S-H, C-A-H, C-S-H, and C-A-S-H) effectively bonding soil particles and contributing to the formation of a denser soil skeleton. The mixing proportion of FA/GGBFS of 0.1, water-cement ratio of 0.8, NS molarity of 1.0, and molar concentration of 3 mol/L was found to be optimal for soft soil stabilization. The corresponding OPG had good workability and achieved a UCS of 4.4 MPa. This study extends the application of solid sodium silicate-inspired one-step geopolymers in deep mixing techniques, providing guidance on the theoretical basis for the reinforcement treatment of soft ground foundations.

In the construction of traffic engineering, a large amount of waste soils was generated. These soils have poor engineering properties, cannot be used as subgrade fill, so they were solidified treatment, commonly used cement curing agent have adverse effects on the environment. One-part geopolymer (OPG), as a green and new type of soil stabilizer, not only provides a new idea for the solidification of engineering waste, but also offers an effective way for the disposal of industrial solid waste, and reduces the consumption of cement. In order to evaluate the durability of geopolymer solidified soil, in this paper, with fly ash (FA) and ground granulated blast furnace slag (GGBS) as raw materials, solid NaOH and Na2SiO3 2 SiO 3 as solid alkali-activator to prepare OPG, which was used as a solidifier to solidify the waste dredged silt to produce one-part geopolymer-solidified soil (OPGSS). The variation patterns of mass, unconfined compression strength (UCS) and elasticity modulus of OPGSS with attack time under 0%, 5% and 10% Na2SO4 2 SO 4 solutions were investigated. The changes in the phase composition, micro- morphology and pore size distribution of OPGSS were characterized by XRD, SEM-EDS and nuclear magnetic resonance (NMR). The results showed that: Under both 5% and 10% Na2SO4 2 SO 4 solutions, the UCS of OPGSS decreased in two stages with attack time, and the number of large pores and total pores of OPGSS increased in two stages. The inflection points appeared on day 8 under 5% Na2SO4 2 SO 4 solution; the inflection points appeared on day 5 under 10% Na2SO4 2 SO 4 solution. This was mainly due to the expansion of corrosion products formed by OPGSS under Na2SO4 2 SO 4 attack, which destroyed the microstructure of OPGSS and led to a reduction in the UCS of the OPGSS.