The soil packing, influenced by variations in grain size and the gradation pattern within the soil matrix, plays a crucial role in constituting the mechanical properties of sandy soils. However, previous modeling approaches have overlooked incorporating the full range of representative parameters to accurately predict the soaked California bearing ratio (CBRs) of sandy soils by precisely articulating soil packing in the modeling framework. This study presents an innovative artificial intelligence (AI)-based approach for modeling the CBRs of sandy soils, considering grain size variability meticulously. By synthesizing extensive data from multiple sources, i.e. extensive tailored testing program undertaking multiple tests and extant literature, various modeling techniques including genetic expression programming (GEP), multi-expression programming (MEP), support vector machine (SVM), and multi-linear regression (MLR) are utilized to develop models. The research explores two modeling strategies, namely simplified and composite, with the former incorporating only sieve analysis test parameters, while the latter includes compaction test parameters alongside sieve analysis data. The models' performance is assessed using statistical key performance indicators (KPIs). Results indicate that genetic AI-based algorithms, particularly GEP, outperform SVM and conventional regression techniques, effectively capturing complex relationships between input parameters and CBRs. Additionally, the study reveals insights into model performance concerning the number of input parameters, with GEP consistently outperforming other models. External validation and Taylor diagram analysis demonstrate the GEP models' superiority over existing literature models on an independent dataset from the literature. Parametric and sensitivity analyses highlight the intricate relationships between grain sizes and CBRs, further emphasizing GEP's efficacy in modeling such complexities. This study contributes to enhancing CBRs modeling accuracy for sandy soils, crucial for pertinent infrastructure design and construction rapidly and cost-effectively. (c) 2025 Institute of Rock and Soil Mechanics, Chinese Academy of Sciences. Published by Elsevier B.V. This is an open access article under the CC BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/ 4.0/).

Concrete is one of the most widely used building materials due to its many advantages, which results in large amounts of concrete waste resulting from demolition. This study will be an attempt to produce an environmentally friendly road. In this research, recycled aggregates were used according to the class A and B, used in the Iraqi specifications for roads and bridges (SORB). Two methods were used, the first method was to use recycled aggregate of class A and B with different proportions of fine soil, as a binding material for the aggregate particles, and the second method was to use recycled aggregate of class A and B with different proportions of fly ash as a binding material for the aggregate particles. The physical and mechanical properties of the recycled aggregate were studied, the behaviour of road layers designed from recycled aggregate was also studied by determining the California bearing ratio in dry and wet conditions, as well as the unconfined compressive strength. The research showed that when using( 5%,10%,14%)of fine soil with recycled aggregate, the California bearing ratio fit gave high and acceptable values. However, when increasing the ratio to 16%, the values decreased from 41.0% to 38.7% for class A in the soaking state, but in the unsoakhng state, it decreased from44.6% to 42.0% and Also the class B values decreased in the soaking state from 41.4% to 39.3%, and in the un soaking state from 45.0% to 43.2%,Likewise The unconfined compressive strength decreased by 25% when the fine soil content increased to 16% while the values increased with increasing fly ash content. This study concluded that it is possible to use recycled aggregate in the design of road layers, especially since the values of the California bearing ratio of recycled aggregate are greater than the values of natural aggregate used in road works. Thus, this study achieved a major goal from an environmental and economic perspective.

India's passenger traffic primarily relies on the road network for commuting. As a result, the demand for transport infrastructure has led to rapid growth in road construction across the country. California Bearing Ratio (CBR) tests measure strength of subgrade soil, which is essential for pavement design. In practice, the CBR value is often estimated through index and strength properties of soil, since it is easier as compared to the conventional time-consuming laboratory CBR testing. Over the years, a lot of efforts has been taken for developing CBR from index and strength properties correlation equations, most of which are based on regression analysis. Moreover, most of the correlation equations developed are based on a wide dataset compiled from different regions, which makes them incapable of accounting for the spatial variability of soil. This study presents a quick approach to estimate onsite CBR values using sensor acceleration data, avoiding time-consuming laboratory tests. An Arduino Uno sensor collected data for 19 locations in Dhule district, Maharashtra was used in present study. The developed CBR equations using sensor data showed a strong correlation with conventional regression equations and experimental results.

The mechanical properties of shallow expansive soil are crucial to expansive soil engineering. However, few effective test methods have been available to measure the in-situ mechanical properties of shallow expansive soil. This paper attempts to test the effects of water content and fissures on the mechanical properties of shallow expansive soil under a natural state by in-situ CBR and resilience modulus tests. The evolution characteristics of shrinkage fissures in expansive soil were recorded and observed. The fissure connectivity coefficient is used to express the degree of fissure development and the integrity of soil structure. The CBR strength and resilience modulus of expansive soil increase first and then decrease with the decrease of water content and the increase of fissure development degree, and reach the peak near the optimal water content. It is effective to use the inverse hyperbolic sine function to fit the relationship between soil mechanical parameters, water content, and fissure connectivity coefficient. When the water content is higher, the influence of water content on soil mechanical properties is great. When the water content is lower, fissures are more developed, and the influence of fissures on soil mechanical properties is dominant.

Road infrastructure construction in developing countries such as Vietnam requires an enormous amount of natural sand. The scarcity of river sand is becoming increasingly severe, with predictions indicating a sustained drop in its supply. Hence, it is essential for the construction industry to implement a sustainable strategy by combining waste materials with abundant resources in order to effectively address this challenging situation. The objective of this study is to investigate the mechanical properties and evaluate the potential application of mixtures comprising rock quarry dust and sea sand for the roadbed layers of expressways. The researchers conducted a series of experiments, including the moisture content, specific gravity, angle of repose of material, and triaxial tests to study the composition and mechanical behaviors of mixtures at different ratios. Extensive parametric investigations in conjunction with the calibration in Plaxis' soil-test module obtain the Young's modulus E50 and confining pressure curves. Based on the assessment of materials utilized in roadbed layer of highway, as determined by the California bearing ratio (CBR) coefficient, it demonstrates that combining sea sand and quarry dust can generate the mixtures possessing appropriate properties for application in the construction of the roadbed of highway.