Gabriele Chiaro

Engineers must assess soil susceptibility to liquefaction, yet conventional evaluations are time‑consuming, costly, and affected by field-testing variability and semi‑empirical tools that introduce uncertainty. This study clarifies the importance of key parameters and proposes a streamlined machine‑learning approach using ensemble methods. A comprehensive reference dataset was compiled and used to train reliable machine‑learning models. Feature importance was examined with logistic regression and random forest, after which the data were split into training and test sets, predictors were scaled, and hyperparame0ters were tuned with GridSearchCV. Advanced models were then fitted, followed by ensemble approaches, including AdaBoost and voting classifiers. Based on feature importance results, the most influential features across all methods continue to be the Standard Penetration Test-derived parameters. The trained models were assessed, in which the AdaBoost provided the most accurate estimations by achieving precision, recall, F1_score, Jaccard index, and accuracy of 88%, 88%, 88%, 79%, and 88%, respectively. The Voting Classifier demonstrated superior performance over the AdaBoost Classifier in terms of lower false negative values and higher true positive values, which could be considered as a better predictor for high-risk cases.

The reuse of rubber inclusions obtained from End-of-Life Tires (ELTs) offers both environmental and technical benefits in civil engineering applications, reducing landfill disposal and enhancing the dynamic properties of geomaterials. The use of well-graded Gravel–Rubber Mixtures (wgGRMs), produced by blending well-graded gravel with granulated rubber, has been investigated for use in different geotechnical applications. The percentage of rubber inclusions included in wgGRMs significantly modifies the mechanical response of these mixtures, influencing stiffness, strength, dilatancy and dynamic properties. Due to the material heterogeneity (i.e., stiff gravel and soft rubber), the effective implementation of wgGRMs requires the development of constitutive models that can capture the non-linear stress–strain response of wgGRMs subjected to representative in situ loading conditions. In this study, a critical state-based generalized plasticity model is presented and tailored for wgGRMs. Calibration is performed using experimental data from isotropically consolidated drained triaxial tests on wgGRMs with different rubber contents. It is shown that the model accurately reproduces key features observed experimentally, including post-peak strain softening, peak strength variation, and volumetric changes across different confining pressure levels and rubber content fractions. This model represents a useful tool for predicting the behavior of wgGRMs in engineering practice, supporting the reuse of ELT-derived rubber.

Rubberized concrete (RuC), which incorporates recycled tire rubber aggregates in the matrix, offers a viable solution for managing waste tire disposal. Although adding rubber aggregates reduces the compressive strength of concrete, research suggests that in specific applications, such as flexure‐controlled members, this adverse effect can be minimized. However, detailed studies on the flexural performance of reinforced RuC members remain limited. This paper presents a comprehensive study to assess the flexural performance of RuC beams, providing detailed measurements of concrete strains, steel strains, neutral axis depth, and crack widths. The experimental program tested 12 reinforced concrete beams with varying rubber content (0%, 10%, and 20% of total aggregate volume), tension reinforcement ratios ( ρ = 1.13%–2.01%), and axial loads (0–0.1 A _g ). The results indicated that beams containing 10% rubber experienced a decrease in moment capacity of up to 13%, along with a 10% reduction in cracked stiffness. In contrast, beams with 20% rubber exhibited more significant decreases, showing reductions of up to 19% in both capacity and stiffness. Additionally, the impact of axial load appeared to double these reductions for both rubber content levels. The findings confirmed that current modeling techniques can accurately predict this behavior when a modified stress–strain relationship for RuC is applied, considering the lower elastic modulus and strain at peak stress and crushing. The study concludes that 10% rubber content can be regarded as an optimal choice for flexure‐controlled elements subjected to low axial loads.

The escalating environmental challenges posed by waste rubber tyres (WRTs) necessitate innovative solutions to address their detrimental effects on the geoenvironment. Thus, the knowledge about the recent advancements in material recovery from WRTs, emphasising their utilisation within the framework of the United Nations Sustainable Development Goals (SDGs) and the circular economy principles, is the need of the hour. Keeping this in mind, various techniques generally used for material recovery, viz., ambient, cryogenic, waterjet, and so on, which unveil innovative approaches to reclaiming valuable resources (viz., recycled rubber, textiles, steel wires, etc.) from WRTs and various devulcanisation techniques (viz., physical, chemical, and microbial) are elaborated in this paper. In parallel, the paper explores the utilisation of the WRTs and recovered materials, highlighting their application in geotechnical and geoenvironmental engineering development projects while addressing the necessary environmental precautions and associated environmental risks/concerns. This paper incorporates circular economy principles into WRTs utilisation and focuses on achieving SDGs by promoting resource efficiency and minimising their environmental impact.

From a geotechnical engineering viewpoint, recycling and reuse of crushed glass and tire rubber can significantly help reduce the demand for natural resources (i.e., sand and gravel aggregates). Following an earlier study by the authors aimed at characterizing gravel–rubber mixtures (GRM), this paper focuses on the geotechnical assessment of gravel–glass–rubber mixtures (GGRM) made of recycled crushed green glass bottles and recycled granulated tire rubber. Specifically, the compaction, one-dimensional compressibility, and shear strength characteristics of GGRM prepared at 40% and 55% rubber content by volume (R_B) with varying glass content by volume (G_L) are investigated. It is found that compacted GGRM possesses high strength (i.e., friction angle ≥ 30°) and adequate compressibility, making it a suitable general and structural fill material for use in eco-friendly geotechnical applications.