Most of the robust artificial intelligence (AI)-based constitutive models are developed with synthetic datasets generated from traditional constitutive models. Therefore, they fundamentally rely on the traditional constitutive models rather than laboratory test results. Also, their potential use within geotechnical engineering communities is limited due to the unavailability of datasets along with the model code files. In this study, the data-driven constitutive models are developed using only laboratory test databases and deep learning (DL) techniques. The laboratory database was prepared by conducting cyclic direct simple shear (CDSS) tests on reconstituted sand, that is, PDX sand. The stacked long short-term memory (LSTM) network and its variants are considered for developing the predictive models of the shear strain (gamma [%]) and excess pore pressure ratio (ru) time histories. The suitable input parameters (IPs) are selected based on the physics behind the generation of ru and gamma (%) of the liquefiable sands. The predicted responses of gamma (%) and ru agree well in most cases and are used to predict the dynamic soil properties of the PDX sand. The same modeling framework is extended for other sand and compared with existing AI-based constitutive models to verify its practical applicability. In summary, it is observed that though the trained models predicted the time histories of ru and gamma reasonably well; however, they struggled to predict the hysteresis loops at higher cycles. Therefore, more research is needed to verify and enhance the predictability of existing AI-based models in the future before using them in practice for simulating cyclic response.

Fiber-reinforcing technology involves adding discrete and tension-resistant fibers into soils to improve the mechanical properties of the soils. This study investigates the static liquefaction responses of the fibre-reinforced sand in loose states by performing the undrained triaxial compression tests. The feasibility of varied excess pore pressure ratios for assessing the liquefaction of fibre-reinforced sand also has been discussed. The test results reveal that the loose sand without reinforcement is highly susceptible to static liquefaction under undrained triaxial compression, while the inclusion of fibers prevents the development of static liquefaction in the sand samples. The presence of fibers significantly alters the effective stress path experienced by the sand skeleton and thereby influencing its liquefaction response. The conventionally defined excess pore pressure ratio (r(u)) based on the principle of effective stress may provide incorrect indications of liquefaction in fiber-reinforced sand. To address this, the study introduces the newly defined effective excess pore pressure ratio (r(u)') and the skeleton excess pore pressure ratio (r(u)(*)), which offer improved indications of liquefaction in reinforced sand. By invoking a constitutive framework based on the rule of mixture, the stress contributions of fibers are quantified. The skeleton excess pore pressure ratio takes into account stress contributions of the fibers and reveals how the external load is shared among the fibers, sand skeleton and the pore water. When r(u)(*) = 1 is attained, the effective mean stress carried by the sand skeleton drops to zero, resulting in liquefaction of the fiber-reinforced sand.