Accurate tunnel deformation prediction is critical for mitigating construction risks and ensuring tunnel stability. This study introduces a novel hybrid model integrating long short‐term memory (LSTM) networks and random forest (RF) to enhance the precision of tunnel deformation predictions during construction. Bayesian optimization was utilized to fine‐tune model parameters, ensuring optimal performance. Validated with multidepth data from the Yangjiashan highway tunnel in China, the hybrid model demonstrates remarkable adaptability to complex geological conditions. The results show that the LSTM‐RF model achieves a mean square error (MSE) of 0.0025, a root‐mean‐square error (RMSE) of 0.0052, and a coefficient of determination ( R2 ) of 0.9810, outperforming individual models and other hybrid frameworks in predicting deformation trends. By effectively capturing temporal dependencies and modeling nonlinear residuals, the hybrid model provides a robust and reliable solution for improving safety and efficiency in tunneling projects. These findings emphasize the potential of hybrid approaches for geotechnical engineering, particularly in predictive maintenance and infrastructure monitoring.
Reinforced soil technology is widely applied in slope stabilization, yet the optimal configuration of reinforcement remains a key design challenge. This study presents a comprehensive investigation of vertical rib‐reinforced and inclined‐reinforced geogrid layouts through scaled physical model tests (1:10) and finite element simulations using MIDAS GTS. Results show that (1) vertical rib reinforcement improves ultimate bearing capacity by 24.6% and reduces settlement by 45.4%, outperforming ordinary horizontal reinforcement (18.1% capacity increase); (2) inclined reinforcement at a 5° angle further enhances performance, achieving a 31.8% increase in bearing capacity and a 57.8% reduction in settlement; (3) numerical simulations reproduce experimental trends with minor displacement underestimation, attributed to idealized soil–geogrid interfaces. This study provides the first integrated comparison of vertical rib and inclined reinforcement strategies, establishing a practical and effective design reference for reinforced soil slopes in loess regions.