In the context of green building and sustainable urban development, understanding the mechanical behavior of structural components like concrete-filled steel tube (CFST) columns is crucial due to their improved load-bearing capacity, energy efficiency, and optimized material usage, which enhance structural resilience and sustainability. This research addresses the complex development of confining stress and its impact on the concrete core (CC) behavior within these columns, which are essential for urban infrastructure. Through extensive numerical studies, this study proposes a model to estimate the confining stress in axially loaded CFST short columns. Study findings reveal that the confinement effectiveness is influenced by variables such as compressive strength (CS) of the concrete, cross-sectional shape, and depth-to-wall thickness percentage. Additionally, the confinement is also significantly affected by the yield strain of steel ε_y/ε_c to the peak strain of unconfined concrete ε_c. A three-dimensional finite element model (FEM) was built for the simulation of the columns’ nonlinear behavior and was rigorously validated against experimental data. This model aids in the design and implementation of more efficient and resilient urban structures, supporting the principles of sustainable construction. The study underscores the importance of structural integrity in sustainable urban development and provides valuable insights for improving the design of green building materials.

Tunnels are essential components of contemporary infrastructure, yet guaranteeing their safety, longevity, and efficiency remains a persistent challenge. Recent breakthroughs in artificial intelligence (AI) and digital twin (DT) technology provide innovative solutions for the real‐time monitoring of tunnel systems, suggesting proactive maintenance tactics and improved safety protocols. This review paper offers a comprehensive examination of the application of AI and DT methodologies in tunnel surveillance. We explore the core concepts of AI and DT and their applicability to structural monitoring, encompassing machine learning, computer vision, and sensor integration. Through the utilization of these AI‐powered technologies, engineers are equipped with unparalleled insights into the state and behavior of tunnels, facilitating the early identification of irregularities and the optimization of maintenance timelines. We discuss the array of AI techniques utilized for the immediate monitoring of tunnel systems, emphasizing their foundations, benefits, and practical uses. Numerous studies have showcased the effectiveness and adaptability of AI‐based monitoring systems in various tunnel settings. Moreover, we address the hurdles and constraints inherent in AI and DT methodologies and suggest strategies for overcoming them, such as data augmentation, interpretable AI, edge computing, and continuous monitoring. Ultimately, the incorporation of AI and DT technologies into tunnel surveillance signifies a paradigm shift, offering substantial advantages over conventional techniques. By adopting AI‐driven monitoring systems, tunnel operators can augment safety, prolong the lifespan of infrastructure, and decrease operational expenses, molding the future of subterranean infrastructure management.

The accurate prediction of rock mass quality ahead of the tunnel face is crucial for optimizing tunnel construction strategies, enhancing safety, and reducing geological risks. This study developed three hybrid models using random forest (RF) optimized by moth-flame optimization (MFO), gray wolf optimizer (GWO), and Bayesian optimization (BO) algorithms to classify the surrounding rock in real time during tunnel boring machine (TBM) operations. A dataset with 544 TBM tunneling samples included key parameters such as thrust force per cutter (TFC), revolutions per minute (RPM), penetration rate (PR), advance rate (AR), penetration per revolution (PRev), and field penetration index (FPI), with rock classification based on the Rock Mass Rating (RMR) method. To address the class imbalance, the Borderline Synthetic Minority Over-Sampling Technique was applied. Performance assessments revealed the MFO-RF model’s superior performance, with training and testing accuracies of 0.992 and 0.927, respectively, and key predictors identified as PR, AR, and RPM. Additional validation using 91 data sets confirmed the reliability of the MFO-RF model on unseen data, achieving an accuracy of 0.879. A graphical user interface was also developed, enabling field engineers and technicians to make instant and reliable rock classification predictions, greatly supporting safe tunnel construction and operational efficiency. These models contribute valuable tools for real-time, data-driven decision-making in tunneling projects.