Prediction tunnel settlement in shield tunnels during the operation period has gained increasing significance within the realm of maintenance strategy formulation. The sparse settlement data during this period present a formidable challenge for predictive Artificial Intelligence (AI) models, as they may not handle non-stationary relationships effectively or have the risk of overfitting. In this study, we propose an improved machine learning (ML) model based on sparse settlement data. We enhance training data via time series clustering, use time decomposition to uncover latent features, and employ Extreme Gradient Boosting (XGBoost) v1.5.1 with Bayesian Optimization (BO) v1.2.0 for precise predictions. Comparative experiments conducted on different acquisition points substantiate our model’s efficacy, the in-training set yielding a Mean Absolute Error (MAE) of 0.649 mm, Root Mean Square Error (RMSE) of 0.873 mm, Mean Absolute Percentage Error (MAPE) of 3.566, and Coefficient of Determination (R2) of 0.872, and the in-testing set yielding a MAE of 0.717 mm, RMSE of 1.048 mm, MAPE of 4.080, and R2 of 0.846. The empirical results show the superiority of the proposed model compared to simple ML models and a complex neural network model, as it has a lower prediction error and higher accuracy across different sparse settlement datasets. Moreover, this paper underlines that accurate settlement predictions contribute to achieving some Sustainable Development Goals (SDGs). Specifically, preventive tunnel maintenance strategies based on predictive results can enhance tunnels’ long-term operational reliability, which is in accordance with SDG 9 (Industry, Innovation, and Infrastructure) and SDG 11 (Sustainable Cities and Communities).
With the rapid development of smart cities, the refined management of urban highway tunnels has put forward higher requirements for the emergency disposal ability of operation and maintenance personnel. This paper proposed a collaborative emergency drill system for urban tunnels using building information modeling (BIM) and an agent-based model. The objectives of this paper are as follows: (1) To help address the challenge of multi-person collaborative intelligent drills in complex emergency scenarios, this system constructed an emergency collaborative drill model and a virtual emergency scenario description method based on trait-based objects (TBOs). (2) To help address the challenge of the organization and integration of multi-source heterogeneous data in complex emergency scenarios, the system established an emergency scenario generation method through lightweight BIM data, standard emergency plan documents, and virtual emergency scenario data. The system was successfully applied to the Hongmei South Road Tunnel in Shanghai, China. The feasibility of the proposed system provided practical help for tunnel emergency management and was extended to other urban tunnels in Shanghai.