As tunnel engineering continues to advance toward deeper, longer, and more complex projects, the risks encountered during the construction phase have evolved into a combination of various disaster types and the accumulation of multiple contributing factors. Traditional empirical and semi-empirical risk management methods are increasingly revealing shortcomings in terms of timeliness, accuracy, and the ability to process multi-source data. In recent years, driven by advancements in computing power and sensor technology, artificial intelligence algorithms (AI algorithms) such as machine learning and deep learning have been rapidly adopted in tunnel construction risk management. This paper retrieved relevant literature from the Web of Science database covering the period from 2010 to 2025. After rigorous screening, 96 highly relevant papers were selected for bibliometric analysis. This paper systematically reviews research progress from two perspectives: algorithmic models and engineering applications. The review indicates that, in terms of algorithmic models, traditional machine learning, convolutional neural network, recurrent neural network, generative adversarial network, Transformer, and graph neural network constitute a multi-level technical framework encompassing feature representation, risk perception, and intelligent decision-making. In terms of applications, AI algorithms have been widely integrated into typical scenarios such as geological hazard identification and prediction, surrounding rock stability and deformation prediction, rock burst assessment and early warning, lining defect detection and structural safety assessment, construction-induced ground settlement prediction, and tunnel gas and fire hazard prediction, significantly enhancing risk identification and early warning capabilities. However, several challenges remain, including the scarcity of high-quality datasets, the prevalence of noisy, incomplete, and heterogeneous monitoring data, insufficient coupling between model interpretability and engineering mechanisms, limited cross-project transferability, and the lack of integrated management systems for multi-hazard lifecycle control. Based on this, this paper proposes future research directions in areas such as data infrastructure development, integration of mechanism constraints, and multi-hazard collaborative modeling, aiming to provide guidance for the further development of intelligent risk management in tunnel construction.

Dam failure can trigger cascading consequences involving human safety, economic losses, social disruption, and environmental damage. Accurate assessment of these consequences remains challenging due to uncertainties associated with indicator selection, expert judgment, and consequence classification. To address these issues, this study develops an integrated model for evaluating dam failure consequences under uncertainty. A multidimensional evaluation index system consisting of life loss, economic loss, social impact, and environmental impact is established based on existing studies and expert knowledge. The hesitant cloud model is combined with an improved entropy weight method to represent the hesitancy in expert evaluations and to improve the rationality of indicator weight determination. Furthermore, set pair analysis is introduced to evaluate the uncertain relationships between assessment indicators and consequence levels. The proposed model is applied to a reservoir case in China to verify its applicability. The results indicate that the first cumulative membership value, obtained by cumulatively summing the dam failure consequence grades from “slight” to extremely severe”, that exceeds the confidence level λ is 0.7799, corresponding to the severe consequence level. This result is consistent with the comprehensive evaluation obtained using the cloud matter element method. Compared with the traditional method, the generalized set pair potential avoids the case where the opposition degree (c) equals 0. The proposed approach improves the representation of uncertainty and reduces the influence of unclear boundaries among evaluation levels. This study provides a practical decision support tool for dam failure consequence assessment and reservoir risk management.