The accuracy of Seismic Landslide Susceptibility Maps (SLSMs) is imperative for the prevention of seismic landslide disasters. This study enhances the precision of SLSMs by integrating nine distinct machine learning methodologies with the GeoDetector version 0.0.4 tool to filter both numerical and physical factors contributing to landslide susceptibility. The dataset comprises 2317 landslide instances triggered by the 2013 Minxian Ms = 6.6 earthquake, from which redundant factors were pruned using the Recursive Feature Elimination technique. Subsequent evaluations of the optimized factors, both individually and in combination, were conducted through Frequency Ratio analysis and Factor Interaction assessment. The study juxtaposes the Area Under the Receiver Operating Characteristic Curve (AUC) and the accuracy of nine machine learning models before and after factor optimization. The findings indicate an increase in AUC from a maximum of 0.989 to 0.992 in the Random Forest model, and an 8.37% increase in AUC for the SVM model, signifying a notable enhancement in the stability across all models. The establishment of the SLSM notably elevated the frequency ratio in high-risk zones from 50.40 to 85.14, underscoring the efficacy of combining machine learning and detector optimization techniques in sustainable practices. This research proposes a universal framework aimed at eliminating redundancy and noise in SLSMs and hazard risk assessments, thereby facilitating sustainable geological disaster risk management.

Traditional bridge monitoring and damage identification techniques typically rely on full-bridge coverage of sensors, such as displacement or strain sensors. However, this approach proves economically unfeasible for the vast numbers of small- and medium-span continuous beam bridges. In response to the need for rapid damage identification and integrity assessment of continuous beam bridges, a novel bridge safety monitoring method relying solely on bearing reaction forces is proposed. Firstly, the analytical expressions for the bearing reaction influence lines of a three-span continuous beam bridge under damage conditions were derived. Secondly, a rapid structural damage localization method based on the bearing reaction influence lines was proposed. Finally, feasibility and applicability were confirmed through numerical simulations and experimental validation. Additionally, the discussion includes the implementation of the warning classification and threshold setting using data from bearing force monitoring. The research demonstrates that utilizing a limited amount of bearing reaction force information can not only identify damage areas in a “non-full-coverage” manner, but also facilitates early warning and the integrity assessment of bridges. In the future, there is potential for large-scale application in medium- and small-span continuous beam bridges.

Tunnel structures account for la large proportion of the structures in mountain highway transportation systems. Most tunnels are located in remote areas in which the geological conditions are complex and harsh and in which the layout of the management facilities along the way is complex. Thus, the management and maintenance costs of various facilities are expensive, the cost of fire safety operations and management is high, and disaster prevention and rescue have a difficult time meeting the objective requirements. Therefore, it is urgent to carry out research on quasi-unmanned operations and intelligent remote monitoring. This study firstly proposes a fire safety intelligent monitoring framework for quasi-unattended tunnels. By making full use of various intelligent sensor monitoring data in the tunnel, the tunnel operation status can be grasped in real time. Then, a fire safety evaluation model can be established through the analytic hierarchy process (AHP), and, based on the monitoring data, the AHP model parameters can be evaluated to realize the real-time evaluation and management of tunnel fire safety. Finally, on the basis of the fire safety intelligent monitoring system and the fire safety evaluation system, an adaptive fire rescue plan formulation scheme is proposed for the quasi-unattended tunnels so as to provide guaranteed support for the rapid automatic response of tunnel fire protection and to provide technical data support for the design and realization of intelligent and efficient tunnel management

Single-pier, dual-bearing bridges are susceptible to effects such as concrete creep, thermal expansion, and uneven foundation settlement. When combined with eccentric loading from heavy vehicles, these factors collectively can significantly increase the risk of bridge overturning. To address this risk, a comprehensive analysis of the bridge overturning mechanism was conducted. Considering the current limitations of health monitoring in bearing reaction force (BRF) measurement and risk mitigation, an adjustable intelligent bearing based on pressure sensing and self-locking principles was developed. Its mechanical performance was analyzed under the most unfavorable load conditions. To further validate the approach, a specific experimental bridge was used as a case study. The effectiveness of the force measurement and height adjustment functions was evaluated through moving load experiments. The results showed that the force measurement function accurately captured dynamic BRF changes within a precision range of ±0.1% FS and demonstrated high sensitivity to instantaneous impact effects. The height adjustment function achieved a reaction force change of up to 40 kN within the maximum adjustment range of 1.2 mm, significantly improving the load distribution of the bridge. These findings validated the reliability of the proposed intelligent bearing in real-time monitoring and proactive risk adjustment. This effectively overcomes the limitations of existing bearings, which only perform passive monitoring. Overall, it achieves the real-time monitoring of BRF and proactive control of bridge overturning risks.