In response to new challenges, the application characteristics of dynamic network algorithms were reviewed. These challenges were posed by complex and diversified urban emergency scenarios. Heterogeneous data fusion and algorithmic collaboration were involved. Additionally, approaches for multi-algorithm collaboration and integration were explored. Firstly, based on 128 publications from the past five years in the Scopus database, four major research themes: path planning, traffic regulation, risk prevention, and resilience analysis, which were identified using keyword frequency statistics and cluster analysis. Then, through content analysis, four core algorithm categories: planning, simulation, clustering, and deep learning were summarized. Their theoretical frameworks and task adaptation logic were examined in conjunction with empirical data, simulations, and hybrid data sources. Finally, a multidimensional evaluation system was constructed to comparatively assess the applicability, strengths, and limitations of different algorithms across various emergency scenarios. The results show that multiple algorithms are integrated in application, which include planning, simulation, clustering, and deep learning. This integrated approach enables a multidimensional response to urban emergency management tasks. Such tasks involve path planning, traffic regulation, risk prevention, and resilience analysis. The adaptability of emergency systems are enhanced. The robustness of these systems is also improved. Data-driven intelligent algorithms further improve the responsiveness of urban road networks, supporting real-time strategy adjustment and resource optimization. Future development should focus on the construction of intelligent collaborative architectures for algorithm integration and coupled analysis across multiple networks, to advance the efficient application of dynamic network algorithms in multi-scenario emergency management.

To enhance the immersion and effectiveness of fire training and improve the interactive experience of acquiring fire-extinguishing skills, a VR particle fire-extinguishing algorithm based on a heat transfer was proposed and developed on a VR platform. First, a thermodynamic interaction model at the particles level was constructed by introducing a heat transfer mechanism to simulate the energy transfer process between extinguishing agent particles and flame particles. Then, the random walk algorithm was combined with the vortex dynamics model to enhance the natural behavior of the particle system during spraying, diffusion, and turbulence, thereby improving the dynamic realism of flame propagation and fire suppression. Finally, a VR-based fire training system featuring multiple typical fire scenarios was developed based on the Unity 3D engine, and simulation experiments were conducted to validate the matching relationship between different types of fire extinguishers and fire categories. The results show that the collision frequency and energy attenuation curves between extinguishing particles and flame particles vary significantly depending on the extinguisher type and its applicable scenario. Furthermore, the flame decay rate governed by the heat transfer model is closely related to the type of fire extinguisher, effectively reflecting the physical patterns of fire suppression processes.

To characterize the performance curve of urban bus systems under different rainfall intensities, a resilience measurement model for urban bus system operations was constructed. Taking the bus system in the main urban area of Yangzhou as a case study, the operational resilience of transit networks across different regions and individual routes were analyzed. Building upon aforementioned resilience measurement results, the operational status of bus stops under different resilience levels was further quantified. The spatio-temporal patterns of resilience evolution within the integrated "network-route-stop" hierarchy were elucidated. The results show that during rainfall events, urban bus systems exhibit varying performance disturbances across different regions. The variations in the absorption, recovery, and adaptation capacities of bus systems across different regions, significant spatial heterogeneity in resilience is observed, resulting in pronounced spatial heterogeneity in operational resilience. The combined effect of morning peak hours and extreme rain events has a notable impact on bus operational resilience. It is also found that the operational resilience of bus routes varies across different regions under rainfall events of varying intensity, and different levels of resilience lead to significant differences in the performance losses of bus stops. Notably, under low resilience conditions, the reliability of stops decreases (an increase in arrival intervals and a decrease in stop punctuality).

In order to improve the ability of accident prevention and risk control of urban drainage networks, first of all, based on the indicators from the four aspects of "human-material-management-environment", 19 assessment indicators were obtained to construct the risk assessment index system of urban drainage pipe networks, and a risk evaluation index system for urban drainage networks was established accordingly. Subsequently, a model of urban drainage networks was constructed by integrating fuzzy theory and BN. Triangular fuzzy numbers were introduced to quantify the scores of experts. Weights were assigned according to differences in professional titles and working years, and α-weighted valuation method was adopted to transform fuzzy evaluations into clear probabilities. Thus, a risk evaluation model for urban drainage networks was obtained, and forward and reverse reasoning of BN was conducted to calculate the posterior probabilities of key nodes. Finally, taking the drainage network of a certain urban area as an example, the risk level of the drainage network in a specific area of the city was evaluated, and investigations were conducted for verification. The results indicate that the model effectively handles uncertainties and subjectivity in the risk assessment process, achieves probabilistic characterization of drainage network risks, and improves the accuracy of evaluation outcomes. External pipe protection is identified as the most critical factor affecting drainage network safety, followed by anti-corrosion measures and joint methods. The overall safety performance of the urban drainage network is found to be satisfactory, with risks remaining within controllable limits. Comparative analysis with historical monitoring data and fault records confirms the practicality and reliability of the model.

In order to enhance the emergency response efficiency of fire rescue zones, a block accessibility-based method for dividing fire rescue territories was proposed. Basic data were obtained through block boundary extraction, as well as the localization of fire stations and demand points. Multi-period real-time traffic data were acquired via an online map to calculate the integrated travel time from each fire station to every block unit, which served as the basis for division. Blocks were assigned to the corresponding fire station based on the shortest accessibility time. Finally, an optimized zoning scheme and an evaluation of the overall regional accessibility were output. A case study was conducted in the HN-FR area, involving 8 fire stations and 10 067 demand points. A total of 542 block units were extracted, and analysis was performed using 618 483 data samples across 29 scenarios. Results indicate that the overall accessibility time for the HN-FR region is 435.96 s, reflecting relatively poor fire rescue accessibility. Furthermore, significant disparities are observed in the areas of the eight fire station territories, ranging from 0.37 to 12.36 km². This variation is primarily attributed to the proximity of some fire stations to the boundary of HN-FR, resulting in minimal coverage capacity.

In order to address the challenges of inaccurate region segmentation and insufficient detail restoration in flood disaster recognition models within complex urban environments, AttResU-Net, an enhanced U-Net semantic segmentation model integrating residual networks and a self-attention mechanism was proposed. Building upon the classical U-Net architecture, the model employed a deep residual network as the encoder to strengthen feature representation. Simultaneously, self-attention mechanisms were incorporated into the decoder to enhance response capability on key flood-related regions. A comprehensive training and testing pipeline was established. The improved AttResU-Net was trained and evaluated on the FloodNet dataset, which contains diverse and complex urban environmental categories. Quantitative metrics and qualitative visual results demonstrate the model's superior performance, achieving a mean pixel accuracy (mPA) of 79.75%, pixel accuracy (PA) of 90.01%, and mean precision (mPrecision) of 81.78%. Comparative experiments against state-of-the-art models reveal that AttResU-Net attains significantly higher segmentation accuracy and global recognition capability, particularly for urban features such as trees, water bodies, roads, and buildings.

In order to enhance maritime emergency rescue efficiency and reduce casualties, a systematic safety design strategy for maritime casualty disposal cabins was proposed. CTA was first used to identify rescue personnel's core needs during critical tasks. The Kawakita Jiro Method method and Analytic Hierarchy Process (AHP) were then used to prioritize these needs. Quality Function Deployment (QFD) was used to translate them into design elements, and Axiomatic Design (AD) was used to map functional requirements to design parameters. Results show that the integrated CTA-QFD-AD approach effectively identifies functional requirements and safety design elements. Optimizing key factors, such as ergonomic dimensions, spatial layout, Color-Material-Finish (CMF), environmental interfaces (lighting, noise, vibration), and tool/information interfaces, can significantly improve human-machine efficiency and ensures rescue safety.

To remedy the fragmented command tiers, a weak data-to-decision link and poor dynamic adaptability, which have long limited the effectiveness of China's emergency-response system, an integrated framework based on digital-twin technology was investigated. A generic four-tier, five-step model—comprising an emergency-command center, on-site command post, rescue teams and individual rescuers, together with the steps Sense, Simulate, Strategize, Decide and Act—was established and extended to the S3DA2 framework. A cost-minimization formula for optimal decision making was derived. Building on this framework, an emergency digital-twin battlefield technology system was established, encompassing multi-source data fusion, twin modelling, fluid-solid-coupled/artificial intelligence hybrid simulation and multi-objective decision optimization. A fluid-solid coupling, multi-agent rescue simulator was developed and validated with the 2024 Tuanzhou Dyke breach on Dongting Lake, enabling a real-time closed loop between the physical scene and its virtual replica. Results show that breach-width predictions deviate by less than 10%, total sealing time is reduced from 82 h to 52 h, and the estimated rock-fill demand of 5.9 × 10⁴ m³ matches field measurements.

In order to improve the efficiency of emergency rescue and reduce accident losses in chemical industrial parks, this study comprehensively considered the risk of chemical parks and the overall risk of emergency supplies, divides the cost of emergency rescue into the cost of construction of emergency supplies reserve, storage cost and transportation cost, and established a model for selecting the site of emergency material reserve in chemical parks. The model aims to minimize the overall risk, minimize the cost of emergency rescue and optimize the coverage of the reserve to the demand point. Taking a chemical industrial park in Tianjin as an example for validation analysis, the model was solved using the NSGA-II algorithm. When constructing different numbers of emergency material storage within the chemical industrial park, the optimal solutions for the location, cost, risk, and coverage of these storage facilities were obtained. The research results show that the model converges stably within 200 generations. As the amount of emergency material storage increases, investment costs continue to rise, coverage gradually improves, risks are significantly reduced in the early stages, and stabilize in the later stages. The model can generate multiple site selection schemes, effectively addressing the challenge of balancing the "risk-cost-coverage ratio" in the site selection process for emergency material storage within chemical industrial parks. This helps decision-makers make more scientific and reasonable decisions in complex emergency material storage site selection issues based on different preferences.

In order to enhance emergency response capabilities and the service efficiency of shelter systems in rural areas, this study adopted an optimal supply-demand allocation model integrated with Geographic Information System (GIS) software (ArcGIS) to evaluate the accessibility of village-level emergency shelters and township-level short-term shelters in northern Henan province. Key factors influencing shelter site selection were identified to construct a spatial suitability evaluation index system. Using this system, we assessed the spatial distribution of emergency shelters in Xicun town and proposed optimization strategies for the shelter system. The results reveal a significant supply-demand imbalance characterized by poor accessibility, partial overload of village-level shelters, and an irrational distribution with severe shortages of township-level shelters. The suitability evaluation indicates a clear north-south disparity, with higher suitability in the south. After implementing optimization measures—including adding village-level shelters and upgrading those in highly suitable areas—both the balance between supply and demand and overall accessibility are improved across the two-tier shelter system in Xicun town.