To develop reasonable emergency material allocation plans for flood disasters, prospect theory was used to characterize the risk perception levels of decision-makers. The reference points for the risk perception of "disaster relief center-disaster site" two-tier decision-makers were defined. A simulation model was constructed using system dynamics to examine the impact of decision-makers' risk perception on the allocation of emergency supplies for flood disasters. The model's validity was verified with case study of 2023 Zhuozhou flood. The study revealed that satisfaction rate at disaster sites and degree of supply-demand imbalance were influenced by risk perception levels of two-tier decision-makers, with a curve representing these effects. The findings show that the risk perception levels of decision-makers at both disaster sites and relief centers have a marginal increasing effect on the disaster site satisfaction rate and supply-demand imbalance. Additionally, under different levels of material availability, the difference in satisfaction rates at disaster sites becomes smaller as decision-makers' risk perception becomes more pessimistic.

In order to explore the emotional expression characteristics of different types of groups under emergencies, and to deeply analyze the influence of gender, temperament type and accident environment on the stress state emotions of the groups, a stress state emotional stimulation test based on facial expression technology was designed. A cohort of 137 participants was exposed to five categories of accident videos. Facial expression data for six basic emotions were collected using FaceReader software, with the Kruskal-Wallis test employed to analyze differences across gender, temperament types, and accident scenarios. A k-means clustering model was further constructed based on arousal dynamic features. The results show that female participants exhibit significantly higher intensities of sadness and fear, whereas males show stronger anger responses. Sanguine individuals demonstrate the most pronounced emotional reactivity, while phlegmatic types achieve the fastest arousal modulation. Fear responses are most pronounced in building fire scenarios. Males outperform females in arousal self-regulation capacity.

In order to address the limitations of traditional earthquake rescue training disaster site, including low simulation fidelity, poor safety, high costs and inadequate quantitative monitoring, this study developed a standardized, full-process earthquake emergency rescue training system using VR technology based on the Unity 3D engine, creating a virtual training scenario for earthquake disaster scenes. While systematically improving rescuers' tactical skills and practical abilities, the system enables quantitative measurement of training effectiveness. On one hand, this paper describes the model building, scene design, functional modules, and interactive design process of the earthquake emergency rescue training system. On the other hand, through pre-test and post-test control experiments, participants' performance is evaluated in terms of theoretical knowledge of earthquake disaster rescue, operational skills, and rescue strategies. The results show that subjects receiving training through this system significantly outperformed the traditional training group in both immediate knowledge acquisition and two-week knowledge transfer efficiency (P < 0.05^*, Cohen's d = 1.0), particularly in skill and strategy learning outcomes (P < 0.05^*, d = 1.23). Meanwhile, subjective experience evaluations confirmed high satisfaction ratings from subjects, corroborating the system's practical efficiency in knowledge transfer performance (P < 0.01^**, 1.1 ≤ d ≤ 3.9).

To address the problems of information distortion, transmission interruption, and response failure in emergency information systems during urban extreme rainstorm disasters, the study first identified five categories of risk—information source, information acquisition, information storage, information processing, and information transmission—from the perspective of the information processing lifecycle. Taking "7·20" Zhengzhou rainstorm event as a case, the risk factors of emergency information were systematically revealed. Subsequently, the connotation of emergency information resilience was defined, and a resilience structure was constructed. Finally, a "risk-resilience" coupling theoretical framework of emergency information resilience for urban extreme rainstorm disasters was established. The Results show that emergency information resilience is formed by the coupled effect of institutional resilience, social resilience, organizational resilience, and physical resilience. The theoretical framework of emergency information resilience consists of four stages. Including scientific construction of information resilience, integration of information risk early warning and response, cutting off the path of information risk diffusion, and enhancing the adaptability of information systems. The theoretical framework of the role of urban mega-rainstorm disaster emergency information resilience constructed in the text significantly improves the absorption capacity, recovery capacity and adaptability of information systems in response to complex disaster impacts.

To quantify the rescue effect of medical supplies delivered to demand points at different times, the concept of rescue utility is introduced, and a rescue utility quantification function was constructed based on the time difference of medical supplies arriving at demand points. On this basis, a path planning model for multi-modal distribution of medical supplies in flood disasters was established with the objective of maximizing total rescue utility and minimizing total distribution time. According to the characteristics of the model, a HNSGA-II was designed for solution. Experiments were conducted using multiple types of examples. The results demonstrate that HNSGA-II achieves a 62% and 29% improvement in total rescue utility compared to the traditional Non-dominated Sorting Genetic Algorithm-II (NSGA-II) and the Multi-Objective Artificial Bee Colony Algorithm (MOABCA), respectively. Additionally, the average satisfaction level of material delivery time is enhanced by 13% and 6.1%, respectively. These findings indicate that HNSGA-II significantly improves emergency rescue outcomes, exhibits superior multi-objective optimization capability, and ensures that disaster victims receive timely and effective treatment under emergency conditions.

In order to effectively predict disasters and evaluate the effectiveness of intervention measures, a multi-disaster coupling evolution intelligent deduction method was proposed. The disaster process, multi-disaster coupling, as well as the advantages and difficulties of evolutionary intelligent deduction, were discussed. The disaster evolution process was described, and an intelligent deduction method was established. Taking the mining process of an open-pit mine as an example, the proposed method was applied for analysis, and its effectiveness was verified. The results show that the multi-disaster coupling process is complex and changeable, with characteristics such as uncertainty, network structure effect and spatio-temporal distribution difference. The system fault evolution theory can provide support for the multi-disaster coupling evolution intelligent deduction from the perspectives of conceptual description, topological structure and mathematical analysis. The evolutionary intelligent deduction method is established, and its steps and mathematical model are provided. This method can qualitatively and quantitatively deduce the multi-disaster coupling evolution process, discover hidden disaster processes and generate emergent knowledge.

To optimize the pathways for cross-regional collaboration in natural disaster management, focused on Yangtze River delta—a pioneering region in cross-provincial collaborative practices—and employed social network analysis and QAP analysis to construct a cross-regional emergency collaboration network for natural disaster response in the area. The study examined both the overall and nodal characteristics of the network to assess the current state of cross-regional emergency collaboration and identify the driving factors behind such cooperation. The results indicate that with the establishment and development of Yangtze River delta emergency management task force, intercity collaboration barriers have gradually diminished, and the emergency collaboration network has become increasingly dense, reflecting more frequent interregional cooperative governance. Provincial governments, represented by the three provinces and one municipality (Jiangsu, Zhejiang, Anhui and Shanghai), serve as the dominant actors in the collaborative network, while municipal governments such as Xuancheng, Jiaxing, and Suzhou act as proactive facilitators. Key factors driving the formation of this cross-regional collaborative governance mechanism include geographical proximity, industrial structure, transportation infrastructure, interprovincial administrative relationships, and historical cooperative ties.

To evaluate the application performance of UAVs and rescue robots in earthquake disaster data acquisition and three-dimensional (3D) modeling, an air-ground collaborative emergency response field experiment was conducted at the Beichuan earthquake site. In the experiment, fixed-wing UAVs were deployed to acquire aerial images covering the entire earthquake-affected area, from which high-resolution top-view images were generated, while rotary-wing UAVs were used to supplement data collection in key local regions. Meanwhile, the NuBot rescue robot was deployed to enter damaged buildings and collect indoor disaster images and 3D point cloud data through real-time video transmission and lidar scanning, and 3D reconstructions of interior building structures and artificially constructed collapse scenes were produced. Based on the acquired 3D geographic information, a human-machine interaction platform was developed using virtual reality technology to support visualization and interactive analysis of 3D scenes.The experimental results indicate that multi-scale image data covering both the overall earthquake-affected area and local regions were obtained and corresponding high-precision real-scene models were generated. Indoor images and 3D point cloud data were collected in complex environments, forming 3D models of interior building structures. The 3D scene data were visualized in the virtual reality system and applied to human-machine interaction analysis.

In order to ensure flight safety and enhance operational efficiency, a classification method for civil aviation pilots' psychological health characteristics was developed based on machine learning clustering algorithms. Firstly, 215 active airline pilots were selected as research subjects. Psychological health data across two dimensions—psychological traits and psychological states—were collected using a pilot psychological competency assessment system. Subsequently, principal component analysis was employed for dimensionality reduction, and the elbow method was utilized to determine the optimal number of clusters. The K-means algorithm was applied to classify the samples into four distinct psychological health categories, facilitating the analysis of psychological characteristic differences among groups. Finally, visualization techniques were implemented based on the clustering outcomes to construct individual and group psychological health profiles. Radar charts were adopted to illustrate the distribution patterns of psychological characteristics across different pilot categories. The psychological health structure of pilots has group heterogeneity and diverse expression patterns. The proposed clustering algorithm can transform pilots' psychological health data into observable group feature portraits, achieving systematic identification and visualization of pilot psychological states at the operational level.

To reveal the co-evolutionary relationship between disease transmission intensity and emotional diffusion rate, based on a two-layer complex network structure, this study integrated the classical Susceptible-Exposed-Infected-Recovered (SEIR) epidemic model with a five-state emotional dynamics framework (S_e-E_e-I_e-G_e-R_e) to construct a coupled dynamics model (SEIR-S_eE_eI_eG_eR_e). Theoretical derivation and simulation validation were conducted using the microscopic Markov chain approach and Monte Carlo simulation. The findings reveal that although reducing the disease infection probability can mitigate the scale of emotional propagation, its inhibitory effect on the peak of emotional propagation remains limited. In contrast, shortening the disease incubation period and improving the recovery rate significantly regulate the spread of negative emotions, exhibiting a two-stage propagation pattern characterized by emotional metabolic hysteresis and the density threshold effect of emotional guides. Furthermore, enhancing individuals' compliance with epidemic preventive measures can effectively delay the spread and reduce the scale of negative emotions through three pathways: blocking transmission chains, reinforcing social norms, and correcting cognitive biases.