Urban flooding significantly impacts city planning and resident safety. Traditional flood risk models, divided into physical and data-driven types, face challenges like data requirements and limited scalability. To overcome these, this study developed a model combining graph convolutional network (GCN) and spiking neural network (SNN), enabling the extraction of both spatial and temporal features from diverse data sources. We built a comprehensive flood risk dataset by integrating social media reports with weather and geographical data from six Chinese cities. The proposed Graph SNN model demonstrated superior performance compared to GCN and LSTM models, achieving high accuracy (85.3%), precision (0.811), recall (0.832), and F1 score (0.821). It also exhibited higher energy efficiency, making it scalable for real-time flood prediction in various urban environments. This research advances flood risk assessment by efficiently processing heterogeneous data while reducing energy consumption, offering a sustainable solution for urban flood management.
The co-evolution mechanisms between traffic mobility and disease transmission under resource constraints remain poorly understood. This study proposes a two-layer transportation network model integrating the Susceptible-Infectious-Susceptible (SIS) epidemic framework to address this gap. The model incorporates critical factors such as total medical resources, inter-network infection delays, travel willingness, and network topology. Through simulations, we demonstrate that increasing medical resources significantly reduces infection scale during outbreaks, while prolonging inter-network delays slows transmission rates but extends epidemic persistence. Complex network topologies amplify the impact of travel behavior on disease spread, and multi-factor interventions (e.g., combined resource allocation and delay extension) outperform single-factor controls in suppressing transmission. Furthermore, reducing network connectivity (lower average degree) proves effective in mitigating outbreaks, especially under low travel willingness. These findings highlight the necessity of coordinated policies that leverage resource optimization, travel regulation, and network simplification to manage epidemics. This work provides actionable insights for policymakers to design efficient epidemic control strategies in transportation-dependent societies.
The outbreak of diseases is influenced by various factors such as the total amount of resources and individual contacts. However, the co-evolution mechanism between individual travel behavior and disease transmission under limited resources remains unclear. In view of this, we construct a disease transmission model on a two-layer transportation network, considering the comprehensive effects of the total amount of medical resources, inter-network infection delay, travel willingness, and network topology. The simulation results show that increasing the total amount of resources can effectively reduce the disease scale in the transportation network during outbreaks. Additionally, an increase in inter-network infection delay can effectively slow down the disease transmission rate but prolongs the persistence of the disease in the population, affecting the regulation of infection scale by travel willingness. Meanwhile, the more complex the topology of the transportation network, the greater the impact of travel behavior on disease transmission. More importantly, compared to single-factor control, multi-factor combined control is more effective in inhibiting disease transmission. This paper provides new insights into the co-evolution mechanism of traffic travel behavior and disease transmission, and will offer valuable guidance for governments to control epidemic spread through transportation networks.