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.
Pathogens are commonly present in the human respiratory tract, but symptoms are varied among individuals. The interactions between pathogens, commensal microorganisms and host immune systems are important in shaping the susceptibility, development and severity of respiratory diseases. Compared to the extensive studies on the human microbiota, few studies reported the association between indoor microbiome exposure and respiratory infections. In this study, 308 students from 21 classrooms were randomly selected to survey the occurrence of respiratory infections in junior high schools of Johor Bahru, Malaysia. Vacuum dust was collected from the floor, chairs and desks of these classrooms, and high-throughput amplicon sequencing (16S rRNA and ITS) and quantitative PCR were conducted to characterize the absolute concentration of the indoor microorganisms. Fifteen bacterial genera in the classes Actinobacteria, Alphaproteobacteria, and Cyanobacteria were protectively associated with respiratory infections (p < 0.01), and these bacteria were mainly derived from the outdoor environment. Previous studies also reported that outdoor environmental bacteria were protectively associated with chronic respiratory diseases, such as asthma, but the genera identified were different between acute and chronic respiratory diseases. Four fungal genera from Ascomycota, including Devriesia, Endocarpon, Sarcinomyces and an unclassified genus from Herpotrichillaceae, were protectively associated with respiratory infections (p < 0.01). House dust mite (HDM) allergens and outdoor NO2 concentration were associated with respiratory infections and infection-related microorganisms. A causal mediation analysis revealed that the health effects of HDM and NO2 were partially or fully mediated by the indoor microorganisms. This is the first study to explore the association between environmental characteristics, microbiome exposure and respiratory infections in a public indoor environment, expanding our understanding of the complex interactions among these factors.