A multimodal flood prediction architecture based on cloud-edge collaboration
Summary
No summary yet. VIRAT can read this paper and write a plain-language summary of its aim, methods, key findings and limitations.
Summarise with VIRAT Free to try with your Science Catalogs account.Abstract
The frequent occurrence of flood disasters is found to pose a serious threat to socio-economic stability and residents' property security, and the improvement of prediction accuracy and timeliness is identified as an urgent issue. To address this problem, a multimodal flood disaster prediction architecture based on cloud-edge collaboration was proposed, which overcame the bottlenecks of traditional cloud computing in terms of transmission latency, computational load, and real-time performance. In this architecture, raw data was collected by IoT devices, a local real-time prediction model based on LSTM networks was constructed at the edge layer to generate local prediction results, and a global fusion model based on Transformer networks was built in the cloud to capture long-range dependencies and produce global results. Moreover, an adaptive weight adjustment algorithm was designed to optimize the coordination between local and global outputs. Experimental results show that the proposed architecture outperforms traditional centralized cloud computing in prediction accuracy, data transmission latency, actual bandwidth rate, and edge computing resource utilization. It is concluded that cloud-edge collaboration and multimodal fusion effectively enhance the accuracy and timeliness of flood disaster prediction, providing new insights for disaster prevention, mitigation, and scientific decision-making.
Fields of Study & Subjects
IoT and Edge/Fog Computing
Hydrological Forecasting Using AI
Energy and Environmental Systems
Publication details
- Journal / source
- DOAJ (DOAJ: Directory of Open Access Journals)
- Publication date
- 1 March 2026
- Language
- ZH