Providing a greater precision of Situational Awareness of urban floods through Multimodal Fusion
作者：
Highlights：
• We identified flood-prone areas in the city of São Paulo (Brazil).
• Empirical methods for setting the flooded area’s range are better than Semivariogram.
• Our multimodal fusion model can obtain Situational Awareness of urban flooding.
• Our hybrid multimodal fusion model is better than classic multimodal fusion models.
• Our hybrid multimodal fusion model is more precise than the unimodal systems.
摘要
•We identified flood-prone areas in the city of São Paulo (Brazil).•Empirical methods for setting the flooded area’s range are better than Semivariogram.•Our multimodal fusion model can obtain Situational Awareness of urban flooding.•Our hybrid multimodal fusion model is better than classic multimodal fusion models.•Our hybrid multimodal fusion model is more precise than the unimodal systems.
论文关键词：Multimodal fusion,Text classification,Floods,Situational awareness,Disaster management,Machine learning
论文评审过程：Received 18 January 2021, Revised 31 July 2021, Accepted 15 September 2021, Available online 12 October 2021, Version of Record 20 October 2021.
论文官网地址：https://doi.org/10.1016/j.eswa.2021.115923
