Open-Source Flood Analytics Information System (FAIS): Release Version 4.0

Floods are on the rise globally with the frequent recorded events occurring during the past few years in the US alone. These extreme events pose a considerable threat to human life and result in destructive damage to property, critical infrastructure, and communities. The aim of this presentation is to present the release version of Flood Analytics Information System (FAIS) as a data engineering and analytics system. FAIS application is smartly designed to integrate crowd intelligence, deep learning (DL) algorithms, and natural language processing (NLP) of tweets to provide early warning with the aim to improve flood situational awareness and risk assessment. FAIS has been Beta tested during major hurricane events in the southeast US where successive storms made extensive damage and disruption. The prototype overall includes 12 new python packages that are seamlessly assembled to provide map-based visualizations and actionable information to users/stakeholders. The developed algorithms include a Twitter Streaming bot (functions on both iOS and Mac), data fusion, DL and data analytics algorithms, and various Internet of Things Application Programming Interfaces (IoT APIs) to gather batch and real-time collection of data generated by various data providers. As a recent upgrade to the original package, four data analytics algorithms were developed for flood image label detection and classification. This presentation will discuss the FAIS functionalities and how this tool can be used as a community-driven data analytics pipeline. This research is funded by the US National Science Foundation (NSF).