A team of engineers at Rice University has developed a system that leverages existing flood observation tools — including traffic cameras, water-level sensors and social media data — to sense evolving road conditions during urban flooding events.

The automated data fusion framework developed by the Rice University engineers is called the OpenSafe Fusion — Open Source Situational Awareness Framework for Mobility using Data Fusion — and reportedly leverages current individual reporting mechanisms and public data sources to detect changing road conditions amid urban flooding.

Source: Jeff Fitlow

Such an automated system, the researchers explained, combines insights from real-time sources, thereby potentially revolutionizing flood situational awareness without the need to invest in new sensors.

According to the researchers, the framework relies on data from sources such as traffic alerts, cameras and even traffic speed, and leverages machine learning and data fusion to make predictions about whether a road is flooded or not.

The team suggests that other data sources for the framework could eventually include water-level sensors, citizen portals, crowdsourcing, social media and flood models, for instance.

An article detailing the system, "More eyes on the road: Sensing flooded roads by fusing real-time observations from public data sources," appears in the journal Reliability Engineering & System Safety.