How can twitter help engineers assess infrastructure performance: the Colorado floods case

Last year's massive flooding in Colorado's Front Range affected a widespread area, destroyed roads and bridges, blocking access to residential areas for extended periods of time, and washed away homes. Based on a study conducted by the University of Colorado Boulder, the tweets sent during the flooding events played an important role in the preliminary reconnaissance of the infrastructure damage and helped geotechnical and structural engineers to more efficiently spend their time and efforts during their visit to the affected areas.

The particular study is among the first to examine the role of social media in engineering reconnaissance efforts. What differentiates it from past research in information systems is that it specifically focuses on non-emergency professionals, like engineers. In that context, tweets with photos and videos posted during the flood events provided a useful insight for the reconnaissance teams as to the extent and type of damage to different infrastructure systems. Even though the geo-tagged postings, which could be immediately mapped and processed, made up a 1.2 percent of the total tweets, they still composed a fairly accurate geographic distribution and time progression of the damage. A comparison between the damage-map issued by the city of Boulder and the map produced from the geo-tagged tweets comes to verify the above conclusion. 

According to Shideh Dashti, an assistant professor of civil, environmental and architectural engineering at CU-Boulder and co-author of the paper, this type of information acquisition on infrastructure performance is particularly valuable for improving future infrastructure resilience, given the fact that frequently - the Colorado case included - reconnaissance teams cannot access the affected areas immediately after a natural disaster. One of the main issues that engineering reconnaissance teams encounter, is the short amount of time between their safe entrance to an area and the beginning of cleanup efforts, which sweeps away any evidence of infrastructure performance. 

Prof. Dashti's future hope is the creation of a platform that will combine social media and self-reported information from citizens, perhaps through a mobile phone application. "My goal is to eventually feed information on damage distribution back to the user. You provide information and as a result, you gain access to live, mapped information provided by other users during a disaster."