FDL 2019



Flooding is the most common natural disaster in the US and is the deadliest weather related disaster, with over 82 deaths a year on average. Flood waters often conceal sewerage, sharp objects and downed power lines. Urban developments are more vulnerable to floods as impermeable surfaces reduce the ability of flood waters to be absorbed by the landscape.

Can AI improve our capabilities to forecast and respond to floods using orbital imagery to better predict the permeability of surfaces, the likelihood of flash flooding or a burst river? Can ML techniques coupled with USGS ground observations and social data be used to better understand how to save lives in terms of better predictive models before and during a flooding event?