Researchers from IBM, UT Austin Predict Guadalupe River’s Behavior

This week, IBM will announce that researchers from IBM and the University of Texas at Austin can now predict the Guadalupe River’s behavior more than a hundred times the normal speed to provide up to several days warning of a flood.

Floods are the most common natural disaster in the U.S., according to Floodsmart, but flood prediction methods traditionally focus on the main stems of the largest rivers, overlooking extensive tributary networks where flooding actually starts and where flash floods threaten lives and property.

By applying advanced analytics to river systems, weather and sensor data, the researchers can simulate thousands of branches of the Guadalupe at a time, allowing more time for disaster prevention and preparedness. In a single hour, the system can currently generate up to 100 hours of river behavior. IBM's flood prediction technology could be applied to other river systems as well.

Source: IBM