On Thursday, IBM plans to announce its work with university researchers to instantly process data for wildfire prediction — changing the delay time from every six hours to real-time. This will not only help firefighters control the blaze more efficiently, but deliver more informed decisions on public evacuations and health warnings.

The new joint project with the University of Maryland, Baltimore County allows for researches to analyze smoke patterns during wildfires by instantly processing the massive amounts of data available from drone aircraft, high-resolution satellite imagery and air-quality sensors, to develop more effective models for smoke dissipation using a cluster of IBM BladeCenters and IBM InfoSphere Streamsanalytics.   Today analysis of smoke patterns is limited to weather forecasting data, observations from front line workers and low resolution satellite imagery.  This new ability will provide fire and public safety officials with a real-time assessment of smoke patterns during a fire, which will allow them to make more informed decisions on public evacuations and health warnings.

Researchers expect to have a prototype of this new system available by next year.