Simulation / Modeling / Design

GPU-Accelerated Supercomputer Assists Firefighters in California

The recent wildfires in California spread at an alarming rate — forcing people to evacuate within minutes of first learning about it. To help battle future fires and possibly save lives, California firefighters are leveraging the power of GPU-accelerated supercomputers to predict the possible trajectories a wildfire could take.
Using the Comet supercomputer at the San Diego Supercomputer Center at the University of California, San Diego, developers from the center developed WIFIRE, a model that adds real-time data to determine a wildfire’s trajectory.
The model integrates satellite data and remote sensor data with computational techniques in signal processing, visualization, modeling, and data assimilation to predict a wildfire’s rate of spread.
“WIFIRE may be used by government agencies in the future to save lives and property during wildfire events, test the effectiveness of response and evacuation scenarios before they occur and assess the effectiveness of high-density sensor networks in improving fire and weather predictions,” the developers stated.
Right now, Cal Fire is using the supercomputer to get real-time data for the Woolsey Fire in Southern California. The agency says it is using the data in an experimental manner, however, the tool could be more widely adopted in the future.
“The more information we can get and decisions we can make based on technology is obviously the future,” Jonathan Cox, division chief with Cal Fire, told NPR.

The Comet Supercomputer is comprised of hundreds of NVIDIA Tesla P100 GPUs.
The project is funded by the National Science Foundation and is still in the development phase.
The developers say their tool was designed to help first responders analyze and visualize data and make it available in a format that informs and assists them before, during, and after a wildfire event.
A version of the model is publicly available on the University of California, San Diego website.

Discuss (0)