This predictive fire model uses CAT scans, advanced computing to forecast wildfires

This predictive fire model uses CAT scans, advanced computing to forecast wildfires. | Picture by special arrangement.  

(Subscribe to our Today's Cache newsletter for a quick snapshot of top 5 tech stories. Click here to subscribe for free.)

Combining data from CAT scans with advanced computing, a team of researchers at Stanford University have developed a predictive fire model to forecast where wildfires might strike.

CAT scanners are used for human body scans, however the researchers have used it to understand the process of smouldering – the state of burning without flame.

Smouldering may appear harmless, but the smouldering logs are capable of reigniting, while the residual glowing sparks could be carried in the air, and can lead to wildfires in different areas, a Stanford release explained.

The team used X-ray Computed Tomography (XCT), to get three-dimensional images of wood structures less than a millimetre in scale as they smoulder and eventually catch fire. It also allows them to measure the temperature of the surrounding flame, it added.

The predictive fire model uses information about the flammability of various materials, landscape data, and weather data, like relative humidity in the air and wind patterns.

Also read | Google expands flood warning feature to all of India

Then, the algorithm runs countless permutations to predict how different combinations alter a fire’s spread, the release noted.

“For wildfire risk assessment or if you’re a firefighter, what you need is an accurate prediction about how fast the local fuel – the trees and plants nearby – will burn. Matthias Ihme,” a Mechanical Engineering Professor at Stanford University, said. “We’ve analysed this fuel in a new way that allows us to do just that.”

The research team also wants to gather wood samples from around the world, analyse them using XCT and compile a detailed database of various fuels.

“We’ve been working on improving the fidelity of the model, adding more complex physics into it,” Matt Bonanni, a Stanford graduate student, says. “It’ll only get better.”

This article is closed for comments.
Please Email the Editor

Printable version | Oct 27, 2020 11:32:43 AM |

Next Story