/* ---- Google Analytics Code Below */

Tuesday, August 09, 2022

Computational Method Can Improve Explosion Detection

More sensor applications. 

 Computational Method Can Improve Explosion Detection

University of Alaska Fairbanks Geophysical Institute

Rod Boyce, July 22, 2022

The University of Alaska Fairbanks' Alex Witsil and colleagues have developed a method to better detect explosions by training computers on artificial explosion signals. Witsil explained, "We used modeling software to generate 28,000 synthetic infrasound signals, which, though generated in a computer, could hypothetically be recorded by infrasound microphones deployed hundreds of kilometers from a large explosion." The signals reflect atmospheric variances, which can change an explosion's signal regionally or globally as sound waves spread, complicating the ability to detect a remote blast's origin and type. The machine learning technique uses hundreds of single-element infrasound microphones already deployed worldwide, enabling them to detect more nuanced signals in real time.  ....' 

No comments: