This post is also available in: עברית (Hebrew)
The Seismological Laboratory at the University of California Berkeley has released a new app: MyShake. The app isn’t meant for at-home Zumba hopefuls, but at gathering seismic data measurements recorded by the users’ smartphones and delivering it to an Internet of Things backend platform. At the backend, the data is analysed to evaluate seismological conditions and to make predictions to the likelihood of earthquakes in a given region.
The app is available for Android smartphones so far, but an iPhone version is in the works. Utilising data from the smartphones’ sensors, the app records earthquake shaking. UC Berkeley hopes that by creating a wide network of input nodes, they could one day provide warnings ahead of earthquakes.
“Just a few seconds’ warning is all you need to ‘drop, take cover and hold on.’ Based on what social scientists have told us about past earthquakes, if everyone got under a sturdy table, the estimate is that we could reduce the number of injuries in a quake by 50%.,” Professor Richard Allen from the UC Berkeley Seismological Laboratory told BBC.
To distinguish seismic activity from the normal movements of a smartphone user, the app “relies on a sophisticated algorithm to analyse all the different vibrations picked up by a phone’s onboard accelerometer. This algorithm has been “trained” to distinguish between everyday human motions and those specific to an earthquake… In simulations, the app detects a quake correctly in 93% of cases.”
At this stage, the app only collects data and sends it to the MyShake central server for analysis. “But the end goal,” Allen said, “is for future versions of the app to send warnings back to individual users.”