The primary objective of the project was to develop a software algorithm that can uniquely identify the electromagnetic pulses that may precede an earthquake by days to weeks. The algorithm would need to successfully learn how to distinguish between false-positive signals – from sources like lightning – and those originating from from the Earth’s crust.
3 TB of data including known/identified quakes to help ‘train’ algorithms, and many data-sets with hidden quakes to test/validate algorithms were provided to the competitors.
At the end of the project the top 6 contestants identified between 1-7 earthquakes with statistically significant scores. Ultimately Quakefinder hopes to incorporate the best features of these and other external algorithms now in development. These combined and tested algorithms will become part of their daily search for earthquakes using data from all our 165 instrument sites in California and international locations.
*Analysis provided by client & the Harvard Crowd Innovation Lab