NASA is looking to a community of more than 800,000 data scientists and developers to find a way to detect earthquakes before they happen.
With the help of Appirio’s TopCoder community, NASA is in the midst of a two-week challenge in which users are tasked with creating algorithms that could uncover electromagnetic pulses that may precede earthquakes.
The relationship between electromagnetic pulse and earthquakes is highly debated among those who research the natural disasters. One theory suggests that fracturing rock in the Earth’s crust creates an electrical pulse that travels to the surface and makes a small change in the local magnetic field. However, researchers often have to deal with fuzzy data due to a number of natural and human-made electromagnetic "noise" sources, such as lightning, solar storms and commuter trains.
“Developing a reliable approach that can separate potential earthquake-induced electromagnetic pulses from the myriad of natural and anthropogenic sources has been a significant challenge,” said Craig Dobson, program scientist at NASA Headquarters in Washington, in a release.