Yellowstone National Park has several geothermal areas of the park including geyser basins, as well as, hot springs and mud pots. The Norris Geyser Basin was able to decode volcano’s messages to Phil Dawson, a geophysicist with the U.S. Geological Survey in California, using voice recognition software that he customized.

Scientists and researchers have been measuring the activity in the park for years estimating anywhere between 200 and 250 geysers eruptions in Yellowstone each year making it the place with the highest concentration of active geysers in the world. However, the main problem has always been prevention.

Dawson said that he was researching and working with voice recognition software when he realized that it could be used to help with seismic activity. Dawson worked together with Carmen Benitez, a Spanish researcher, to decode the messages from the geysers in hopes to learning something new.

The various geyser basins are located where rainwater and snowmelt can collect on the ground and get heated by the Yellowstone hotspots. At any time, the geysers can then erupt at the surface. Dawson said his voice software showed patterns that can now be interpreted.

“The cool thing about volcanoes is very often there are repeated signals, indicating that the source process is the same. What that means is, in the context of speech recognition, it’s very easy to see them as a sentence or a song,” said Dawson. This means that if Dawson uses the software and sees the same pattern appearing he might be able to predict Mother Nature.

Dawson said he was able to work with Benitez to research the data even further being able to pick out specific “words” the volcano was speaking using this new technology to better monitor volcanic activity. “It’s very common in volcanic systems that you see the same ‘word’ over and over again…we want to be able to do efficient monitoring so that when things begin to get active, we can protect people,” said Dawson.

“Its very exciting science,” said Hank Heasler, Geologist for Yellowstone National Park. “Who would have thought that voice recognition software could be applied to this kind of problem?”

Heasler said some of Dawson’s data was already known and collected by other park researchers. However, Heasler confirmed that Dawson’s new technique might have collected additional data and seismic activity from spots on the park researchers were not measuring. “To me this study very clearly illustrates how much more we have to learn about this system. Nature is very complex, fascinating system and this study helps point that out,” said Heasler.