A recent study published in the high-impact journal Science Advances has revealed that a machine learning algorithm uncovered approximately 10 times more earthquakes in the Yellowstone caldera over a 15-year period than previously recorded. This discovery significantly improves our understanding of volcanic and seismic systems, thanks to better data collection and systematic analyses.
The Yellowstone caldera, located in Wyoming, Idaho, and Montana, is one of Earth’s most seismically active networks of volcanic activity. A caldera is formed when a volcano erupts and the magma chamber beneath it empties, leading to the collapse of the land above. The new study has added 86,276 earthquakes to the historical catalogue for the Yellowstone caldera, spanning from 2008 to 2022.
The researchers found that more than half of the recorded earthquakes were part of earthquake swarms – groups of small, interconnected earthquakes that spread and shift within a relatively small area over a short period. This is distinct from aftershocks, which are smaller earthquakes that follow a larger mainshock in the same general area.
Machine learning was used to re-examine historical data and detect seismic events that would have been missed by manual inspection. The algorithm has sparked a new era of data-mining in seismology, allowing researchers to revisit vast amounts of historical waveform data and gain insights into current and previously unknown seismic regions around the world.
The study also revealed that earthquake swarms beneath the Yellowstone caldera occurred along relatively immature fault structures, which were characterized by fractal patterns. These patterns are geometric shapes that exhibit self-similarity and can be seen in nature, such as coastlines and snowflakes. The researchers believe that the mix of slowly moving underground water and sudden bursts of fluid caused these earthquakes.
The findings of this study have significant implications for understanding volcanic and seismic systems, improving safety measures, informing the public about potential risks, and guiding geothermal energy development away from danger zones.
Source: https://phys.org/news/2025-07-machine-uncovers-earthquakes-yellowstone-caldera.html