Earthquakes usually are a cause for concern, but they may actually be a source of energy.
A team of researchers at Penn State University has discovered a surprising link between low-magnitude microearthquakes and the permeability of rocks beneath Earth's surface, potentially uncovering a breakthrough in renewable energy. According to a news release posted on Phys.org, geothermal energy transfer can be scaled into reality by applying machine learning.Â
Microearthquakes, also known as microquakes or microtremors, are earthquakes with low intensity, reaching a magnitude of only 2.0 or less on the Richter scale.
For geothermal energy to be generated, a permeable subsurface must release heat. This heat is released when cold fluids are pushed into the permeable rock. Using this knowledge, the researchers studied the ideal times for energy transfer when looking at the connection to microearthquakes.
The research team conducted a process known as transfer learning — creating a model from one site and applying it to another — to confirm that the connection is based on the physics related to subsurface rocks.
"This suggests seismic monitoring could broadly be used to improve geothermal energy transfer efficiencies across a wide range of sites," said Pengliang Yu, a postdoctoral scholar and the lead author of the study.
Increasing the permeability of subsurface rocks leads to greater chances of energy extraction, such as when hydrocarbons and heat are released to the surface. By understanding microearthquakes, energy could be harnessed more efficiently without endangering the public.
"Machine learning played a key role in uncovering the relationship between seismic activity and rock permeability," professor of engineering science and mechanics and co-author Parisa Shokouhi said.
The study results show promise for alternative forms of energy, especially since the availability of geothermal energy means less dependence on dirty energies.
According to the Office of Energy Efficiency and Renewable Energy, geothermal energy could represent 8.5% of total electricity generation in the United States by 2050.
The research team hopes to use the findings to make geothermal energy commercially available and affordable for customers, allowing access to a clean economy. The team also plans to use its progress with machine learning to anticipate earthquakes and prevent health hazards associated with them.
By reducing harmful pollutants in the air and water, this energy solution could help drive progress toward a cleaner, safer future for all.
Join our free newsletter for weekly updates on the coolest innovations improving our lives and saving our planet.