Submission + - Startup discovers hidden abundant, clean energy and did it in an unusual way (cnn.com)
schwit1 writes: It’s a “classic needle in the haystack problem,” said Joel Edwards, co-founder and CTO of Zanskar. “There’s no one type of data that tells you that a system is below you, even if you’re right on top of it.” Instead, there are multiple indicators which are really hard for humans to put together to figure out if a system exists.
That’s where AI comes in.
The AI models Zanskar uses are fed information on where blind systems already exist. This data is plentiful as, over the last century and more, humans have accidentally stumbled on many around the world while drilling for other resources such as oil and gas.
The models then scour huge amounts of data — everything from rock composition to magnetic fields — to find patterns that point to the existence of geothermal reserves. AI models have “gotten really good over the last 10 years at being able to pull those types of signals out of noise,” Hoiland said.
Once a potential location has been found, the next step for the company is to drill down to confirm the reserve exists and is hot enough to produce utility-scale power.
That’s exactly what they did at Big Blind over the summer, drilling wells to depths of around 2,700 feet where they found porous rock at 250 degrees Fahrenheit. They know the site is at least the minimum size needed to support a power plant, but don’t yet have a sense of how big it could be.
There is also work to be done to navigate permitting processes and grid interconnection, but the company estimates the first electricity could be produced here in three to five years’ time.
That’s where AI comes in.
The AI models Zanskar uses are fed information on where blind systems already exist. This data is plentiful as, over the last century and more, humans have accidentally stumbled on many around the world while drilling for other resources such as oil and gas.
The models then scour huge amounts of data — everything from rock composition to magnetic fields — to find patterns that point to the existence of geothermal reserves. AI models have “gotten really good over the last 10 years at being able to pull those types of signals out of noise,” Hoiland said.
Once a potential location has been found, the next step for the company is to drill down to confirm the reserve exists and is hot enough to produce utility-scale power.
That’s exactly what they did at Big Blind over the summer, drilling wells to depths of around 2,700 feet where they found porous rock at 250 degrees Fahrenheit. They know the site is at least the minimum size needed to support a power plant, but don’t yet have a sense of how big it could be.
There is also work to be done to navigate permitting processes and grid interconnection, but the company estimates the first electricity could be produced here in three to five years’ time.
