A US Department of Energy-funded project led by UC Irvine will spend three years developing AI tools to help identify promising geothermal sites and predict how underground rock may fracture. If the approach works, it could help operators assess a site’s chances of success and the risk of triggering earthquakes before drilling begins.
Watch Desk analysis
What happened
The project, called MAESTRO, has been selected to move into Phase 2 of the DOE’s Genesis initiative, according to UC Irvine’s 8 October announcement. Its researchers plan to combine geophysical observations, previous learning and complex simulations to model conditions underground that cannot be measured directly.
That includes rock properties, stress, water availability and existing cracks. The team aims to predict how fractures may form during enhanced geothermal operations, where fluid is circulated through deep, low-permeability rock to extract heat. Researchers from five University of California campuses, four national laboratories and three private-industry partners are involved.
UC Irvine says the project also aims to improve understanding and control of induced seismicity. It plans to make the work open source, with a free browser-based tool for exploring geothermal potential, assessing risk and reviewing data.
Why it matters
Geothermal power can provide energy regardless of the weather, but finding suitable sites and managing the risks of fracturing underground rock remain difficult. Better predictions could help developers decide where projects are viable and how to operate them more safely. That is useful groundwork, rather than a new power source ready to switch on.
Our read
The interesting part is AI being used to model a physical system that is mostly hidden from view, with predictions intended to inform real engineering decisions. The test will be whether the models prove useful across actual sites, not just whether they make impressive maps. A public tool and open-source resources would make the project’s claims easier to examine, which is a welcome change from the usual black-box flourish.
What to watch
- Whether MAESTRO publishes its methods, data and browser-based tool as promised.
- How well its fracture predictions perform against observations from geothermal sites.
- Whether the work helps operators assess and reduce induced-seismicity risks.
Discussion spark: Should AI predictions be allowed to guide geothermal drilling decisions, or should they remain advisory until they have been tested across multiple sites?
Sources and evidence
- Department of Energy selects UC Irvine-led, AI-driven geothermal energy project – UC Irvine News (8 October 2026, 13:48 UTC)
Watch Desk is operated by WittyWires as an independent cross-cutting AI news tracker. It does not speak for the organisations or people it covers.