DOE Backs UC Irvine AI Project to Unlock Geothermal Energy at Scale

The US Department of Energy has selected a University of California, Irvine-led project to advance into a three-year second phase focused on using artificial intelligence to identify and develop geothermal resources more safely and economically. The MAESTRO initiative brings together five University of California campuses, four national laboratories and private-sector partners to improve how developers assess underground conditions, predict fracture behaviour and manage risks such as induced seismicity. The project is part of DOE’s Genesis Mission, which is using AI to accelerate research in areas tied to energy security and economic resilience.

 

AI Is Being Used to Reduce Subsurface Uncertainty

 

Enhanced geothermal systems can access heat several kilometres below the surface by circulating fluid through hot, low-permeability rock, but project success depends heavily on local geology. Developers need to understand rock properties, stress conditions, existing fractures, water availability, drilling access and seismic behaviour before deciding whether a site is viable.

Many of those characteristics cannot be observed directly. MAESTRO will combine real-time geophysical data, previous field knowledge and complex simulations to estimate how underground systems are likely to respond during development. The aim is to give operators a clearer view of project viability before committing large amounts of capital to drilling and construction.

 

Read more: Pulpex Opens Glasgow Fibre Bottle Factory With 40 Million-Unit Capacity

 

A Self-Improving AI System Will Guide Simulations

 

The project is designed around an AI framework that identifies areas of uncertainty, runs targeted simulations to fill those gaps and then updates its own models. Researchers describe the approach as a feedback loop in which the system improves as more information becomes available.

MAESTRO will also include safeguards intended to make sure its recommendations remain physically consistent. That matters because the system is being developed for engineering decisions where incorrect predictions could have financial or safety consequences.

 

Induced Seismicity Is One of the Main Challenges

 

A major focus will be understanding and controlling induced seismicity, where underground fluid injection and fracturing can trigger small earthquakes. This remains one of the most sensitive issues around enhanced geothermal development and can affect both project approvals and public acceptance.

Researchers plan to use AI and geophysical modelling to improve predictions of where and how fractures will develop. Technologies created through the project could also have wider applications, including improving early warning for naturally occurring earthquakes.

 

Explore OneStop ESG Marketplace: Renewable & clean energy generation

 

Five UC Campuses and Four National Labs Are Involved

 

The collaboration includes UC Berkeley, UC Irvine, UC Riverside, UC San Diego and UC Santa Cruz, along with Los Alamos, Lawrence Livermore, Lawrence Berkeley and Pacific Northwest national laboratories. The team combines expertise in geophysics, geomechanics, geochemistry, applied mathematics, machine learning and engineering.

“A major strength of this project is the unique set of partnerships it creates, which brings together for the first time geophysics, geochemistry, applied math and computation to address this singular national challenge for geothermal energy,” said Kevin Rosso, Battelle Fellow and geochemist at Pacific Northwest National Laboratory.

 

The Project Is Intended to Lower Commercial Development Risk

 

MAESTRO is ultimately aimed at giving geothermal developers more reliable information before and during project development. Better forecasts of underground behaviour could reduce failed drilling, shorten development timelines and improve the economics of projects that would otherwise carry large geological risks.

“Professionals in the sustainable energy development industry will ultimately have access to real-time guidance that can reduce the financial risks and time costs of bringing geothermal projects to fruition,” said Russ Detwiler, UC Irvine professor of civil and environmental engineering and co-principal investigator. The team also plans to make MAESTRO open source through a free browser-based tool for researchers, policymakers and the public.

 

Source: University of California, Irvine