Fervo Energy Co Ltd (NASDAQ:FRVO) shares climbed 11.1% in premarket trading on Monday after the company unveiled a new collaboration with Nvidia and Pacific Northwest National Laboratory (PNNL) aimed at developing a digital twin platform for Enhanced Geothermal Systems (EGS).
The project is designed to combine advanced modelling, artificial intelligence and real-time operational data to improve the development and management of geothermal energy assets.
New Platform to Combine AI and Geothermal Data
The partnership will create a platform known as EGS-Twin, which is intended to merge live field information, physics-based simulations and AI-powered forecasting tools.
Researchers at PNNL will use operational data supplied by Fervo to train artificial intelligence models using Nvidia’s AI computing infrastructure. Those models will subsequently be incorporated into Nvidia Omniverse libraries to support advanced geothermal analysis and simulation capabilities.
Improving Efficiency and Scalability
The EGS-Twin platform is expected to help geothermal operators better understand subsurface conditions, anticipate operational changes and optimise electricity generation.
In addition, the system is intended to support broader deployment of enhanced geothermal technologies by improving operational visibility and decision-making.
To support the initiative, PNNL will develop specialised workflows and data pipelines using high-performance computing systems, including U.S. Department of Energy supercomputers, enabling large-scale geothermal simulations.
Digital Twins Could Accelerate Geothermal Development
Fervo believes the technology has the potential to significantly improve geothermal project performance and shorten development timelines.
“We believe that digital twins will expedite the learning curve for geothermal development as we build and operate our GeoBlock assets,” commented Fervo’s CTO and co-founder, Jack Norbeck. “Integrating high-fidelity physics-based models with AI-driven forecasting has the potential to reshape reservoir management, improve heat recovery, and enhance system reliability.”
Nevada and Utah Data to Support Model Training
The initial phase of development will utilise proprietary field data gathered from Fervo’s geothermal operations in Nevada and Utah.
PNNL will begin training the digital twin models immediately, with additional operational data expected to further enhance the platform’s capabilities over time.
The companies currently expect the EGS-Twin platform to be fully implemented by 2029.