Fervo Energy Inc. (NASDAQ: FRVO) announced a partnership with NVIDIA Corp. (NASDAQ: NVDA) and the Pacific Northwest National Laboratory (PNNL) to develop EGS-Twin, a digital twin platform for enhanced geothermal systems. The collaboration aims to deliver real-time insight into subsurface behavior and operational performance by integrating high-resolution field data with physics-based modeling and AI-driven forecasting. This initiative is designed to help geothermal operators identify subsurface changes, optimize power generation, and strengthen the scalability of enhanced geothermal systems. The announcement overshadowed Fervo's first quarterly earnings miss as a public company, with the stock gaining more than 6% during Monday's session.
To build EGS-Twin, PNNL researchers will use Fervo’s industry expertise and field data to train scalable AI models on NVIDIA AI infrastructure. The trained AI models will be integrated into NVIDIA Omniverse libraries. PNNL will develop the workflows and data pipelines, leveraging high-performance computing, including U.S. Department of Energy supercomputing resources, to run large-scale simulations.
Implementation Timeline and Data Sources
The PNNL team will begin training the digital twin immediately using currently available proprietary field data from Fervo’s Nevada and Utah sites. The platform is scheduled for implementation by 2029. The team will continue refining the platform as additional production data comes online.
| Aspect |
Detail |
| Platform Name |
EGS-Twin |
| Primary Technology |
AI-driven forecasting, physics-based modeling, NVIDIA Omniverse libraries |
| Data Sources |
Proprietary field data from Fervo’s Nevada and Utah sites |
| Implementation Target |
2029 |
Strategic Impact and Financial Performance
Jack Norbeck, CTO and co-founder of Fervo Energy, stated that digital twins will expedite the learning curve for geothermal development as the company builds and operates its GeoBlock assets. He emphasized that integrating high-fidelity physics-based models with AI-driven forecasting has the potential to reshape reservoir management, improve heat recovery, and enhance system reliability. The collaboration supports the deployment of 24/7 carbon-free power to meet growing global energy demand.
The partnership announcement came alongside Fervo’s first earnings report since completing its Nasdaq initial public offering in May. Fervo reported first-quarter revenue of $61,000, missing the analyst estimate of $480,000. The company reported a GAAP net loss per share attributable to common stockholders of $3.72, missing the analyst estimate for a loss of 10 cents per share. Operating loss widened to $20.1 million from $9.9 million, while net loss widened to $31.8 million from $9.1 million.
Cape Station Development and Outlook
Capital expenditures rose to $172.8 million from $105.4 million, reflecting continued investment in Cape Station development and construction. Cape Station Phase I, an approximately 100-megawatt project, remains on track for first power in the fourth quarter of 2026. GeoBlock Unit 1 commissioning is underway, while GeoBlocks 2 and 3 are expected to reach commercial operation in the first quarter of 2027. Cape Station Phase II, a 400-megawatt expansion, began construction in the first quarter, with commercial operation expected in 2028.
Fervo secured $421.4 million in non-recourse project financing for Cape Station Phase I. Cash and cash equivalents were $280.8 million as of March 31, compared with $461.8 million at year-end. The company expects about $1.2 billion in capital expenditures from the second quarter of 2026 through the first quarter of 2027, primarily for Cape Station construction and other GeoCluster development.