Zanskar thinks 1 TW of geothermal power is being overlooked

The article highlights the untapped potential of conventional geothermal energy in the U.S., which experts at the Department of Energy estimate could provide nearly 10% of the nation’s electricity by 2050. Unlike enhanced geothermal systems that rely on fracking to access deep hot rock, conventional geothermal has been limited by outdated assumptions and reliance on surface indicators like hot springs or volcanoes, which only represent about 5% of geothermal systems. Zanskar, a startup leveraging AI, challenges these assumptions by using machine learning and Bayesian evidential learning (BEL) to identify and validate previously overlooked geothermal sites, significantly expanding the potential capacity from tens of gigawatts to possibly a terawatt scale. Zanskar’s AI-driven approach has already led to the revival of a power plant in New Mexico and the discovery of two new sites with over 100 megawatts of combined potential. These successes helped the company secure $115 million in Series C funding from a diverse group of investors. The startup currently focuses