Hardware Podcasts

How AI Is Unlocking Geothermal Power at Scale with Joel Edwards

Hardware to Save a Planet · 19 Feb 2026 · 51m · Episode 96

What this episode covers

Joel Edwards, CTO and co-founder of Zanskar, explains how the company uses AI and geoscience to locate hidden conventional geothermal reservoirs, reducing exploration costs by up to 90%. Edwards details Zanskar's 'flywheel' process of training physics-constrained models on satellite and field data to predict hotspot locations, avoiding the high subsurface risk that stalled the industry after oil majors exited in the 1980s. He highlights the success of their Lightning Dock project in New Mexico, where AI-driven reservoir modeling identified a highly productive well that maxed out the plant's capacity, and outlines Zanskar's goal to reach one gigawatt of installed capacity within ten years.

Most relevant to

early-stage companies

Topics

Mentioned

Companies
Zanskar, Chevron, Hunt, Phillips, Unical, Rhodium Group, Furbo, NASA
Products
The Geysers, McGinnis Hills, Big Blind, Pumpernickel, Lightning Dock
Also
UC Santa Cruz, Alex Net, MIT

Related episodes from other shows

Other shows on the same ground, closest first.

  • Catalyst · 32m

    How geothermal gets built

    Carl Hoiland, co-founder and CEO of Zanskar, explains the step-by-step process of developing geothermal projects, from initial temperature gradient drilling to proving permeability and managing reservoir decline. He details the historical stall of the industry due to exploration risk and dry holes, and how new technologies like AI and enhanced geothermal systems (EGS) are de-risking the sector. Hoiland highlights Zanskar's rapid 12-month development of the Lightning Dock field in New Mexico and discusses the massive potential of hundreds of gigawatts of accessible geothermal resources in the western United States.

    Energy & climate techSourcing & supply chain
    9 chapters

  • How I Built This · 39m

    HIBT Lab! Quaise Energy: Carlos Araque

    Carlos Araque, co-founder and CEO of Quaise Energy, explains how his company plans to unlock global geothermal energy by drilling 20-kilometer deep holes using millimeter-wave technology developed at MIT. Araque details his transition from a 15-year career in the oil and gas industry, including time at Schlumberger, to founding Quaise to address the technological gaps in the energy transition. He discusses the technical mechanics of vaporizing rock with gyrotrons, the economic potential of repowering existing fossil fuel plants, and the challenges of scaling this capital-intensive technology to compete with wind, solar, and coal.

    Energy & climate techStarting a product company
    6 chapters

  • Catalyst · 1h 01m

    Could geothermal become a major zero-emissions player?

    Jamie Beard, executive director of Project Innerspace, discusses the potential for 'geothermal anywhere' technologies to scale globally by overcoming subsurface risks and financing gaps. He explains how enhanced geothermal systems (EGS) and closed-loop technologies can replicate Iceland's success worldwide, while highlighting the critical need to leverage the oil and gas industry's drilling expertise and workforce. Beard also covers the role of geothermal heat pumps in decarbonizing heating and the challenges of securing venture capital and government support for first-of-a-kind projects.

    Energy & climate techSourcing & supply chain
    9 chapters

  • Catalyst · 36m

    Digging deep for super hot geothermal

    Carlos Araque, founder and CEO of Quaise Energy, explains the company's approach to super hot geothermal energy using millimeter-wave drilling technology to reach depths of up to 12 miles and temperatures of 800 degrees Fahrenheit. He contrasts this with traditional hydrothermal geothermal, noting that while shallow super-hot systems (3-4 miles) can leverage existing oil and gas drilling precedents, deeper systems require vaporizing rock to access ubiquitous heat resources. Araque outlines Quaise's roadmap, targeting a commercial-grade flow test in Oregon by the end of 2026, with subsequent milestones for deeper, supercritical wells by 2028.

    Energy & climate techMaterials & manufacturing processes
    9 chapters

  • Catalyst · 36m

    Inside a $300 million bet on AI for physical R&D

    Ekin Dogus Cubuk, co-founder of Periodic Labs, explains how his company combines frontier AI models with automated physical labs to accelerate materials discovery. Cubuk argues that recent advances in reasoning models like OpenAI's O1 and improved lab automation allow AI to overcome its reliance on limited training data by generating synthetic data and running high-throughput experiments. The company is targeting breakthrough materials, specifically high-temperature superconductors, using a hybrid approach where humans provide initial hypotheses and AI handles execution and iteration. With a $300 million seed round, Periodic Labs aims to build a generalized scientific intelligence platform that serves both its own discovery goals and external partners' R&D needs.

    AI & machine learningMaterials & manufacturing processes
    10 chapters

The summary, chapters and topics are generated from the episode’s audio by this directory, not written by Hardware to Save a Planet. The episode itself belongs to its publisher.