Skip to main content

Envisioning is an emerging technology research institute and advisory.

LinkedInInstagramGitHub

2011 — 2026

research
  • Reports
  • Newsletter
  • Methodology
  • Origins
  • My Collection
services
  • Research Sessions
  • Signals Workspace
  • Bespoke Projects
  • Use Cases
  • Signal Scanfree
  • Readinessfree
impact
  • ANBIMAFuture of Brazilian Capital Markets
  • IEEECharting the Energy Transition
  • Horizon 2045Future of Human and Planetary Security
  • WKOTechnology Scanning for Austria
audiences
  • Innovation
  • Strategy
  • Consultants
  • Foresight
  • Associations
  • Governments
resources
  • Pricing
  • Partners
  • How We Work
  • Data Visualization
  • Multi-Model Method
  • FAQ
  • Security & Privacy
about
  • Manifesto
  • Community
  • Events
  • Support
  • Contact
  • Login
ResearchServicesPricingPartnersAbout
ResearchServicesPricingPartnersAbout
  1. Home
  2. Research
  3. Forge
  4. Generative AI for Materials Discovery

Generative AI for Materials Discovery

Google DeepMind's GNoME discovered 2.2 million new crystal structures, while US national labs use AI to design novel alloys, polymers, and catalysts 100x faster than traditional experimental methods.
Back to ForgeView interactive version

Generative AI for materials design uses machine learning to predict the properties of novel material compositions and crystal structures before they are synthesized. Google DeepMind's Graph Networks for Materials Exploration (GNoME) identified 2.2 million new stable crystal structures — equivalent to 800 years of conventional scientific discovery. US national laboratories (ORNL, Argonne, Sandia) are applying similar techniques to design specific materials for batteries, aerospace, and catalysis.

Materials discovery has historically been slow, serendipitous, and expensive. Testing a single new alloy composition can take months of synthesis, characterization, and performance evaluation. AI models can screen millions of candidates computationally, identifying the most promising for physical testing and reducing the discovery cycle from years to weeks.

The US benefits from its network of national laboratories and university materials science programs, which provide both the training data and experimental validation capabilities that AI-driven discovery requires. Accelerated materials innovation has implications across every technology sector — better batteries, lighter aircraft, more efficient solar cells, and stronger construction materials all depend on new materials.

TRL
5/9Validated
Impact
4/5
Investment
5/5
Category
Hardware

Book a research session

Bring this signal into a focused decision sprint with analyst-led framing and synthesis.
Research Sessions