Orbital Materials is a startup, directed by a former DeepMind researcher, that uses AI technology (GenAI) to aid in the creation of new physical materials. The company’s AI-driven platform is used to discover a range of materials, from batteries, to cells that capture carbon dioxide. The goal of this AI application is to save traditional research methods time and money by predicting the properties and processes that may result in the formation of specific types of materials.
Orbital Materials was launched by Jonathan Godwin, who was previously involved in DeepMind’s material research efforts. Inspired by AI systems like AlphaFold, which predicts a protein’s 3D structure, Godwin realized he could apply similar techniques to materials science. Traditional methods of discovering new materials often relied on time-consuming lab trials and experiments, so Godwin aimed to utilize AI to reduce the time needed to bring new materials from computer simulations to reality.
Creating a new material involves complex processes and it’s not usually a very intuitive process. For example, achieving specific properties like lightweightness and rigidity involves identifying related physical and chemical structures, and determining the processes (e.g., melting, evaporating) that reliably create such structures. AI can’t solve all the challenges in materials design; however, it can expedite the process by predicting which properties and processes might yield desired materials.
Orbital Materials isn’t the only company applying AI to materials research and development (R&D). Another notable startup is Osmium AI, which like Orbital Materials, uses AI to predict new materials’ physical properties and enhance them. DeepMind has also announced its own work on AI-based materials discovery, including an algorithm that could discover millions of crystals for commercial technology use.
What sets Orbital Materials apart, according to Godwin, is its proprietary AI model for materials science. This model, named Linus, underlies Orbital’s lab work in New Jersey. Scientists input natural language instructions, like a description of a carbon dioxide absorbing material, and Linus generates a 3D molecular structure to fit. Despite Linus’ ability, it isn’t perfect and sometimes designs materials that can’t physically be created. Still, Godwin mentioned that they have successfully developed at least one material—a reliable, low-cost filter to capture atmospheric carbon dioxide, with more details about it to be announced later on.
Orbital Materials, headquartered in London, does not intend to manufacture materials itself. Instead, it seeks to bring materials to the “proof of concept” or “pilot demonstration” stage and then collaborate with external manufacturers. To aid its growth, Orbital has recently raised $16 million in a Series A round, pushing its total funding to $21 million.
Godwin emphasized their aim with this technology saying, “Just like AlphaFold is enabling new drugs to be discovered and brought to market faster, Orbital Materials’ technology is enabling new advanced materials to be designed and commercialized at unprecedented speed.”
