Exploring New Materials through Artificial Intelligence: A Startup’s Innovative Approach

Orbital Materials — founded by Jonathan Godwin, who previously was involved with DeepMind’s material research efforts — is creating an AI-powered platform that can be used to discover materials ranging from batteries to carbon dioxide-capturing cells. Godwin says he was inspired to found Orbital Materials by seeing how the techniques underpinning AI systems like AlphaFold, DeepMind’s AI that can predict a protein’s 3D structure from its amino acid sequence, could be applied to the materials sciences. “[Yet] demand for new advanced materials … is growing hugely as our economies become electrified and de-carbonized.”Orbital Materials isn’t the first to apply AI to materials R&D. Osmium AI, led by an ex-Googler and backed by Y Combinator, enables industrial customers to predict the physical properties of new materials, then refine and optimize those new materials leveraging AI. But what sets Orbital Materials apart is its proprietary AI model for materials science, Godwin claims.

In a tech world captivated by text-generating AI, image-generating AI, and even movie-generating AI, one startup is breaking the mold. Orbital Materials, founded by former DeepMind senior researcher Jonathan Godwin, is paving the way for a new type of AI technology – GenAI. This innovative approach aims to support the creation of physical materials for manufacturing.

Godwin, inspired by the success of AI systems like AlphaFold, set out to apply similar techniques to the field of materials science. His goal: to revolutionize the traditional methods of discovering new materials, which often rely on time-consuming and costly trial and error processes in the lab.

“I felt that a new type of organization – one with AI experts as well as materials-scientists – was needed to bring materials out of the computer into the real world.”
-Jonathan Godwin, Founder of Orbital Materials

With the help of AI, Orbital Materials’ platform has the potential to uncover groundbreaking materials, ranging from batteries to carbon dioxide-capturing cells. This type of technology is in high demand as economies strive to become more electrified and de-carbonized.

However, crafting new materials is not an easy feat. It requires identifying specific physical and chemical structures, as well as determining the appropriate processes, such as melting or evaporating, to successfully create them. Once the material is devised, it must also undergo rigorous testing in various conditions to ensure its viability for its intended application.

“AI-enabled technology can greatly assist in mapping out which properties and processes may yield certain types of materials, ultimately saving time and money,” explains Godwin.

  • Traditional methods of discovering new materials are slow and expensive, often resulting in years of experimentation before success is achieved.
  • AI technology can speed up material design workflows and lead to the development of new products.

While Orbital Materials is not the first to utilize AI in materials research and development, what sets them apart is their proprietary AI model for materials science.

“We’ve taken a lot of inspiration from the successes of large language models and AlphaFold in building our data sets…This diversity is one of the things that gives the models their remarkable capabilities,” says Godwin.

“[We’re] taking a full-stack AI approach to developing a pipeline of materials in house.”
-Jonathan Godwin, Founder of Orbital Materials

At their lab in New Jersey, Orbital Materials’ AI model, called Linus, serves as the backbone for materials and chemical research and development. Linus was trained on a vast dataset of simulations and materials, allowing it to generate 3D molecular structures that meet specific criteria.

Scientists using Linus can enter natural language instructions, and the system will produce a molecular structure that satisfies the criteria. While it is not perfect and sometimes generates materials that are not physically possible to manufacture, Orbital Materials has successfully created at least one material – a cheaper, more reliable filter for capturing carbon dioxide from the air.

“Our goal is to bring materials to the proof of concept or pilot demonstration phase and then seek outside manufacturers as partners,” explains Godwin.

To further their mission, Orbital recently raised $16 million in a Series A round, bringing their total raised to approximately $21 million. This new capital will be used to expand their data science and wet lab teams and continue their advancements in the materials industry.

“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,” says Godwin confidently. And with the power of GenAI on their side, there’s no doubt that Orbital Materials will continue to make waves in the world of materials science.

Avatar photo
Kira Kim

Kira Kim is a science journalist with a background in biology and a passion for environmental issues. She is known for her clear and concise writing, as well as her ability to bring complex scientific concepts to life for a general audience.

Articles: 836

Leave a Reply

Your email address will not be published. Required fields are marked *