Listen to the Podcast:
Novel materials for carbon capture and wind turbines could minimize pollution. A small but rising number of firms want to employ AI to help them develop faster.
Companies have promoted numerous ways artificial intelligence can make our lives easier since ChatGPT went viral last autumn. They’ve promised superhuman virtual assistants, tutors, attorneys, and even doctors.
What About a Superhuman Chemical Engineer?
Orbital Materials, a London-based startup, wants to achieve exactly that. The business is attempting to use generative AI — the technology underlying tools like ChatGPT — to accelerate the development of clean energy products. Essentially, the goal is to create computer models that are powerful and acute enough to discover the optimal formulations for items such as sustainable jet fuel or batteries free of rare-earth materials.
Jonathan Godwin, a co-founder of Orbital Materials, wants a system as straightforward and efficient as the software engineers already use to develop designs for things like furniture and airplane wings.
“That has historically been too difficult for molecular science,” he remarked.
ChatGPT works because it is good at predicting text – here’s the next appropriate word or sentence. For the same concept to operate in chemistry, an AI system must forecast how a novel molecule will act in the real world, not simply in a lab.
Researchers and companies have used artificial intelligence to seek better, greener materials. Symyx Technologies, a materials discovery business founded in the 1990s, closed its doors following a sale. More recently, petrochemical alternatives and cell programming have gained traction.
However, the technology for many elements required to decarbonize the world is not yet available.
New sophisticated materials can take decades to make their way from discovery to sale. That timescale is too sluggish for firms and nations aiming to reduce emissions quickly to attain net zero ambitions.
According to Aaike van Vugt, co-founder of the material science company VSParticle, “that needs to happen in the next ten years, or sooner.”
AI researchers believe they can assist. Godwin spent three years in DeepMind, Google’s AI unit, researching advanced material discoveries before founding Orbital Materials. That lab published AlphaFold, a model for predicting protein shapes that could aid in discovering new medications and vaccinations. This, combined with the fast adoption of tools such as ChatGPT, convinced him that AI would soon be capable of dominating the physical world.
“What I thought would take ten years happened in 18 months,” he stated. “Things are getting better and better.”
Godwin compares his Orbital Materials method to AI image generators such as Dall-E and Stable Diffusion. These models are built from billions of online photographs, and when users write in a text prompt, a photorealistic creation appears. Orbital Materials intends to train models on the molecular structure of materials using massive amounts of data. Enter a desired feature and material — an alloy that can endure extremely high temperatures — and the model returns a proposed molecular formula.
According to Rafael Gomez-Bombarelli, an assistant professor at MIT who advised Orbital Materials, this approach is effective in theory since it can both imagine new molecules and test how they would perform. (He stated that he is not an investor.)
Using AI to Develop Climate Friendly Materials
Many IT investors are currently looking for startups that may profit from greener material production. This is especially true in Europe, where regulators require firms to reduce carbon emissions or risk heavy fines. In the future, the markets for sophisticated materials in areas such as renewable energy, transportation, and agriculture are expected to rise by tens of billions of dollars.
Some researchers, such as those at the University of Toronto, have established “self-driving labs” that combine AI systems with robots to search for new materials at unprecedented rates. A Dutch company called VSParticle makes equipment for making parts for renewable hydrogen and gas sensors.
According to co-founder van Vugt, consider it comparable to a DNA sequencer in a genomics lab. He thinks his technology can help cut the 20-year time horizon of advanced materials to one year and eventually “a couple of months.” His business is currently looking for funding for growth.
Orbital Materials, which obtained $4.8 million in previously undisclosed seed funding, intends to begin by focusing its AI on carbon capture. The business is developing an algorithmic model that can more efficiently separate CO2 and other harmful chemicals from other pollutants than current methods.
(According to Godwin, the startup, which employs numerous AI experts, intends to publish peer-reviewed results on this technology soon.) Carbon capture has yet to function at scale, but thanks to a flood of government incentives, particularly in the United States, interest in deploying the technology is rapidly increasing.
Godwin stated that Orbital Materials would eventually aim to expand into areas such as fuel and batteries. He envisions a business model similar to synthetic biology and drug development firms: build the brainpower, then license the software or innovative materials to manufacturers. “It’s going to take us a little bit of time to get to market,” Godwin admitted. “But once you’re there, it all happens very quickly.”
However, perfecting the AI is only half the battle. Making sophisticated materials in battery and fuel manufacturing fields necessitates collaboration with large incumbent firms and tangled supply chains. According to MIT’s Gomez-Bombarelli, this can be even more expensive than inventing new medications.
“The economics and de-risking make it way harder,” he explained.
According to Heather Redman, managing partner at Flying Fish Partners, which supported Orbital Materials, most tech investors pursuing the shiny penny of generative AI have failed to see beyond chatbots. She acknowledges the dangers associated with energy businesses but feels the $1 trillion potential of products such as batteries and carbon capture is worth the investment risk.
“We love big hills as long as there’s a big gigantic market and opportunity at the top,” she explained.
Gomez-Bombarelli understands how large these hills can be. In 2015, he helped found Calculario, a startup similar to Orbital Materials that employed AI and quantum chemistry to accelerate the development of novel materials. It did not get enough traction and was forced to concentrate on the OLED market.
“Perhaps we didn’t make our case,” he said. “Or maybe the market wasn’t ready.”
It’s debatable whether it is currently. However, there are some positive indicators. Computing has undoubtedly advanced. Newcomers may also have an easier time selling AI because potential clients can see the benefits more clearly. Gomez-Bombarelli’s pitch is straightforward: “Look at ChatGPT.” We may apply the same logic to chemistry.”
Read Also: Google’s Next-Generation AI Gemini
