how ‘autonomous’ labs are using AI to develop remarkable new materials

Led by Professor Alán Aspuru-Guzik, the Acceleration Consortium at the University of Toronto has an ambitious plan: dramatically reduce the time it takes to go from a scientific inquiry to a ready-to-use application using the latest approaches in matter of automation. The Acceleration Consortium is a University of Toronto institutional strategic initiative that designs and builds autonomous labs, an emerging technology that uses artificial intelligence (AI) and robotics to radically change the timeline and cost of materials development advances. A discovery process that would take an average of 20 years and $100 million, for example, can be reduced to just one year and $1 million.

This is achieved in part through the ability of the Autonomous Lab to reverse the usual scientific discovery process. Instead of researchers spending countless hours performing tedious trial-and-error experiments, autonomous lab technologies allow scientists to predefine the desired properties of a material, leaving the lab to then work autonomously – by using computer modeling to predict which molecular combinations will best suit a particular application. A robotic lab then uses these predictions to autonomously synthesize and test the desired properties. This data is then fed back into the AI ​​system, so that it can learn from the results to generate a new, better performing candidate list. After rounds of predictions, summaries and tests, a winner emerges.

A number of research initiatives at the University of Toronto are using this “stand-alone” laboratory approach to advance much-needed technologies aimed at solving the problems of the present, as well as anticipating the problems of the future. Of these, two projects to produce a range of advanced materials promise breakthrough benefits for industry and the consumer…

Built to last
“Corrosion is everywhere, and its mitigation and remediation costs Canadian taxpayers $38 billion a year,” says Professor Jason Hattrick-Simpers, who leads the Built-to-Last project, using AI to find combinations innovative corrosion-resistant alloys. . “The human cost [of corrosion] is even higher: the lead problems in Flint, Michigan were related to the corrosion of lead pipes there, and it is almost certain that the corrosion contributed to the collapse of the Surfside condominium [in Miami].”

The project is looking for new “high entropy materials”, ie alloys composed of many elements. To put this into context, consider that bronze, the first alloy ever created, is composed of only two elements: copper and tin. Given the number of possible combinations of metals and elements, there are potentially billions of undiscovered alloys. It would be impossible to test these combinations one by one to sort out which properties would be suitable for the implementation and which would not. The required human labor hours simply do not exist. But this is no longer the case once the process is augmented by artificial intelligence (AI).

“I’m interested in materials for the green economy,” says Hattrick-Simpers. “A potential application for corrosion-resistant alloys is more robust electrical contacts: our phones, laptops and even our vehicles need to be charged every night, but the electrical connections aren’t exactly kept in a pristine environment or treated gently. “, he says. . “Still, we want to know that at the end of the night, when we plug the EV we just covered in salt or mud into the connector we left in our damp garage, our battery will recharge with the same efficiency than when we bought it. Unfortunately, even the process of plugging the car in degrades the electrical connections. Imagine what the electrical connections of a wind turbine have to go through, even worse one near salt water.

The laboratory of matter
Researchers from the University of Toronto’s Matter Lab have collaborated with the Acceleration Consortium to accelerate and deepen studies of new organic materials for storing energy. Matter Lab researcher Professor Yang Cao is interested in creating new battery materials, moving away from the use of conventional metal ions such as lithium and towards organic compounds derived from vitamins.

Such batteries could be cheaper and more environmentally friendly than those currently available. “We hope to find molecules capable of storing the electricity produced during the day in solar farms for use at night. This technology can help stabilize the energy grid and significantly reduce our reliance on fossil fuels,” says Cao, who leads the project.

Much like the hunt for new alloys, finding the right molecules is a Herculean human task made possible by the auxiliary power of AI. “Autonomous labs help eliminate bias or human error and make results more reliable,” Cao says. “They can also operate 24/7 and make decisions on the fly, freeing researchers from repetitive tasks and allowing them to focus on creating new molecules and materials. And, thanks to the autonomous laboratories, we can quickly validate historical results so that better predictions can be made for future molecules.

Elsewhere at the Matter Lab, Dr. Han Hao is studying new organic semiconductor materials, which fall somewhere on the electrical conductivity scale between metals and materials that insulate electricity, such as glass. Organic semiconductor materials are crucial for developing better lasers, with applications in a multitude of technologies, from phone screens and solar panels to wearable devices.

“Using autonomous labs, we were able to explore more than 200 candidate laser molecules in a month,” says Hao, noting that without the support of autonomous labs, a predecessor in the field published fewer than 10 candidate molecules. in five years.

“We were also able to improve the success rate of synthesizing complex organic laser molecules by 150% or more.”

A magnet for top talent
Along with all this cutting-edge research, a virtuous circle is emerging: the more exciting the technological developments, the more talent and funding from the University of Toronto’s Accelerator Consortium attract, says Aspuru-Guzik. “One of the things that’s really cool is that we’re growing really fast,” he says. “You can talk about science, but basically we’re building a movement here.”

Meet the amazing community pushing the boundaries of what’s possible. utoronto.ca/news

Leave a Reply

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