Design News is part of the Informa Markets Division of Informa PLC

This site is operated by a business or businesses owned by Informa PLC and all copyright resides with them. Informa PLC's registered office is 5 Howick Place, London SW1P 1WG. Registered in England and Wales. Number 8860726.

AI Can Predict How a Material Will Behave Before It's Made

AI Can Predict How a Material Will Behave Before It's Made
Researchers have leveraged machine learning to predict how certain materials will act before they are synthesized – saving time and resources when developing materials for next-generation applications.

The structure of a material called a metal organic framework (MOF) shown under magnification. Researchers at the University of Cambridge now have developed a method to predict how MOFs will behave before they are synthesized. (Image source: University of Cambridge)

When developing new materials, it’s always helpful to know how they will perform ahead of time to gauge their utility for various applications, as well as to avoid wasting precious time and resources. Now, a team of engineers at the University of Cambridge, has applied machine learning to assist with predicting the properties of materials before they are synthesized.

The researchers, led by Professor David Fairen-Jimenez of Cambridge’s Department of Chemical Engineering and Biotechnology, applied their research specifically to metal-organic frameworks (MOFs), compounds that scientist believe hold great promise for future applications because of their range of uses—from extracting water from air in the desert, to storing dangerous gases, to even powering hydrogen-powered cars.

Using a custom machine learning algorithm, Fairen-Jimenez and his team were able to predict the characteristics of more than 3,000 existing MOFs, as well as ones that have yet to be created in a lab. By applying this method, researchers can analyze both existing and non-synthesized MOFs to ensure that only those with the necessary mechanical stability are manufactured.

The Cambridge team's machine learning algorithm, which was developed in conjunction with with scientists from the United States and Belgium, predicts the mechanical properties of MOFs using a multi-level computational approach in order to build an interactive map of the structural and mechanical landscape of MOFs.

“We are now able to explain the landscape for all the materials at the same time,” Fairen-Jimenez said. “This way, we can predict what the best material would be for a given task.”

The team published a paper reporting their work in the journal Matter.

MOFs are self-assembling 3D compounds comprised of connected metallic and organic atoms. They are similar to plastics in that they are versatile and can be customized into countless different combinations to form different materials for different uses.

Structurally, however, they are completely different from plastics. MOFs feature an orderly crystalline structure that grows in all directions, while plastics are based on long chains of polymers that grow in only one direction.

This structure gives MOFs an advantage over plastics. For one, individual atoms or molecules can be switched in or out of it so they can be made like building blocks. MOFs also have a massive surface area—an MOF the size of a sugar cube laid flat would cover an area the size of six football fields, for example.

Additionally, the porous nature of these materials allows them to be customized as storage pockets for different molecules just by changing building blocks, adding to their versatility, the researchers said.

Fairen-Jimenez and his team were particularly interested in the porous nature of MOFs. “That MOFs are so porous makes them highly adaptable for all kinds of different applications, but at the same time their porous nature makes them highly fragile,” he explained.

Fairen-Jimenez’s team set out to solve a challenge to synthesizing MOFs in powder form, which is the typical way scientists develop the materials. However, that powder has to be put under pressure to form larger-shaped pellets for the materials to be of any use, which, due to the MOFs’ porosity, causes many of them to be crushed during this process—a waste of time and investment.

The Cambridge researchers have also launched an interactive website so other researchers can design and predict the performance of their own MOFs.

“It allows researchers to access the tools they need in order to work with these materials; it simplifies the questions they need to ask,” Fairen-Jimenez said of the site.

Elizabeth Montalbano is a freelance writer who has written about technology and culture for more than 20 years. She has lived and worked as a professional journalist in Phoenix, San Francisco and New York City. In her free time she enjoys surfing, traveling, music, yoga and cooking. She currently resides in a village on the southwest coast of Portugal.

Drive World with ESC Launches in Silicon Valley

This summer (August 27-29), Drive World Conference & Expo launches in Silicon Valley with North America's largest embedded systems event, Embedded Systems Conference (ESC). The inaugural three-day showcase brings together the brightest minds across the automotive electronics and embedded systems industries who are looking to shape the technology of tomorrow.
Will you be there to help engineer this shift? Register today!

Hide comments


  • Allowed HTML tags: <em> <strong> <blockquote> <br> <p>

Plain text

  • No HTML tags allowed.
  • Web page addresses and e-mail addresses turn into links automatically.
  • Lines and paragraphs break automatically.