Using AI to design of functional and sustainable polymers

Finding the polymers of the future!

Follow us onFollow Tech Explorist on Google News

Nylon, Teflon, and Kevlar are some well-known polymers that have transformed the world as we know it. From non-stick frying pans to advanced 3D printing, polymers are the backbone of technological innovation.

The quest for the next groundbreaking polymer is a never-ending challenge, but at Georgia Tech, researchers are pioneering a new approach using artificial intelligence (AI) to revolutionize the field. Led by Rampi Ramprasad, their work in developing and adapting AI algorithms is accelerating the pace of materials discovery.

This summer, their efforts have culminated in two groundbreaking papers published in the Nature family of journals, showcasing the remarkable progress and success stories resulting from years of AI-driven polymer informatics research. The first paper, featured in Nature Reviews Materials, highlights recent breakthroughs in polymer design across crucial and contemporary application domains such as energy storage, filtration technologies, and recyclable plastics.

The second paper, published in Nature Communications, focuses on the use of AI algorithms to identify a specific class of polymers for electrostatic energy storage. The designed materials have undergone successful laboratory synthesis and testing, marking a significant leap forward in materials science.

“In the early days of AI in materials science, propelled by the White House’s Materials Genome Initiative over a decade ago, research in this field was largely curiosity-driven,” said Ramprasad, a professor in the School of Materials Science and Engineering. “Only in recent years have we begun to see tangible, real-world success stories in AI-driven accelerated polymer discovery. These successes are now inspiring significant transformations in the industrial materials R&D landscape. That’s what makes this review so significant and timely.”

Ramprasad’s team has developed revolutionary algorithms that have the potential to transform the field of polymer development. These algorithms can accurately predict polymer properties and formulations even before they are physically created, saving time and resources.

Using machine learning (ML) models, the team can forecast the properties of new polymers and identify the top candidates that meet specific criteria. This cutting-edge technology not only accelerates the discovery of new polymers but also enhances predictive capabilities by continuously refining the models with real-world experimental data.

However, harnessing the power of AI in this domain presents its own set of challenges. The accuracy of AI predictions relies heavily on the quality and diversity of the initial data sets. Additionally, designing algorithms capable of creating chemically realistic and synthesizable polymers is a complex task that demands expertise and innovation.

The real challenge arises after the algorithms make their predictions: proving the viability of these designed materials in the lab and demonstrating their scalability for real-world applications. Collaborating with experts from institutions like Georgia Tech, Ramprasad’s group not only designs these materials but also oversees their fabrication, processing, and testing to ensure their practicality and functionality.

This groundbreaking work has garnered attention from notable figures in the field, including Professor Ryan Lively from the School of Chemical and Biomolecular Engineering, who frequently collaborates with Ramprasad’s team and is a co-author of the paper published in Nature Reviews Materials.

“In our day-to-day research, we extensively use the machine learning models Rampi’s team has developed,” Lively said. “These tools accelerate our work and allow us to rapidly explore new ideas. This embodies the promise of ML and AI because we can make model-guided decisions before we commit time and resources to explore the concepts in the laboratory.”

Leveraging the power of AI, Ramprasad’s team and their collaborators have achieved groundbreaking progress across various domains, from energy storage to recyclable materials.

One remarkable breakthrough, featured in a Nature Communications paper, highlights the development of novel polymers for capacitors, critical components in electric and hybrid vehicles. Collaborating with researchers from the University of Connecticut, they identified insulating materials made from polynorbornene and polyimide polymers.

These materials have the exceptional capability to simultaneously deliver high energy density and thermal stability, setting new standards in the industry. The enhanced polymers are tailored to excel in demanding environments, such as aerospace applications while upholding ecological sustainability.

“The new class of polymers with high energy density and high thermal stability is one of the most concrete examples of how AI can guide materials discovery,” said Ramprasad. “It is also the result of years of multidisciplinary collaborative work with Greg Sotzing and Yang Cao at the University of Connecticut and sustained sponsorship by the Office of Naval Research.”

The groundbreaking potential of AI-assisted materials development is vividly highlighted by the active involvement of industry leaders in the recent Nature Reviews Materials article. Significantly, the co-authors of this paper also feature scientists from prestigious institutions such as the Toyota Research Institute and General Electric.

In order to further expedite the integration of AI-driven materials development into various industries, Ramprasad has taken the initiative to co-found Matmerize Inc., an innovative software startup recently established at Georgia Tech. Their cutting-edge polymer informatics software, which operates on a cloud-based platform, is already being embraced by companies spanning diverse sectors, including energy, electronics, consumer products, chemical processing, and sustainable materials.

“Matmerize has transformed our research into a robust, versatile, and industry-ready solution, enabling users to design materials virtually with enhanced efficiency and reduced cost,” Ramprasad said. “What began as a curiosity has gained significant momentum, and we are entering an exciting new era of materials by design.”

Journal reference:

  1. Huan Tran, Rishi Gurnani, Chiho Kim, Ghanshyam Pilania, Ha-Kyung Kwon, Ryan P. Lively & Rampi Ramprasad. Design of functional and sustainable polymers assisted by artificial intelligence. Nature Reviews Materials, 2024; DOI: 10.1038/s41578-024-00708-8
Up next

eaSEL: A system to promote social-emotional learning and parent-child interaction

The work paves directions in how AI can support children's social-emotional reflection of media.

Researchers discovered 268 new high-performance metal alloys

A fast-track way to search for high-performance metal alloys.
Recommended Books
Picks for you