Polymers such as Nylon, Teflon, and Kevlar have played a crucial role in transforming the world, from Teflon-coated frying pans to 3D printing. Finding the next revolutionary polymer is a challenge, but researchers at Georgia Tech are using artificial intelligence (AI) to accelerate materials discovery. Rampi Ramprasad and his team have developed AI algorithms that predict polymer properties and formulations, allowing for the creation of new materials that meet specific performance criteria. These algorithms are transforming the industrial materials R&D landscape, with recent success stories inspiring significant changes.
Two recent papers published in the Nature family of journals highlight the advancements in AI-driven polymer informatics research. One paper in Nature Reviews Materials showcases breakthroughs in polymer design for applications such as energy storage, filtration technologies, and recyclable plastics. The second paper in Nature Communications focuses on using AI algorithms to discover a subclass of polymers for electrostatic energy storage, with successful laboratory synthesis and testing of the designed materials. These successes are a testament to the power of AI in accelerating polymer discovery.
While AI can speed up the discovery of new polymers, it also presents challenges. The accuracy of AI predictions relies on the availability of high-quality initial data sets, making data paramount. Designing algorithms that can generate chemically realistic and synthesizable polymers is complex. The real challenge lies in proving that the designed materials can be produced and function as expected at scale. Collaborators, such as Professor Ryan Lively from Georgia Tech, work with Ramprasad’s team to design and test these materials, demonstrating their real-world viability.
Ramprasad’s team and their collaborators have made significant advancements in diverse fields, including energy storage, filtration technologies, additive manufacturing, and recyclable materials using AI. One notable success is the design of new polymers for capacitors with high energy density and thermal stability, vital for electric vehicles and aerospace applications. The collaboration with researchers from the University of Connecticut has led to the development of polymers that can meet these demanding requirements while remaining environmentally sustainable. This success showcases how AI can guide materials discovery and lead to groundbreaking innovations.
The potential for real-world translation of AI-assisted materials development is highlighted by industry participation in these research efforts. Co-authors from Toyota Research Institute and General Electric were part of the Nature Reviews Materials article, underscoring the interest from industry in AI-driven materials development. Ramprasad co-founded Matmerize Inc., a software startup spun out of Georgia Tech, to further accelerate the adoption of AI in materials development across various sectors. Their cloud-based polymer informatics software is already being used by companies in energy, electronics, consumer products, chemical processing, and sustainable materials, signaling the beginning of an exciting new era of materials by design.
