Nylon, Teflon, Kevlar. These are just a few familiar polymers — large-molecule chemical compounds — that have changed the world. From Teflon-coated frying pans to 3D printing, polymers are vital to creating the systems that make the world function better. 

Finding the next groundbreaking polymer is always a challenge, but now Georgia Tech researchers are using artificial intelligence (AI) to shape and transform the future of the field. Rampi Ramprasad’s group develops and adapts AI algorithms to accelerate materials discovery. 

This summer, two papers published in the Nature family of journals highlight the significant advancements and success stories emerging from years of AI-driven polymer informatics research. The first, featured in Nature Reviews Materials, showcases recent breakthroughs in polymer design across critical and contemporary application domains: energy storage, filtration technologies, and recyclable plastics. The second, published in Nature Communications, focuses on the use of AI algorithms to discover a subclass of polymers for electrostatic energy storage, with the designed materials undergoing successful laboratory synthesis and testing. 

“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.”

AI Opportunities

Ramprasad’s team has developed groundbreaking algorithms that can instantly predict polymer properties and formulations before they are physically created. The process begins by defining application-specific target property or performance criteria. Machine learning (ML) models train on existing material-property data to predict these desired outcomes. Additionally, the team can generate new polymers, whose properties are forecasted with ML models. The top candidates that meet the target property criteria are then selected for real-world validation through laboratory synthesis and testing. The results from these new experiments are integrated with the original data, further refining the predictive models in a continuous, iterative process. 

While AI can accelerate the discovery of new polymers, it also presents unique challenges. The accuracy of AI predictions depends on the availability of rich, diverse, extensive initial data sets, making quality data paramount. Additionally, designing algorithms capable of generating chemically realistic and synthesizable polymers is a complex task. 

The real challenge begins after the algorithms make their predictions: proving that the designed materials can be made in the lab and function as expected and then demonstrating their scalability beyond the lab for real-world use. Ramprasad’s group designs these materials, while their fabrication, processing, and testing are carried out by collaborators at various institutions, including Georgia Tech. Professor Ryan Lively from the School of Chemical and Biomolecular Engineering frequently collaborates with Ramprasad’s group 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."

Using AI, Ramprasad’s team and their collaborators have made significant advancements in diverse fields, including energy storage, filtration technologies, additive manufacturing, and recyclable materials.

Polymer Progress

One notable success, described in the Nature Communications paper, involves the design of new polymers for capacitors, which store electrostatic energy. These devices are vital components in electric and hybrid vehicles, among other applications. Ramprasad’s group worked with researchers from the University of Connecticut.

Current capacitor polymers offer either high energy density or thermal stability, but not both. By leveraging AI tools, the researchers determined that insulating materials made from polynorbornene and polyimide polymers can simultaneously achieve high energy density and high thermal stability. The polymers can be further enhanced to function in demanding environments, such as aerospace applications, while maintaining environmental 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.”

Industry Potential

The potential for real-world translation of AI-assisted materials development is underscored by industry participation in the Nature Reviews Materials article. Co-authors of this paper also include scientists from Toyota Research Institute and General Electric. To further accelerate the adoption of AI-driven materials development in industry, Ramprasad co-founded Matmerize Inc., a software startup company recently spun out of Georgia Tech. Their cloud-based polymer informatics software is already being used by companies across various 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.”

 

 

While the U.S. federal government has clean energy targets, they are not binding. Most economically developed countries have mandatory policies designed to bolster renewable electricity production. Because the U.S. lacks an enforceable federal mandate for renewable electricity, individual states are left to develop their own regulations. 

Marilyn Brown, Regents’ and Brook Byers Professor of Sustainable Systems in Georgia Tech’s School of Public Policy; Shan Zhou, an assistant professor at Purdue University and Georgia Tech Ph.D. alumna; and Barry Solomon, a professor emeritus of environmental policy at Michigan Technological University, investigated how clean electricity policies affect not only the states that adopt them, but neighboring states as well. Using data-driven comparisons, the researchers found that the impact of these subnational clean energy policies is far greater — and more nuanced — than previously known. 

Their research was recently published in the journal Proceedings of the National Academy of Sciences. 

“Analysts are asking if the U.S. should have a federal renewable mandate to put the whole country on the same page, or if individual state policies are sufficient,” Brown said. “To answer that question, it is useful to know if states with renewable energy policies are influencing those without them.”

Brown, Solomon, and Zhou examined a common clean energy policy tool: the Renewable Portfolio Standard (RPS). Adopted by more than half of U.S. states, RPSs are regulations requiring a state’s utility providers to generate a certain percentage of their electricity from renewable resources, such as wind or solar. Many of these standards are mandatory, with utility companies facing fines if they fail to reach targets within a given time.

To investigate the influence of these policies across state lines, the researchers first created a dataset that included 31 years (1991-2021) of annual renewable electricity generation data for 48 U.S. states and the District of Columbia. They then used the dataset to generate pairs of states linking each state to its geographic neighbors or electricity trading partners, allowing them to examine the influence of the RPS policy adopted by one of the pair on the renewable energy generation of the other — a total of 1,519 paired comparisons. 

“By only looking at the pairs, we can see if an RPS in one state directly affects renewable electricity generation in another state, and, if that’s the case, whether it is because they are geographic neighbors or if it’s because they are participating in the same wholesale electricity market,” Zhou said. 

Looking into the electricity market is important, because states often purchase electricity from other states through wholesale markets rather than exclusively producing their own power, and the purchased power can be generated from renewables. Utilities in some states may be allowed to meet their own RPS requirements by purchasing renewable energy credits based on the renewable electricity generated in other states. 

In their analyses, the team also considered the concept of “policy stringency.” A stringency measure evaluates a state’s renewable electricity targets relative to the amount currently produced in the state. For example, if a state requires electric utilities to generate 30% of their electricity from renewable sources by 2030 and the state already has 25%, it isn’t a very stringent policy. On the other hand, if a state has a 30% target and only uses 10% renewables currently, it has a more ambitious and stringent RPS.

Though policy experts have used the metric in related work for over a decade, the research team improved the design. 

“Our stringency variable includes interim targets as well as the existing share of renewable energy generation,” Solomon said.

The team found that the amount of renewable electricity generation in a state is not only influenced by whether that state has its own RPS, but also by the RPS policies of neighboring states. 

“We also learned that the stronger a neighboring state’s RPS policy is, the more likely a given state is to generate more renewable electricity,” Brown said. “It’s all a very interactive web with many co-benefits.”

The authors were surprised to find that a given state’s electricity trading partners did not hold the most influence over renewable generation, but rather the geographical proximity to RPS states. They suggest that past RPS policy research focusing on within-state impacts likely underestimated an RPS’s full impact. While the researchers have not yet identified all factors that can cause spillover effects, they plan to investigate this further. 

“The spillover effect is very significant and should not be overlooked by future research, especially for states without RPSs,” Zhou said. “For states without policies, their renewable electricity generation is very heavily influenced by their neighbors.”

Citation: Shan Zhou, Barry D. Solomon, and Marilyn A. Brown, “The spillover effect of mandatory renewable portfolio standards.” PNAS (June 2024). 
DOI: https://doi.org/10.1073/pnas.2313193121
 

 

The federally funded IAC program provides small to mid-sized industrial facilities in the region with free assessments for energy, productivity, and waste, while also supporting workforce development, recruitment, and training.

“This IAC is a great example of the ways in which Georgia Tech is serving all of Georgia and the Southeast,” said Tim Lieuwen, executive director of Georgia Tech’s Strategic Energy Institute (SEI) and Regents’ Professor and holder of the David S. Lewis, Jr. Chair in the Daniel Guggenheim School of Aerospace Engineering.

“We support numerous small and medium-sized enterprises in rural, suburban, and urban areas, bringing the technical expertise of Georgia Tech to bear in solving real-world problems faced by our small businesses.”

Georgia Tech’s IAC, which serves Georgia, South Carolina, and North Florida, is administered jointly by the George W. Woodruff School of Mechanical Engineering and the Georgia Manufacturing Extension Partnership (GaMEP), part of the Enterprise Innovation Institute (EI2). The organization has performed thousands of assessments since its inception in the 1980s – usually at rate of 15 to 20 per year – and typically identifies upwards of 10% in energy savings for clients.

The assessment team, overseen by IAC associate director Kelly Grissom, comprises faculty and student engineers from Georgia Tech and the Florida A&M University/Florida State University College of Engineering.

In addition, Georgia Tech leads the Southeastern IACs Center of Excellence, which partners the institution with fellow University System of Georgia (USG) entity Kennesaw State University, local HBCU Clark Atlanta University, and neighboring state capital HBCU Florida A&M University.

Although mechanical engineering has historically been the chief area of concentration for IAC’s interns, the program currently accepts students across a range of disciplines. “Increased diversity from that standpoint enriches the potential of the recommendations we can make,” said Grissom.

Students are integral to the program, as is Grissom’s role in facilitating their experiences with client engagement and technical recommendations.

“Kelly is the reason our program has been recognized,” said Randy Green, energy and sustainability services group manager at GaMEP. “He works tirelessly to ensure that assessments are accomplished with success for our manufacturers and students.”

“We also recognize our partnership with the Woodruff School of Mechanical Engineering and with IAC program lead Comas Haynes, Ph.D., who works diligently to keep us on track and connected with our sponsors at the U.S. Department of Energy,” Green added.

The DoE accolade represents “a ‘one Georgia Tech’ win,” symbolic of the synergistic relationships forged across the Institute, said Haynes, who also serves as the Hydrogen Initiative Lead at Georgia Tech’s Strategic Energy Institute (SEI) and Energy branch head in the Intelligent Sustainable Technologies Division at the Georgia Tech Research Institute. Haynes specifically cited Green’s “technical prowess and managerial oversight” as another key to the IAC program’s success.

Said Devesh Ranjan, Eugene C. Gwaltney, Jr. School Chair and professor in the George W. Woodruff School of Mechanical Engineering, “It is truly an honor for Georgia Tech to be named the Department of Energy Industrial (Training and) Assessment Center of the Year. Clean energy and manufacturing have been a focus for the Institute and the Woodruff School for a long time, and GTRI, EI2, and SEI have collaboratively done phenomenal work in helping manufacturers save energy, improve productivity, and reduce waste.”

To check eligibility and apply for assistance from Georgia Tech’s IAC, click here.

Christine Conwell has been named interim executive director of the Strategic Energy Institute (SEI), effective Sept. 10. 

A principal research scientist, Conwell has served as SEI’s director of planning and operations since 2020. In this role, she oversaw strategic and annual planning within SEI and partnered with campus researchers and units to create and execute strategic programs and events. Most recently, she led the development of a new five-year action plan and launched a signature initiative to build energy-focused research partnerships with historically Black colleges and universities and minority-serving institutions.  

Before her role at SEI, Conwell was managing director of the $40 million NSF-NASA Center for Chemical Evolution (CCE) in the School of Chemistry and Biochemistry, where she oversaw daily operations, fostered collaborations between 12 universities and other partners, and developed outreach and educational programs. Annually, she worked with more than 80 faculty, postdoctoral researchers, and students and advised on key opportunities to maximize the center's impact. She served as a key leader within CCE’s management team and, in 2020, she was awarded Georgia Tech’s prestigious Outstanding Achievement in the Research Enterprise Award for her leadership.

“Christine has been instrumental in the growth and expansion of the Strategic Energy Institute,” said Julia Kubanek, vice president of Interdisciplinary Research at Georgia Tech. “The strong research ties she has built as a long-standing member of the Georgia Tech research community, along with her outstanding leadership during the past few years, makes her the natural choice for SEI’s interim executive director.”

Conwell holds a B.S. in molecular biology and chemistry from Westminster College in Pennsylvania and a Ph.D. in biochemistry from Georgia Tech. She has authored several peer-reviewed manuscripts, book chapters, and grants on her research in DNA biophysics and non-viral gene delivery, and was a postdoctoral recipient of the NIH Ruth Kirschstein National Research Service Award. During her time at Georgia Tech, Conwell has served as a member of the Research Faculty Senate and the Faculty Executive Board, and she was selected as a member of the fifth Leading Women at Georgia Tech cohort.

“I am honored to serve as the interim executive director of the Strategic Energy Institute during this pivotal moment for energy research,” she said. “As we navigate an exciting period of innovation at the local, regional, and national levels, I am eager to build on our current momentum and deepen collaborations with our exceptional researchers, faculty, and staff to further advance our energy community and drive progress in the field.”

- Written by Benjamin Wright -

Yuanzhi Tang knows firsthand how much of an impact BBISS can make through its programs. The associate professor in the School of Earth and Atmospheric Sciences answered a BBISS call for faculty fellowships, and later seed funding for a project related to sustainable resources. That project grew into a collaboration with Georgia Tech’s Strategic Energy Institute; the Center for Critical Mineral Solutions (CCMS), supported by the College of Sciences and co-sponsored by BBISS; SEI; the Institute for Electronics and Nanotechnology (IEN); and the Institute for Materials (IMat and IEN are now combined into the Institute for Matter and Systems). The goal of the center is to develop sustainable solutions for the grand challenges associated with critical metals and materials essential for the clean energy transition.

During her time as a faculty fellow within BBISS, Yuanzhi became familiar with the people in the organization and had the opportunity to evaluate student and faculty fellow applications. When the opportunity arose to take on the role of associate co-director of interdisciplinary research for BBISS, she was happy to accept so she could help others access resources that had shaped her growth as a researcher at Georgia Tech.

“Being part of a community of people who value interdisciplinary research on sustainability-related topics, I benefited from the interactions and engagement with BBISS and I hope to carry that forward, particularly for young faculty. They are often eager to connect but might not know where to begin. BBISS can be a starting point for them.”

With a background in geochemistry and degrees from Peking University, Stony Brook University, and a postdoc at Harvard, Yuanzhi has gained a breadth of experience that has earned her a variety of awards and recognition. As she joins BBISS in a formal role, she has some advice for early-career colleagues.

“Go to seminars, events, and organized activities, as the best ideas often come through communicating and networking with others, and that’s how you discover that your expertise is needed in other fields. Be confident in who you are as a scholar, but also go out and find ways to collaborate. Georgia Tech places value on interdisciplinary research, and this is a unique strength that you should leverage.”

Away from the office, classroom, and lab, Yuanzhi is a wife and mother of two young children. She enjoys cuddle time with the kids and navigating parenthood in an academically driven household. Her husband is also a Georgia Tech professor and together they juggle the challenges of their careers with spending quality time with the children. “We try to keep work minimal on weekends and get out of the house and enjoy what Atlanta has to offer. We love nature and appreciate that we can be close to campus, close to the city, and still have so many green places to be outside.”

As she embarks on her new role with BBISS, Yuanzhi sees parallels between being a parent, professor, and now an administrator.

“The world is changing rapidly with the explosion of information and technology. It’s a struggle to know what to teach my kids and my students. How do we prepare them for five, 10, or even 20 years from now? This feeling of responsibility connects my work and personal life. It’s challenging, but also very exciting to see how we can help them embrace changes.”