The program’s goal is to prepare students to use advanced computational tools and data science to “discover, innovate and engineer” new types of materials, with a specific focus on polymers. The program is modeled after Jayaraman’s own research lab, which regularly uses advanced computational tools such as molecular modeling, simulations and machine learning to address problems in soft materials and formulations (things like shampoo, toothpaste and food products). She explained that these tools are essential to making progress in these types of fields due to the sheer complexity of the problems that researchers and companies are facing.

“To make the next best material, you can do a lot of experimentation. Or you can do things much more quickly by creating appropriate models to predict material properties, then following up on the most promising ones,” Jayaraman said. “This is now how most companies who do R&D are looking at new chemicals: They want to spend less money and time on finding the right materials through experimental trial and error. Instead, they prefer to use digital models to help determine what will work best before starting work in the lab.”

Jayaraman added that another one of the program’s aims is to help bridge existing knowledge gaps between researchers in different fields. 

“What companies want is to minimize communication barriers between experts and reduce the hesitation someone might have to approach a colleague who has a different academic background,” said Jayaraman. “Having a program like NRT-MIDAS helps break down those barriers.”

Core discipline courses and interdisciplinary industry project ‘hackathon’ course

NRT-MIDAS is designed for first-year and second-year doctoral students at UD, as well as graduate students from Delaware State University, who have experience working in high-performance computing, data science and/or soft materials. Students who complete all required elements of the program receive a Graduate Certificate in Computing and Data Science for Soft Materials.

Interested students apply in November of their first year of graduate studies and are admitted into the program during the winter term. So far, the program has welcomed three cohorts: cohort 1 completed the program this past fall, cohort 2 will complete their internship or teaching course requirements this summer, and cohort 3 just began their training. 

Kelsey Koutsoukos, a second-year materials science and engineering doctoral candidate working in the lab of assistant professor and NRT core faculty member Laure Kayser, is part of the second cohort. After seeing how prominent the tools of data science were at a pharmaceutical company internship, he enrolled in NRT-MIDAS to “learn about how computational methods are used to tease out the structure property relationships in polymers before going into a lab and synthesizing them,” he said.

Kyle O’Donnell is part of the third cohort and a doctoral student in computer and information sciences working with professor Chandra Kambhamettu. Along with his prior work experience involving data science for chemical sensing applications, O’Donnell aims to get more practical knowledge in chemistry and soft materials as part of the NRT-MIDAS program. 

“By learning skills and concepts from a different discipline, a computer scientist like me can provide valuable insights for approaching a problem in this modern research landscape while also making me a more well-rounded researcher,” he said.

The doctoral students in the NRT program take a set of nine credit hours of classes, which includes three credits of courses on soft materials and/or polymers and three credits on machine learning, molecular modeling and/or simulations that provide trainees with a strong foundation in polymers, soft materials and computational tools.

Students then enroll in the program’s required three credit course Computing and Data Science for Soft Materials Innovation (CHEG/CISC/ELEG/MSEG 848), known as the “NRT Hackathon,” during the spring semester of their second year. The Hackathon has been offered since the spring of 2022, with lead instructor Jayaraman co-teaching the course in 2022 with Sunita Chandrasekaran, associate professor and David L. and Beverly J.C. Mills Career Development Chair in the computer and information sciences department, and in 2023 with Austin Brockmeier, assistant professor in electrical and computer engineering.

In the Hackathon course, students work in small teams to address a materials science or chemistry-oriented problem that is provided by an industry sponsor. As each team includes a mix of individuals with varying backgrounds — some with more computational, others more experimental or soft materials focused — completing the project successfully means that the students must find ways to communicate and collaborate across their different disciplines.

Justin Labombard, a doctoral candidate in electrical and computer engineering working with Brockmeier, is part of the second cohort and is currently taking the Hackathon course. As part of a team with Tasia Walker from the DSU chemistry program and Ana Maria Mosquera Rodriguez from UD materials science and engineering, his group is using machine learning to predict the performance of paints made by the specialty materials company Arkema.

Between his Hackathon project, as well as the work he did for his project in Jayaraman’s molecular dynamics and simulations course last fall, he explained that “a lot of diagrams and a lot of patience” are key for being a member of an interdisciplinary team. 

“If you stick with it, you both figure it out, and things start to click. It can be a repetitive, iterative process but you have to keep trying and keep communicating until it makes sense,” Labombard said.

For his Hackathon project, Koutsoukos worked with Nikhil Karthikeyan from UD materials science and engineering and Wanwei Pan from UD chemical and biomolecular engineering on understanding why malodorous molecules stick to synthetic clothing. 

“The course is great because you can see what problems industry is trying to tackle and also make connections with industry leaders,” he said. “Networking is really important, and through this class we also get to learn from the other companies as well, which is really beneficial for all of us.”

Soham Jariwala has a unique perspective: He took the Hackathon course in 2022 and this spring is a project mentor alongside Vasu Venkateshwaran from W. L. Gore. & Associates. Jariwala, a doctoral alumnus from the chemical and biomolecular engineering department and now a modeling and simulation scientist at Gore, was not officially part of the NRT program but took the course to gain hands-on experience with using machine learning tools for industry projects, an experience that he said was formative in helping him succeed in his current role.

“In a traditional classroom, you have a limited perspective on how projects are conducted in industry,” Jariwala said. “In the Hackathon class, you have a problem that even the industry experts don't know the answer to. As a team, you bring your own expertise, brainstorm ideas, find the best approach, and learn about other areas in order to reach a decision.”

Learning by doing and learning about teaching

The summer after completing the Hackathon course, students in the NRT-MIDAS program have the option of either completing a summer internship or a two-week teaching workshop.

Alison Shapiro, a chemical engineering doctoral candidate working in the lab of Allan & Myra Ferguson Distinguished Professor Thomas H. Epps, III, worked at Dow last summer as part of the company’s cable and wire department. During her time at Dow, she looked for ways to recycle and more sustainably fabricate the insulating, protective polymers that coat electrical wires and conducted life cycle assessments for candidate materials.

Shapiro said that understanding the vernacular used to talk about chemicals during the Hackathon course was extremely helpful in completing her internship projects. 

“At Dow, they had the same way of talking about [formulations] as we did in the Hackathon class, which is different from how most academic research was done,” she said. “That was one of the things that translated over the most, and I initially had no idea that it was going to be so helpful.”

Sean Farrington, who is also part of the first NRT cohort, is a doctoral candidate working under Unidel Robert L. Pigford Chair Norman Wagner and Arthur B. Metzner Professor Antony Beris. Last summer he completed a teaching workshop developed by NRT core faculty member and associate professor Joshua Enszer, which involved presentations about class preparation and teaching strategies followed by each student delivering a mock lecture and receiving constructive feedback.

Farrington, who is currently a TA in the chemical engineering department, regularly uses a list of action verbs provided by Enszer when preparing to teach. He said that the workshop was invaluable, not only for his current career plans of working in academia but because “no matter what job you have, you are always going to have to teach people something, and to do so you need to figure out exactly what your learning outcomes are,” he said.

Broadening horizons and reaching out to the community

Outside of the program’s coursework and professional development activities, NRT-MIDAS also fosters a strong sense of community that reaches across multiple departments.

This includes a biweekly NRT community hour organized by Johnston and Jayaraman, where all members of the NRT-MIDAS community get together during the lunch hour. Along with socializing over pizza, students get to hear invited speakers discuss their research in academic and national laboratories, learn about various STEM careers in industry, publishing, and teaching, and attend professional development workshops on topics such as data ethics, responsible conduct of research, and science communication.

As NRT program coordinator, Johnston plays a key role in helping foster this sense of community, from helping students become comfortable with public speaking and communication during their outreach activities to hosting monthly individual advising meetings with all of the trainees, which Johnston said is the highlight of her week.

“Not only do I enjoy getting to know our students, but they also provide valuable information on what they need from us as a program,” Johnston said. “These meetings have helped influence our professional skill community hour topics and have given us the ability to really cater to the needs of the students in our program.” 

During the summer, students work in teams to complete an outreach activity that showcases STEM research and data science concepts for a variety of non-scientific audiences.

In the summer of 2022, the first cohort created videos to help explain their research and pique other students’ interest in science.

“It was something I’d never done before, trying to distill my research down to an elementary school level,” Shapiro said. “Overall, I thought the experience was really fun — it really pushed me out of my comfort zone, and it was a good skillset to learn.”

Last summer, the second cohort worked in teams to create three comics explaining different aspects of research and life as a scientist, with artist and scientist Kara Martin creating the illustrations to bring the storylines to life. 

“It was a great project where we got to be more creative while also thinking scientifically,” said Koutsoukos, whose group created a comic explaining how data science can be used to make better plastics and polymers.

This June and July, students in cohort 3 will work in groups to develop a website with STEM-based activities for elementary and middle school students.

Learning together while looking toward the future

This NSF-supported program will enroll its fourth cohort this winter. Jayaraman adds that, thanks to many of the training activities developed in the context of NRT-MIDAS, there is support and momentum moving forward even after the end date of this NSF grant.

“The increasing engagement with scientists from leading industries — including DuPont, Dow, Merck, IFF, W. L. Gore, Arkema, and 3M — through the NRT Hackathon course and the student internships suggests that the skills the students are gaining via this program are in line with the needs of industry,” Jayaraman said. “I’m also grateful to our NRT faculty advisors, especially Dr. Kayser and Dr. Brockmeier, who encourage graduate students to be part of this program.”

For Shapiro, one of the benefits of NRT-MIDAS is the opportunity to be part of a tight-knit group of students where “everyone is learning together” outside of her own department. 

“As our work becomes more computational, being able to communicate and work with collaborators who are more computational is an invaluable skill,” added Shapiro. “I feel like I’m a lot more prepared, both confidence-wise and knowledge-wise, thanks to this program.”

“You'll gain this knowledge in a new field, and, thanks to this program, you will be able to understand it well enough to work with it,” added Labombard. “For the program being as new as it is, it’s really well-designed, it fits in well with our existing course requirements while also supporting our own research projects and ideas.”

“So far I’ve gained a greater understanding of how data science has affected the field of chemistry and soft materials,” O’Donnell said. “I hope to further this understanding going forward, and also gain some practical experience in this area of research.”

Farrington added that between the technical skills he learned, the industry connections he’s made, and the colleagues he’s met through the program, he would highly recommend it to anyone interested in the intersection of computational analysis and materials research. 

“By being part of this program, it helped me build a really nice community of people who I get along with and who I’ve learned a lot from,” he said. “You're only going to regret the opportunities that you didn't take. So, if you're thinking about doing this program, it's an absolute yes.”

In addition to funding from NSF, the NRT-MIDAS program has been supported by the four participating departments in UD’s College of Engineering (Department of Chemical and Biomolecular Engineering, Department of Computer and Information Sciences, Department of Electrical and Computer Engineering, and Department of Materials Science and Engineering), as well as UD’s Graduate College, and the Office of the Provost. This financial support has allowed the program to enroll international students as well as students from other graduate programs, such as UD’s master’s program in data science.