In most every realm of scientific exploration, remarkable strides have been made at the nexus of artificial intelligence and data science. Materials science is no different, where these approaches are turning the stuff of comic book lore into real-world solutions.
At the center of this sprawling frontier lies massive data repositories–vast treasure troves of clues leading to new materials that span an awe-inspiring array of applications, like aerospace components and adaptable electronics.
The synergy between AI and materials science is transforming how we perceive and harness the infinite possibilities that the field has to offer. With this graduate certificate, you too can transform and harness that same power to contribute to a sustainable future.
Fellowships are available for graduate students training for using AI for materials science research, filling the workforce gap in this emerging field. Supported by a $3 million grant from the National Science Foundation to Duke.
This graduate certificate program will give you a vital toolkit forged through rigorous interdisciplinary study.
With the support of world-class faculty, your skills will be honed to further the boundaries pushed by AI integration in materials science.
Graduate students admitted to the certificate program will complete at least four data and material science courses. This is also an exciting opportunity to engage with computational methodology.
Duke’s aiM Certificate trains students to be ‘natives’ in AI and materials, equipping them to dramatically accelerate materials design for applications of societal impact. For example, these materials will enable next generation energy systems, the development of more resilient roads and bridges, and access to higher-quality, personalized health care.
Cate BrinsonSharon C. and Harold L. Yoh III Distinguished Professor
Confront materials design problems
Certificate holders will be trained in both materials fundamentals and data science principles and will be empowered to tackle critical problems in the field’s semi-infinite design space.
Build on your foundational knowledge
Supplement your materials science foundation with the necessary skills to evolve as a participant in the field.
Collaborate over cutting-edge research
Machine learning and materials science make it possible to be at the forefront of new material discoveries.
Certificate Requirements
Three courses and a hands-on experience:
Select one:
ME 510: Diffraction and Spectroscopy, Delaire, Offered Spring
ME 511: Computational Materials Science, Blum, Spring
ME 512: Modern Materials, Payne, Fall
ME 514: Theoretical and Applied Polymer Science, Zauscher, Fall
ME 515: Electronic Materials, Curtarolo, Spring
ME 519: Molecular Modeling of Soft Materials, Arya, Fall
ME 555 Intermediate Polymer Physics, Rubinstein, offered occasionally
ME 562: Materials Synthesis and Processing s, Mitzi, Fall
ME 563: Fundamentals of Soft Matter, Rubinstein/ Zauscher, Spring
ME 564: Introduction to Polymer Physics, Rubinstein, Fall
ME 711: Nanotechnology Materials Lab, Walters, Fall, Spring
ECE 511 Foundations of Nanoscale Science & Technology, Franklin, Fall
ECE 524 Introduction to Solid-State Physics, Brown, Fall
PHYS 516 Quantum Materials, Baranger, Fall
Select one:
ME 555-09/CEE 690 Data Science and machine learning for applied science and engineering, Carlson/Holt, Fall, Spring
COMPSCI 671D:Theory and Algorithms for Machine Learning, C. Rudin, Fall
ECE 685D: Introduction to Deep Learning, V. Tarokh, Once a year
ECE 590: Advanced Deep Learning, V. Tarokh, Once a year
ECE 590: Computer Engineering ML and Deep Neural Nets, Y. Chen/ H. Li, Once a year
ECE 682D/STA 561D: Probabilistic Machine Learning, E. Laber, Once a year
Select one:
ME 582 Data and Materials Science Applications, Brinson/Arya/ Curtarolo/ Guilleminot/ Rudin/ Lu/ Jie Liu/ Banks, Spring
ME 555: Sci Computing, Simulation and ML, Aquino, Spring
ME 555: Applications of Computational Materials, Curtarolo, Spring
Fall/Spring Data & Materials Science Capstone. 3 units
Other research project courses or independent study course with work related to machine learning and materials science may satisfy this requirement, but require pre-approval from certificate administrators and faculty team review
Internship or external research experience related to machine learning and materials science. Requires approval as 3- to 4- unit course by the Director of Graduate Studies
Apply Now
This certificate is open to all graduate students at Duke University.
You may apply for the certificate at any time during your degree program, as long as you meet the deadlines for Fall graduation (July 1) and for Spring graduation (November 1).
Assistant Research Professor in the Thomas Lord Department of Mechanical Engineering and Materials Science
This website uses cookies as well as similar tools and technologies to understand visitors' experiences. By continuing to use this website, you consent to Duke University's usage of cookies and similar technologies, in accordance with the Duke Privacy Statement.I Accept
