Building AI for Designing New Materials for Clean Energy and Chemical Transformation
Excited about using AI to design next-gen materials for clean energy and sustainable chemistry? Join our team to explore and develop cutting-edge machine learning and data science techniques!
Project description
Artificial intelligence (AI) is transforming how scientists discover new materials, especially those critical for clean energy and sustainable chemical transformations. Multicomponent crystalline materials offer remarkable versatility and promise for applications ranging from renewable energy production and storage to efficient chemical manufacturing. However, the complexity involved in predicting how atoms arrange themselves within these materials remains a fundamental barrier, limiting the discovery of optimal solutions. Traditional computational methods struggle with these complexities, necessitating advanced machine learning and data science tools such as graph neural networks.
In this project, students will develop and apply state-of-the-art AI models, specifically graph convolutional neural networks and crystal graph transformers, to learn how the arrangement of atoms (atomic ordering) affects material properties. Students will systematically evaluate whether these AI models accurately distinguish among various atomic arrangements across different crystal structures and how this can have a significant impact on designing materials for various practical applications using scientific computing and AI. Insights from this project will enable more reliable, computationally efficient AI predictions, accelerating the discovery of next-generation materials for various core technologies relevant to society.
Join us to explore cutting-edge AI methods that could revolutionize how we understand, design, and optimize new materials for energy and sustainability!
Project outcome
- Gain valuable hands-on experience in AI, data science, and materials informatics, specifically in the context of designing advanced materials for clean energy and chemical processes, and become proficient in cutting-edge machine learning methods, including graph neural networks and crystal graph transformers.
- Develop skill sets to interpret and visualize complex data, critically analyze scientific literature, and clearly communicate research findings through regular presentations in team meetings, gained through collaboration with the PI and graduate students within the research group and other top-notch research collaborators at UB and around the world.
- Have opportunities to present their work at local symposia, participate in national conferences, publish the research results in peer-reviewed journal publications, and build a track record of research experience and recommendation letters for graduate school applications.
Project details
| Length of commitment | Long (longer than a semester; 6-9 months) |
| Start time | Anytime |
| In-person, remote, or hybrid? | Hybrid Project (can be remote and/or in-person; to be determined by mentor and student) |
| Level of collaboration | Individual student project |
| Benefits | Academic credit Work study Stipend |
| Who is eligible | All undergraduate students who have experience in Python coding and linear algebra. Students showing a strong interest in machine learning, data science, and computational materials science are preferred. |
Project mentor
Jiayu Peng
Assistant Professor
Department of Materials Design and Innovation
Phone: (716) 645-5433
Email: jypeng@
Start the project
- Email the project mentor using the contact information above to express your interest and get approval to work on the project. (Here are helpful tips on how to contact a project mentor.)
- After you receive approval from the mentor to start this project, click the button to start the digital badge. (Learn more about ELN's digital badge options.)
Preparation activities
Once you begin the digital badge series, you will have access to all the necessary activities and instructions. Your mentor has indicated they would like you to also complete the specific preparation activities below. Please reference this when you get to Step 2 of the Preparation Phase.
The student should learn the basics of Python coding and linear algebra. The PI will also guide the reading of a few fundamental research papers based on this project to help the student(s) understand the background and goal of this project.
Keywords
Materials Design and Innovation, Computer Science and Engineering, Chemical and Biological Engineering, Chemistry, Physics, energy, sustainability, data science, artificial intelligence